阅读说明：本技术 一种用于无人驾驶设备远程遥控的方法及装置 (Method and device for remotely controlling unmanned equipment ) 是由 周芹 白钰 樊明宇 任冬淳 夏华夏 于 2021-09-07 设计创作，主要内容包括：本说明书公开了一种用于无人驾驶设备远程遥控的方法及装置,首先,接收无人驾驶设备发送的接管请求。其次,将传感数据输入到预先训练的风险模型中,确定接管请求对应的优先级。而后,针对每个候选远程遥控设备,根据接管请求对应的优先级,以及预先确定出的在该候选远程遥控设备对应的请求队列中当前持有的待处理请求数量的前提下所对应的平均等待时长,确定该候选远程遥控设备针对接管请求的收益值。最后,根据各候选远程遥控设备针对接管请求的收益值,通过选取出的目标远程遥控设备,对无人驾驶设备进行控制。本方法可以通过各候选远程遥控设备针对接管请求的收益值,将接管请求合理的分配给远程遥控设备,从而提高了处理接管请求的效率。(The specification discloses a method and a device for remotely controlling unmanned equipment. Secondly, inputting the sensing data into a risk model trained in advance, and determining the priority corresponding to the takeover request. And then, for each candidate remote control device, determining the profit value of the candidate remote control device for the takeover request according to the priority corresponding to the takeover request and the average waiting time corresponding to the predetermined average waiting time under the premise of the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device. And finally, controlling the unmanned equipment through the selected target remote control equipment according to the profit value of each candidate remote control equipment for the takeover request. The method can reasonably distribute the takeover request to the remote control equipment according to the profit value of each candidate remote control equipment aiming at the takeover request, thereby improving the efficiency of processing the takeover request.)

1. A method for remotely controlling an unmanned device, wherein the method is applied to the field of unmanned driving and comprises the following steps:

receiving a takeover request sent by unmanned equipment, wherein the takeover request comprises sensing data of the unmanned equipment in the current state;

inputting the sensing data into a pre-trained risk model, and determining a priority corresponding to the takeover request, wherein the priority is used for reflecting the complexity of the road condition of the road where the unmanned equipment is located currently, and the higher the complexity of the road condition is, the higher the priority is;

for each candidate remote control device, determining a profit value of the candidate remote control device for the takeover request according to the priority corresponding to the takeover request and the average waiting duration corresponding to the predetermined average waiting duration on the premise of the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device;

and selecting target remote control equipment from the candidate remote control equipment according to the profit value of the candidate remote control equipment for the takeover request, and controlling the unmanned equipment through the target remote control equipment.

2. The method of claim 1, wherein before predetermining an average wait duration corresponding to a number of pending requests currently held in a request queue corresponding to the candidate remote control device, the method further comprises:

obtaining historical data, the historical data comprising: processing the time consumed by the historical takeover request in a first working state and processing the time consumed by the historical takeover request in a second working state, wherein the first working state is used for representing that the unmanned equipment is controlled through remote control equipment, the second working state is used for representing that the unmanned equipment is controlled through the remote control equipment, and the running state of the controlled unmanned equipment is tracked and monitored, and the time consumed by processing the historical takeover request in the first working state is shorter than the time consumed by processing the historical takeover request in the second working state;

the method for determining the average waiting time length corresponding to the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device in advance specifically includes:

for each request quantity which can be held by the remote control equipment in the request queue, determining, according to the historical data, that the remote control equipment is in the first working state under the condition that the request quantity is held by the remote control equipment in the request queue, newly adding an average waiting time required by taking over the remote control equipment for processing as an average waiting time corresponding to the request quantity in the first working state, and when the remote control equipment is in the second working state under the condition that the request quantity is held by the remote control equipment in the request queue, newly adding an average waiting time required by taking over the remote control equipment for processing as an average waiting time corresponding to the request quantity in the second working state;

and determining the average waiting time corresponding to the number of the requests to be processed currently held in the request queue corresponding to the candidate remote control device according to the average waiting time corresponding to the number of the requests in the first working state and the average waiting time corresponding to the number of the requests in the second working state.

3. The method of claim 2, wherein the historical data further comprises: operating state related data, the operating state related data comprising: at least one of duration of the second operating state and operating state transition probability;

according to the average waiting time length of each request quantity in the first working state and the average waiting time length of each request quantity in the second working state, the average waiting time length corresponding to the candidate remote control device under the premise that the candidate remote control device currently holds the number of the requests to be processed is determined, and the method specifically comprises the following steps:

and determining the average waiting time corresponding to the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device according to the average waiting time corresponding to each request number in the first working state, the average waiting time corresponding to each request number in the second working state and the working state related data.

4. The method according to claim 2 or 3, wherein determining, according to the average waiting duration of each request quantity in the first operating state, the average waiting duration of each request quantity in the second operating state, and the operating state-related data, the average waiting duration corresponding to the candidate remote control device on the premise of determining the number of to-be-processed requests currently held in the request queue corresponding to the candidate remote control device specifically includes:

according to the historical data, determining the probability that the candidate remote control equipment is in the first working state under the quantity of the requests to be processed as a first state probability, and determining the probability that the candidate remote control equipment is in the second working state under the quantity of the requests to be processed as a second state probability;

and determining the average waiting time length corresponding to the candidate remote control equipment in the number of the requests to be processed according to the average waiting time length corresponding to each request number in the first working state, the average waiting time length corresponding to each request number in the second working state, the first state probability and the second state probability.

5. The method of claim 4, wherein determining, based on the historical data, a probability that the candidate remote control device is in the first working state for the number of pending requests comprises:

taking the number of the requests to be processed and the first working state as a first state combination;

and determining the probability that the candidate remote control equipment is in the first working state under the quantity of the requests to be processed according to the adjacent state combination of the first state combination, wherein the adjacent state combination of the first state combination comprises: the state combination is in the first working state, the number of the requests in the request queue is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, the state combination is in the second working state, and the state combination is in the second working state, the number of the requests in the request queue is smaller than the number of the requests to be processed, and the state combination is adjacent to the number of the requests to be processed;

according to the historical data, the probability that the candidate remote control device is in the second working state under the number of the requests to be processed specifically comprises:

taking the number of the requests to be processed and the second working state as a second state combination;

and determining the probability that the candidate remote control equipment is in the second working state under the quantity of the requests to be processed according to the adjacent state combination of the second state combination, wherein the adjacent state combination of the second state combination comprises: the state combination is in the second working state, the number of the requests in the request queue is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, the state combination is in the first working state, and the number of the requests in the request queue is larger than the number of the requests to be processed and is adjacent to the number of the requests to be processed.

6. The method according to claim 2, wherein selecting a target remote control device from the candidate remote control devices according to the profit value of the candidate remote control devices for the takeover request specifically comprises:

and selecting candidate remote control equipment of which the profit value is larger than a set profit value threshold value and the number of the requests to be processed currently held in the request queue of the candidate remote control equipment is smaller than the determined maximum receivable request number from the candidate remote control equipment as target remote control equipment according to the profit value of the candidate remote control equipment for the takeover request.

7. The method of claim 6, wherein determining the maximum number of receivable requests specifically comprises:

according to the historical data, determining the average waiting time corresponding to the takeover request when the remote control equipment is in a saturated working state, wherein the average waiting time corresponding to the takeover request is used as the average waiting time corresponding to the saturated working state, and the saturated working state is used for representing the working state corresponding to the remote control equipment when the number of the requests in the request queue reaches the maximum receivable number of the requests;

and determining the maximum receivable number according to the average waiting time corresponding to the saturated working state and the priority corresponding to the takeover request.

8. The method according to claim 7, wherein determining, according to the historical data, that the remote control device is in the saturated operating state, an average waiting duration corresponding to the takeover request as the average waiting duration corresponding to the saturated operating state specifically includes:

according to the historical data, determining the probability that the candidate remote control equipment is in the saturated working state and in the first working state as a first state saturation probability, and determining the probability that the candidate remote control equipment is in the saturated working state and in the second working state as a second state saturation probability;

and determining that the average waiting time corresponding to the takeover request is taken as the average waiting time corresponding to the saturated working state when the target remote control device is in the saturated working state according to the average waiting time corresponding to each request number in the first working state, the average waiting time corresponding to each request number in the second working state, the first state saturation probability and the second state saturation probability.

9. The method of claim 8, wherein determining, as the first state saturation probability, a probability that the candidate remote control device is in the saturated operating state and in the first operating state according to the historical data specifically includes:

combining the saturated operating state and the first operating state as a first saturated state;

and according to the adjacent state combination of the first saturated state combination, determining the probability that the candidate remote control device is in the saturated working state and in the first working state, wherein the adjacent state combination of the first saturated state combination comprises: the state combination is in the first working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, the state combination is in the second working state, and the state combination is in the second working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed;

determining, according to the historical data, a probability that the candidate remote control device is in the saturated working state and in the second working state, as a second state saturation probability, specifically including:

combining the saturated operating state and the second operating state as a second saturated state;

and determining the probability of the candidate remote control device being in the second working state when the candidate remote control device is in the saturated working state according to the adjacent state combination of the second saturated state combination, wherein the adjacent state combination of the second saturated state combination comprises: and the state combination is in the second working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed, and the number of the requests in the request queue is the same as the number of the requests to be processed and is in the first working state.

10. The method of claim 1, wherein training the risk model specifically comprises:

acquiring a training sample, wherein the training sample comprises a historical takeover request sent by the unmanned equipment and historical sensing data collected by the unmanned equipment under the condition of sending the historical takeover request;

inputting the historical takeover request into a risk model to be trained, and determining the priority corresponding to the historical takeover request;

and training the risk model by taking the minimized deviation between the priority corresponding to the historical takeover request and the label information determined by the historical sensing data as an optimization target.

11. An apparatus for remote control of an unmanned aerial device, the apparatus being for use in the field of unmanned aerial vehicles, comprising:

the system comprises a receiving module, a receiving module and a sending module, wherein the receiving module is used for receiving a take-over request sent by the unmanned equipment, and the take-over request comprises sensing data of the unmanned equipment in the current state;

the input module is used for inputting the sensing data into a pre-trained risk model and determining the priority corresponding to the takeover request, wherein the priority is used for reflecting the complexity of the road condition of the road where the unmanned equipment is located currently, and the higher the complexity of the road condition is, the higher the priority is;

a determining module, configured to determine, for each candidate remote control device, a profit value of the candidate remote control device for the takeover request according to the priority corresponding to the takeover request and an average waiting duration corresponding to a predetermined average waiting duration on the premise of a number of to-be-processed requests currently held in a request queue corresponding to the candidate remote control device;

and the control module is used for selecting target remote control equipment from the candidate remote control equipment according to the profit value of the candidate remote control equipment for the takeover request, and controlling the unmanned equipment through the target remote control equipment.

12. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 10.

13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 10 when executing the program.

Technical Field

The specification relates to the technical field of unmanned driving, in particular to a method and a device for remotely controlling unmanned equipment.

Background

In the technical field of unmanned driving, in order to ensure safe driving of the unmanned equipment, a remote driver can be used for monitoring in real time, for example, when the unmanned equipment has a fault or is in an emergency, the remote driver can temporarily take over and intervene to park the unmanned equipment nearby or drive the unmanned equipment away from the fault position.

At present, when a certain unmanned device requests remote access, if all remote control devices are in busy states, a newly added takeover request needs to be queued in a request queue corresponding to a remote control system to be processed. And allocating the takeover requests in the request queue corresponding to the remote control system to the remote control equipment in the idle state in sequence. This approach does not reasonably distribute the takeover request to the remote control device, and may cause some of the takeover requests that need to be processed preferentially to miss the optimal processing time, thereby reducing the efficiency of processing the takeover request.

Therefore, how to reasonably distribute the takeover request and improve the efficiency of processing the takeover request is an urgent problem to be solved.

Disclosure of Invention

The present specification provides a method, an apparatus, a storage medium, and an unmanned aerial vehicle for remote control of an unmanned aerial vehicle, which partially solve the above problems of the prior art.

The technical scheme adopted by the specification is as follows:

the present specification provides a method for remotely controlling an unmanned device, the method being applied to the field of unmanned driving, comprising:

receiving a takeover request sent by unmanned equipment, wherein the takeover request comprises sensing data of the unmanned equipment in the current state;

inputting the sensing data into a pre-trained risk model, and determining a priority corresponding to the takeover request, wherein the priority is used for reflecting the complexity of the road condition of the road where the unmanned equipment is located currently, and the higher the complexity of the road condition is, the higher the priority is;

for each candidate remote control device, determining a profit value of the candidate remote control device for the takeover request according to the priority corresponding to the takeover request and the average waiting duration corresponding to the predetermined average waiting duration on the premise of the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device;

and selecting target remote control equipment from the candidate remote control equipment according to the profit value of the candidate remote control equipment for the takeover request, and controlling the unmanned equipment through the target remote control equipment.

Optionally, before the average waiting duration corresponding to the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device is predetermined, the method further includes:

obtaining historical data, the historical data comprising: processing the time consumed by the historical takeover request in a first working state and processing the time consumed by the historical takeover request in a second working state, wherein the first working state is used for representing that the unmanned equipment is controlled through remote control equipment, the second working state is used for representing that the unmanned equipment is controlled through the remote control equipment, and the running state of the controlled unmanned equipment is tracked and monitored, and the time consumed by processing the historical takeover request in the first working state is shorter than the time consumed by processing the historical takeover request in the second working state;

the method for determining the average waiting time length corresponding to the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device in advance specifically includes:

for each request quantity which can be held by the remote control equipment in the request queue, determining, according to the historical data, that the remote control equipment is in the first working state under the condition that the request quantity is held by the remote control equipment in the request queue, newly adding an average waiting time required by taking over the remote control equipment for processing as an average waiting time corresponding to the request quantity in the first working state, and when the remote control equipment is in the second working state under the condition that the request quantity is held by the remote control equipment in the request queue, newly adding an average waiting time required by taking over the remote control equipment for processing as an average waiting time corresponding to the request quantity in the second working state;

and determining the average waiting time corresponding to the number of the requests to be processed currently held in the request queue corresponding to the candidate remote control device according to the average waiting time corresponding to the number of the requests in the first working state and the average waiting time corresponding to the number of the requests in the second working state.

Optionally, the history data further comprises: operating state related data, the operating state related data comprising: at least one of duration of the second operating state and operating state transition probability;

according to the average waiting time length of each request quantity in the first working state and the average waiting time length of each request quantity in the second working state, the average waiting time length corresponding to the candidate remote control device under the premise that the candidate remote control device currently holds the number of the requests to be processed is determined, and the method specifically comprises the following steps:

and determining the average waiting time corresponding to the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device according to the average waiting time corresponding to each request number in the first working state, the average waiting time corresponding to each request number in the second working state and the working state related data.

Optionally, determining, according to the average waiting duration of each request quantity in the first working state, the average waiting duration of each request quantity in the second working state, and the working state related data, the average waiting duration corresponding to the candidate remote control device on the premise that the number of to-be-processed requests currently held in the request queue corresponding to the candidate remote control device specifically includes:

according to the historical data, determining the probability that the candidate remote control equipment is in the first working state under the quantity of the requests to be processed as a first state probability, and determining the probability that the candidate remote control equipment is in the second working state under the quantity of the requests to be processed as a second state probability;

and determining the average waiting time length corresponding to the candidate remote control equipment in the number of the requests to be processed according to the average waiting time length corresponding to each request number in the first working state, the average waiting time length corresponding to each request number in the second working state, the first state probability and the second state probability.

Optionally, determining, according to the historical data, a probability that the candidate remote control device is in the first working state under the number of the requests to be processed, specifically including:

taking the number of the requests to be processed and the first working state as a first state combination;

and determining the probability that the candidate remote control equipment is in the first working state under the quantity of the requests to be processed according to the adjacent state combination of the first state combination, wherein the adjacent state combination of the first state combination comprises: the state combination is in the first working state, the number of the requests in the request queue is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, the state combination is in the second working state, and the state combination is in the second working state, the number of the requests in the request queue is smaller than the number of the requests to be processed, and the state combination is adjacent to the number of the requests to be processed;

according to the historical data, the probability that the candidate remote control device is in the second working state under the number of the requests to be processed specifically comprises:

taking the number of the requests to be processed and the second working state as a second state combination;

and determining the probability that the candidate remote control equipment is in the second working state under the quantity of the requests to be processed according to the adjacent state combination of the second state combination, wherein the adjacent state combination of the second state combination comprises: the state combination is in the second working state, the number of the requests in the request queue is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, the state combination is in the first working state, and the number of the requests in the request queue is larger than the number of the requests to be processed and is adjacent to the number of the requests to be processed.

Optionally, selecting a target remote control device from the candidate remote control devices according to the profit value of the candidate remote control devices for the takeover request, specifically including:

and selecting candidate remote control equipment of which the profit value is larger than a set profit value threshold value and the number of the requests to be processed currently held in the request queue of the candidate remote control equipment is smaller than the determined maximum receivable request number from the candidate remote control equipment as target remote control equipment according to the profit value of the candidate remote control equipment for the takeover request.

Optionally, determining the maximum number of receivable requests specifically includes:

according to the historical data, determining the average waiting time corresponding to the takeover request when the remote control equipment is in a saturated working state, wherein the average waiting time corresponding to the takeover request is used as the average waiting time corresponding to the saturated working state, and the saturated working state is used for representing the working state corresponding to the remote control equipment when the number of the requests in the request queue reaches the maximum receivable number of the requests;

and determining the maximum receivable number according to the average waiting time corresponding to the saturated working state and the priority corresponding to the takeover request.

Optionally, determining, according to the historical data, that the average waiting duration corresponding to the takeover request is in a saturated working state of the remote control device, where the average waiting duration corresponding to the saturated working state is used as the average waiting duration corresponding to the saturated working state, and specifically includes:

according to the historical data, determining the probability that the candidate remote control equipment is in the saturated working state and in the first working state as a first state saturation probability, and determining the probability that the candidate remote control equipment is in the saturated working state and in the second working state as a second state saturation probability;

and determining that the average waiting time corresponding to the takeover request is taken as the average waiting time corresponding to the saturated working state when the target remote control device is in the saturated working state according to the average waiting time corresponding to each request number in the first working state, the average waiting time corresponding to each request number in the second working state, the first state saturation probability and the second state saturation probability.

Optionally, determining, according to the historical data, a probability that the candidate remote control device is in the saturated working state and in the first working state, as a first state saturation probability, specifically including:

combining the saturated operating state and the first operating state as a first saturated state;

and according to the adjacent state combination of the first saturated state combination, determining the probability that the candidate remote control device is in the saturated working state and in the first working state, wherein the adjacent state combination of the first saturated state combination comprises: the state combination is in the first working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, the state combination is in the second working state, and the state combination is in the second working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed;

determining, according to the historical data, a probability that the candidate remote control device is in the saturated working state and in the second working state, as a second state saturation probability, specifically including:

combining the saturated operating state and the second operating state as a second saturated state;

and determining the probability of the candidate remote control device being in the second working state when the candidate remote control device is in the saturated working state according to the adjacent state combination of the second saturated state combination, wherein the adjacent state combination of the second saturated state combination comprises: and the state combination is in the second working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed, and the number of the requests in the request queue is the same as the number of the requests to be processed and is in the first working state.

Optionally, training the risk model specifically includes:

acquiring a training sample, wherein the training sample comprises a historical takeover request sent by the unmanned equipment and historical sensing data collected by the unmanned equipment under the condition of sending the historical takeover request;

inputting the historical takeover request into a risk model to be trained, and determining the priority corresponding to the historical takeover request;

and training the risk model by taking the minimized deviation between the priority corresponding to the historical takeover request and the label information determined by the historical sensing data as an optimization target.

The present specification provides an apparatus for remote control of an unmanned device, the apparatus being applied in the field of unmanned driving, comprising:

the system comprises a receiving module, a receiving module and a sending module, wherein the receiving module is used for receiving a take-over request sent by the unmanned equipment, and the take-over request comprises sensing data of the unmanned equipment in the current state;

the input module is used for inputting the sensing data into a pre-trained risk model and determining the priority corresponding to the takeover request, wherein the priority is used for reflecting the complexity of the road condition of the road where the unmanned equipment is located currently, and the higher the complexity of the road condition is, the higher the priority is;

a determining module, configured to determine, for each candidate remote control device, a profit value of the candidate remote control device for the takeover request according to the priority corresponding to the takeover request and an average waiting duration corresponding to a predetermined average waiting duration on the premise of a number of to-be-processed requests currently held in a request queue corresponding to the candidate remote control device;

and the control module is used for selecting target remote control equipment from the candidate remote control equipment according to the profit value of the candidate remote control equipment for the takeover request, and controlling the unmanned equipment through the target remote control equipment.

The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described method for remote control of an unmanned device.

The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-described method for remote control of an unmanned device when executing the program.

The technical scheme adopted by the specification can achieve the following beneficial effects:

in the method for remotely controlling the unmanned device, a takeover request sent by the unmanned device is received, wherein the takeover request comprises sensing data of the unmanned device in the current state. Secondly, inputting the sensing data into a pre-trained risk model, and determining a priority corresponding to the takeover request, wherein the priority is used for reflecting the complexity of the road condition of the road where the unmanned equipment is located at present, and the higher the complexity of the road condition is, the higher the priority is. And then, for each candidate remote control device, determining the profit value of the candidate remote control device for the takeover request according to the priority corresponding to the takeover request and the average waiting time corresponding to the predetermined average waiting time under the premise of the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device. And finally, selecting target remote control equipment from the candidate remote control equipment according to the profit value of the candidate remote control equipment for the takeover request, and controlling the unmanned equipment through the target remote control equipment.

As can be seen from the above method for remotely controlling an unmanned aerial vehicle, the method may determine the profit value of the candidate remote control device for the takeover request according to the complexity of the road condition of the road where the unmanned aerial vehicle is currently located corresponding to the takeover request and the average waiting time corresponding to the predetermined number of the requests to be processed currently held in the request queue corresponding to the candidate remote control device, and control the unmanned aerial vehicle by selecting the target remote control device satisfying the set condition. Compared with the prior art, the newly added takeover request needs to be queued in a request queue corresponding to the remote control system to wait for being processed. The method can reasonably distribute the takeover request to the remote control equipment through the income value of each candidate remote control equipment aiming at the takeover request, thereby ensuring that the takeover request can be processed in time, avoiding the takeover request needing to be processed preferentially missing the optimal processing time and further improving the efficiency of processing the takeover request.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:

FIG. 1 is a schematic flow chart diagram illustrating a method for remotely controlling an unmanned aerial vehicle according to an embodiment of the present disclosure;

fig. 2 is a schematic diagram of a takeover request processing procedure provided in an embodiment of the present specification;

FIG. 3 is a schematic structural diagram of an apparatus for remotely controlling an unmanned aerial vehicle according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an electronic device provided in an embodiment of this specification.

Detailed Description

In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.

The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic flowchart of a method for remotely controlling an unmanned aerial vehicle according to an embodiment of the present disclosure, which specifically includes the following steps:

s100: receiving a takeover request sent by the unmanned device, wherein the takeover request comprises sensing data of the unmanned device in the current state.

The execution main body for the remote control of the unmanned equipment provided by the specification can be a remote control system, and can also be terminal equipment such as a server and a desktop computer. For convenience of description, the method for remotely controlling the unmanned aerial vehicle provided in this specification will be described below with only the remote control system as an execution subject.

In this embodiment, the remote control system may receive a takeover request sent by the drone, where the takeover request mentioned herein may be used to characterize a request sent by the drone to take over the drone in the event of a failure or an emergency, where the takeover request includes sensing data of the drone in a current state. The sensing data mentioned here may be sensing data acquired by sensors such as a camera, a laser radar, a temperature and humidity sensor, an inertial measurement unit, and the like provided on the unmanned aerial vehicle, for example, image data acquired by the camera, point cloud data acquired by the laser radar, weather data acquired by the temperature and humidity sensor, attitude data acquired by the inertial measurement unit, and the like. The drone may be used to sense the environment around the drone during travel by sensing data. For example, position data of the unmanned aerial device, position data of obstacles around the unmanned aerial device, current weather conditions, current road scenes (intersections, curves, straight roads, etc.), and the like are determined.

The unmanned device referred to in this specification may refer to an unmanned vehicle, a robot, an automatic distribution device, or the like capable of realizing automatic driving. Based on this, the unmanned device to which the method for remotely controlling the unmanned device provided by the present specification is applied can be used for executing delivery tasks in the delivery field, such as business scenes of delivery such as express delivery, logistics, takeaway and the like by using the unmanned device.

S102: and inputting the sensing data into a pre-trained risk model, and determining a priority corresponding to the takeover request, wherein the priority is used for reflecting the complexity of the road condition of the road where the unmanned equipment is located at present, and the higher the complexity of the road condition is, the higher the priority is.

In this embodiment, the remote control system may input the sensing data into a risk model trained in advance, and determine a priority corresponding to the takeover request, where the priority is used to reflect a complexity of a road condition of a road on which the unmanned device is currently located, and the higher the complexity of the road condition, the higher the priority.

The remote control system can input the sensing data into a pre-trained risk model, and determine the road condition of the unmanned equipment corresponding to the takeover request at the current moment, such as weather condition, road scene, the number of surrounding obstacles, interaction condition with the surrounding obstacles, and the like. And determining the priority corresponding to the takeover request according to the road condition of the unmanned equipment corresponding to the takeover request at the current moment.

In the embodiment of the present specification, the risk model may be trained in advance through a training sample to obtain a trained risk model, and the trained risk model is deployed in a remote control system in practical application.

Firstly, a training sample is obtained, wherein the training sample comprises a historical takeover request sent by the unmanned equipment and historical sensing data collected by the unmanned equipment under the condition of sending the historical takeover request. Then, the remote control system can input the historical takeover request into a risk model to be trained, and determine the historical road condition of the unmanned equipment corresponding to the historical takeover request and label information corresponding to the historical road condition. And the remote control system determines the priority corresponding to the takeover request according to the historical road condition of the unmanned equipment corresponding to the takeover request. And finally, training the risk model by taking the deviation between the priority corresponding to the minimized historical takeover request and the label information determined through the historical sensing data as an optimization target.

Through multiple rounds of iterative training, the deviation between the priority corresponding to the historical takeover request and the label information determined through the historical sensing data can be continuously reduced and converged in a numerical range, and then the training process of the risk model is completed. The tag information mentioned here may be determined by referring to historical sensing data based on actual experience.

In the embodiments of the present specification, the risk model may have various forms, for example, a Back Propagation (BP) Neural network (CNN), etc., and the present specification does not specifically limit the risk model.

S104: and for each candidate remote control device, determining the profit value of the candidate remote control device for the takeover request according to the priority corresponding to the takeover request and the average waiting time corresponding to the predetermined average waiting time under the premise of the number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device.

In an embodiment of the present specification, the remote control system includes a plurality of remote control devices, each of which can be controlled by a remote driver to enable remote manipulation of the unmanned device.

The remote control system needs to determine in advance an average waiting time corresponding to the number of requests to be processed currently held in the request queue corresponding to the candidate remote control device. Specifically, the remote control system may first obtain historical data, where the historical data includes: processing the time length consumed by the historical takeover request in the first working state and processing the time length consumed by the historical takeover request in the second working state.

The first working state is used for representing that the unmanned equipment is controlled through the remote control equipment, and the second working state is used for representing that the unmanned equipment is controlled through the remote control equipment and tracking and monitoring the driving state of the controlled unmanned equipment.

That is, when the remote control device is in the second operating state, it is necessary to monitor the driving process of the unmanned device for a certain period of time, which is longer than the first operating state. Therefore, the time period consumed for processing the history takeover request in the first operating state is shorter than the time period consumed for processing the history takeover request in the second operating state.

Further, the remote control system may determine, according to the history data, for each request quantity that the remote control device can hold in the request queue, that, when the remote control device is in the first operating state under the condition that the request quantity is held in the request queue, an average waiting time length required for newly adding a pipe request to wait for processing by the remote control device is taken as an average waiting time length corresponding to the request quantity in the first operating state, and when the remote control device is in the second operating state under the condition that the remote control device holds the request quantity in the request queue, an average waiting time length required for newly adding a pipe request to wait for processing by the remote control device is taken as an average waiting time length corresponding to the request quantity in the second operating state.

Then, the remote control system may determine, according to the average waiting duration corresponding to each request quantity in the first operating state and the average waiting duration corresponding to each request quantity in the second operating state, the average waiting duration corresponding to the candidate remote control device on the premise that the request queue corresponding to the candidate remote control device currently contains the quantity of the requests to be processed.

In this specification embodiment, the history data may further include: operating state related data, the operating state related data comprising: a duration of the second operating state, and an operating state transition probability. The remote control system may determine, according to the average waiting duration of each request quantity in the first operating state, the average waiting duration of each request quantity in the second operating state, and the operating state-related data, the average waiting duration corresponding to the candidate remote control device on the premise of determining the number of to-be-processed requests currently held in the request queue corresponding to the candidate remote control device. As shown in particular in fig. 2.

Fig. 2 is a schematic diagram of a takeover request processing procedure provided in an embodiment of the present specification.

In fig. 2, (n, i) may be used to indicate the current integrated state of the remote control device, n may be used to indicate the number of takeover requests in the remote control device, i may be used to indicate the current operating state of the remote control device, 1 is the first operating state, and 0 is the second operating state. For example, (1, 1) may be used to indicate that the number of requests currently pending in the request queue corresponding to the remote control device is 1, and the remote control device is in the first working state. λ may be used to represent the average arrival rate of take-over requests.May be used to represent the average rate at which the first operating state processes historical takeover requests,may be used to represent the average length of time it takes to process historical takeover requests in the first operating state.May be used to represent the average rate at which the second operating state processes historical takeover requests,may be used to represent the average length of time it takes to process the historical takeover request in the second operating state.May be used to indicate the average rate at which the second operating state is maintained,may be used to represent the average duration of the second operating state.May be used to represent an operating state transition probability, i.e., a transition probability from a first operating state to a second operating state.

As can be seen from fig. 2, the operating state of the remote control device changes when the number of requests held in the request queue by the remote control device is different. For example, when the current comprehensive state of the remote control device is (1, 0), the number of the requests to be processed currently held in the request queue corresponding to the remote control device is 1, and the remote control device is in the second working state, and the average rate of the historical takeover requests is processed in the second working stateAfter processing the takeover request, the current integrated state of the remote control device becomes (0, 0). If the duration of the remote control equipment in the second working state reaches, the remote control equipment is switched from the second working state to the first working state, and the remote control equipmentBecomes (1, 1).

For another example, when the current comprehensive state of the remote control device is (2, 1), the number of the requests to be processed currently held in the request queue corresponding to the remote control device is 2, and the remote control device is in the first working state, and the average rate of the historical takeover requests is processed in the first working stateAfter the takeover request is processed, the current comprehensive state of the remote control equipment has the working state transition probabilityAnd changes from the first operating state to the second operating state to (1, 0). The current comprehensive state of the remote control equipment also has the working state transition probabilityStill in the first operating state, the state becomes (1, 1).

Further, the remote control system may determine an average waiting time period corresponding to each integrated state of the remote control device, determine an average waiting time period corresponding to each request number in the first operating state, and determine an average waiting time period corresponding to each request number in the second operating state. Specifically, the following formula can be referred to:

in the above formula, when the current integrated state of the remote control device is (0, 0), the last takeover request may still be processed. Because there is no pending request in the request queue corresponding to the remote control device and the remote control device is in the second working state, the current working state of the remote control device may be the second working state to process the previous takeover request, or the first working state to process the previous takeover request. And average duration in the second operating stateAfter the process is finished, if a takeover request is newly added, the remote control equipment immediately changes to a first working state.

That is, the total length of time that the current integrated state of the remote control device exists may be considered to be. And, average durationIs the length of time that the remote control device must be in the second operating state. Therefore, the temperature of the molten metal is controlled,may be used to indicate the duration of time that the remote control device is in the first operational state. Further, in the above-mentioned case,the method can be used for representing the probability that the remote control device does not have the pending request in the request queue corresponding to the remote control device and is in the first working state. In the same way as above, the first and second,may be used to indicate the duration of time that the remote control device is in the second operational state.Can be used to represent the probability that the request queue corresponding to the remote control device has no pending request and is in the second working state. Therefore, the temperature of the molten metal is controlled,the method and the device can be used for indicating that the request queue corresponding to the remote control device does not have the request to be processed and is in the second working state, and adding the average waiting time required by the takeover request to wait for the remote control device to process.

In the above formula, when the current integrated state of the remote control device is (1, 1), the last takeover request may still be processed, and therefore,may be used to represent the average length of time that the remote control device has consumed processing the last takeover request in the first operating state.Can be used to indicate that the remote control device hasIs converted from the current state (1, 1) to (0, 0), continuing to process the average duration of time spent taking over requests.Can be used to indicate that the remote control device hasThe first operating state is maintained and the average duration of time spent in taking over requests is processed in the first operating state. Therefore, the temperature of the molten metal is controlled,the method and the device can be used for indicating that the number of the requests to be processed currently in the request queue corresponding to the remote control device is 1, and when the request queue is in the first working state, the average waiting time required for the newly added takeover request to wait for the remote control device to process is increased.

Further, in the above-mentioned case,can indicate that the number of the requests currently held to be processed in the request queue corresponding to the remote control equipment isAnd is in an operating stateAnd then, newly adding an average waiting time for the takeover request to wait for the processing of the remote control equipment. Specifically, the following formula can be referred to:

in the above formula, when the current integrated state of the remote control device isThe last takeover request may still be in process, and therefore,may be used to represent the average length of time that the remote control device has consumed processing the last takeover request in the first operating state.Can be used to indicate that the remote control device hasIs converted from the current state (n, 1) toThe average length of time spent taking over requests continues to be processed.Can be used to indicate that the remote control device hasIs maintained in the first operating state, with the first operating stateThe average length of time spent processing takeover requests.Can indicate that the number of the requests currently held to be processed in the request queue corresponding to the remote control equipment isAnd when the remote control equipment is in the first working state, newly adding a take-over request to wait for the average waiting time required by the processing of the remote control equipment.

In the above formula, when the current integrated state of the remote control device isThe last takeover request may still be in process, and therefore,may be used to indicate the average length of time it takes for the remote control device to process the last takeover request in the second operational state,can be used for representing remote control equipmentThe probability of processing the last takeover request in the second operational state.Can be used to indicate that the remote control device hasIs converted from the current state (n, 0) toThe average length of time spent taking over requests continues to be processed.Can be used to indicate that the remote control device hasIs converted from the current state (n, 0) toThe average length of time spent taking over requests continues to be processed.Can indicate that the number of the requests currently held to be processed in the request queue corresponding to the remote control equipment isAnd when the remote control equipment is in the second working state, newly adding a take-over request to wait for the average waiting time required by the processing of the remote control equipment.

In this specification embodiment, the remote control system may determine, as the first state probability, a probability that the candidate remote control device is in the first working state in the number of requests to be processed, and as the second state probability, a probability that the candidate remote control device is in the second working state in the number of requests to be processed, based on the history data. And determining the average waiting time length corresponding to the candidate remote control equipment in the number of the requests to be processed according to the average waiting time length corresponding to each request number in the first working state, the average waiting time length corresponding to each request number in the second working state, the first state probability and the second state probability.

In the illustrated embodiment, the takeover request process of FIG. 2 can be viewed as a finite state Markov chain, where there is a steady state profile at each time, and each of the composite states of the remote control deviceThe transitions between are all in equilibrium. For example, the remote control device currently has a general state ofRemote control device from the current state of integrationChange to other state, and change to current integrated state with other stateIs balanced between them.

In the embodiment of the present specification, the remote control device may combine the number of pending requests and the first operating state as the first state. And then determining the probability that the candidate remote control equipment is in the first working state under the quantity of the requests to be processed according to the adjacent state combination of the first state combination.

Wherein the adjacent state combinations of the first state combination include: the state combination is in a first working state, the number of the requests in the request queue is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, the state combination is in a second working state, and the number of the requests in the request queue is smaller than the number of the requests to be processed, and the state combination is adjacent to the number of the requests to be processed.

Taking FIG. 2 as an example, if the first state combination isThe first state combinationThe adjacent state combinations of (1) include: in the first working state, the state combination of the request quantity in the request queue and the quantity of the requests to be processed which are adjacent is、The number of requests in the request queue is the same as the number of requests to be processed, and the state combination in the second working state isAnd in a second working state, the number of requests in the request queue is less than the number of requests to be processed, and the states adjacent to the number of requests to be processed are combined into。

The remote control system may determine, according to each first state combination, a probability that the candidate remote control device is in the first working state under the number of the requests to be processed, and may specifically refer to the following formula:

in the above-mentioned formula,can be used to representAverage rate of processing takeover requests in a first operating stateProcessing a takeover request, converting intoAnd adding a takeover request at the average arrival rate lambda of the takeover requests, and converting into。Can be used to representAdding a takeover request at the average arrival rate lambda of the takeover request, and converting the takeover request into a takeover request。Can be used to representTo maintain the average rate of the second operating stateSwitching from the second operating state to the first operating state。Can be used to representIs provided withTo a first operating state to process the average rate of takeover requestsProcessing a takeover request, converting into。

Wherein, as can be seen from fig. 2, the current comprehensive state of the remote control device isThe special state can be referred to the following formula:

in the above-mentioned formula,can be used to representAverage rate of processing takeover requests in a first operating stateProcessing a takeover request, converting intoAnd adding a takeover request at the average arrival rate lambda of the takeover requests, and converting into。Can be used to representTo maintain the average rate of the second operating stateSwitching from the second operating state to the first operating state。Can be used to representIs provided withTo a first operating state to process the average rate of takeover requestsIs converted into。

In the embodiment of the present specification, the remote control device may combine the number of pending requests and the second operation state as the second state. And then determining the probability that the candidate remote control equipment is in the second working state under the quantity of the requests to be processed according to the adjacent state combination of the second state combination.

Wherein the adjacent state combinations of the second state combinations include: the state combination is in the second working state, the number of the requests in the request queue is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, and the state combination is in the first working state, and the number of the requests in the request queue is larger than the number of the requests to be processed, and the state combination is adjacent to the number of the requests to be processed.

Taking FIG. 2 as an example, if the first state combination isThe second state combinationThe adjacent state combinations of (1) include: in the second working state, the state combination of the request quantity in the request queue and the quantity of the requests to be processed which are adjacent is、The number of requests in the request queue is the same as the number of requests to be processed, and the state combination in the first working state isAnd in the first working state, the number of requests in the request queue is greater than the number of requests to be processed, and the states adjacent to the number of requests to be processed are combined into。

The remote control system may determine, according to each second state combination, a probability that the candidate remote control device is in the first working state under the number of the requests to be processed, and may specifically refer to the following formula:

in the above-mentioned formula,can be used to representAdding a takeover request at the average arrival rate lambda of the takeover request, and converting the takeover request into a takeover requestAnd processing the average rate of takeover requests in the second operating stateIs converted intoAlso at an average rate to maintain the second operating stateSwitching from the second operating state to the first operating state。Can be used to representAdding a takeover request at the average arrival rate lambda of the takeover request, and converting the takeover request into a takeover request。Can be used to representAverage rate of processing takeover requests in the second operating stateProcessing a takeover request, converting into。Can be used to representIs provided withTo a first operating state to process the average rate of takeover requestsProcessing a takeover request, converting into. It can be seen from the above description that the transition of the remote control device from the current state to the other state is balanced with the transition of the other state to the current state.

Wherein, as can be seen from fig. 2, the current comprehensive state of the remote control device isThe special state can be referred to the following formula:

in the above-mentioned formula,can be used to representAdding a takeover request at the average arrival rate lambda of the takeover request, and converting the takeover request into a takeover request。Can be used to representAverage rate of processing takeover requests in the second operating stateProcessing a takeover request, converting into。Can be used forTo representAverage rate of processing takeover requests in a first operating stateProcessing a takeover request, converting into。

In this embodiment, the remote control system may determine the probability that the remote control device is in the first working state in the number of pending requests according to the probability that the remote control device is in the first working state in each number of pending requests. Specifically, the following formula can be referred to:

in the above-mentioned formula,may be used to indicate that the remote control device is in a steady state profile in the first operating state. By the formula corresponding to the conversion between each comprehensive state of the remote control equipment, the remote control equipment can obtainThe following conditions need to be satisfied:

the aboveCan be regarded as a unitary quartic equation, since the final requirement is solvedTherefore, it is required toThe above conditions are satisfied, that is, only in the case where the above conditions are satisfied,will have a solution, correspondingly, finally solvedIt is understood that the resulting probability that the remote control device is in the first operational state for the number of pending requests is under the constraints of the above conditions.

In this embodiment, the remote control system may determine the probability that the remote control device is in the second working state in the number of pending requests according to the probability that the remote control device is in the second working state in each number of pending requests. Specifically, the following formula can be referred to:

in the above-mentioned formula,may be used to indicate that the remote control device is in a steady state profile in the second operating state. By the formula corresponding to the conversion between each comprehensive state of the remote control equipment, the remote control equipment can obtainThe following conditions need to be satisfied:

the aboveCan be regarded as a unitary quartic equation, since the final requirement is solvedTherefore, it is required toThe above conditions are satisfied, that is, only in the case where the above conditions are satisfied,will have a solution, correspondingly, finally solvedIt is understood that the resulting probability that the remote control device is in the second operational state for the number of pending requests is under the constraints of the above conditions.

Further, the remote control system may determine, according to the average waiting duration corresponding to each request quantity in the first operating state, the average waiting duration corresponding to each request quantity in the second operating state, the first state probability, and the second state probability, the average waiting duration corresponding to the candidate remote control device in the pending request quantity. Specifically, the following formula can be referred to:

in the above-mentioned formula,can be used to indicate that the candidate remote control device is in the first working state under the number of the pending requestsThe probability of (c).May be used to represent the probability that the candidate remote control device is in the second operational state for the number of pending requests. From the above formula, it can be seen thatMay be used to indicate the average wait time required for a newly added takeover request to wait for processing by the remote control device without knowing whether the candidate remote control device is currently in the first operating state or the second operating state.

It should be noted that when the number of pending requests currently held in the request queue of the remote control device reaches the maximum acceptable number, the remote control device does not receive any takeover request. As can be seen from fig. 2, the adjacent state combinations corresponding to the time when the number of pending requests currently held in the request queue of the remote control device reaches the maximum acceptable number are different from the adjacent state combinations corresponding to the time when the number of pending requests currently held in the request queue of the remote control device does not reach the maximum acceptable number. Therefore, when the number of the requests to be processed currently held in the request queue of the remote control device reaches the maximum acceptable number, the average waiting time required for the newly added takeover request to wait for the remote control device to process needs to be analyzed separately.

In the embodiments of the present description, the remote control system may combine the saturated operating state and the first operating state as the first saturated state. And then, determining the probability of the candidate remote control device in the first working state when the candidate remote control device is in the saturated working state according to the adjacent state combination of the first saturated state combination. The saturated operating state mentioned here is used to represent the operating state corresponding to the remote control device when the number of requests in the request queue reaches the maximum number of receivable requests, for example, if the maximum number of receivable requests in the request queue of the remote control device is 5, when the number of requests to be processed in the request queue of the remote control device reaches 5, it is determined that the remote control device is in the saturated operating state.

Wherein the adjacent state combinations of the first saturated state combination include: the state combination is in a first working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, and is in a second working state, and the state combination is in the second working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed.

Taking FIG. 2 as an example, when the number of pending requests in the request queue of the remote control device reaches the maximum acceptable number, the method is appliedTo indicate that the number of pending requests in the request queue of the remote control device reaches a maximum acceptable number. If the first saturation state combination isFirst combination of saturated statesThe adjacent state combinations of (1) include: in the first working state, the number of the requests in the request queue is less than the number of the requests to be processed, and the state adjacent to the number of the requests to be processed is combined intoThe number of requests in the request queue is the same as the number of requests to be processed, and the state combination in the second working state isAnd in a second working state, the number of requests in the request queue is less than the number of requests to be processed, and the states adjacent to the number of requests to be processed are combined into。

The remote control system may determine, by using an adjacent state combination of the first saturated state combination, a probability that the candidate remote control device is in the saturated operating state and in the first operating state, specifically referring to the following formula:

in the above-mentioned formula,which may be used to represent the maximum acceptable number of pending requests in the request queue of the remote control device.Can be used to representAverage rate of processing takeover requests in a first operating stateProcessing a takeover request, converting into。Can be used to representAdding a takeover request at the average arrival rate lambda of the takeover request, and converting the takeover request into a takeover request。Can be used to representTo maintain the average rate of the second operating stateSwitching from the second operating state to the first operating state。

In the embodiments of the present description, the remote control system may combine the saturated operating state and the second operating state as the second saturated state. And then, determining the probability of the candidate remote control device being in the second working state when the candidate remote control device is in the saturated working state according to the adjacent state combination of the second saturated state combination.

Wherein the adjacent state combinations of the second saturated state combinations include: and the state combination is in the second working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed, and the number of the requests in the request queue is the same as the number of the requests to be processed and is in the first working state.

Taking FIG. 2 as an example, if the second saturation state is combined asSecond combination of saturated statesThe adjacent state combinations of (1) include: in the second working state, the number of the requests in the request queue is less than the number of the requests to be processed, and the state adjacent to the number of the requests to be processed is combined intoThe number of requests in the request queue is the same as the number of requests to be processed, and the state combination in the first working state is。

The remote control system may determine, by using an adjacent state combination of the second saturated state combination, a probability that the candidate remote control device is in the second working state when being in the saturated working state, specifically referring to the following formula:

in the above-mentioned formula,can be used to representAverage rate of processing takeover requests in the second operating stateProcessing a takeover request, converting intoAnd at an average rate to maintain the second operating stateSwitching from the second operating state to the first operating state。Can be used to representAdding a takeover request at the average arrival rate lambda of the takeover request, and converting the takeover request into a takeover request. From the above descriptionIt can be seen that when the number of pending requests in the request queue of the remote control device reaches the maximum acceptable number, the current state is changed to another state, and the current state is changed to another state.

In an embodiment of the present description, the remote control system may determine a probability of being in a saturated operating state and being in a first operating state. Specifically, the following formula can be referred to:

in the above-mentioned formula,may be used to indicate the probability that the remote control system may determine that it is in the saturated operating state and in the first operating state.

In an embodiment of the present description, the remote control system may determine a probability of being in a saturated operating state and being in a second operating state. Specifically, the following formula can be referred to:

in the above-mentioned formula,may be used to indicate the probability that the remote control system may determine that it is in a saturated operating state and in a second operating state.

Further, the remote control system may determine that the target remote control device is in the saturated operating state according to the average waiting duration corresponding to each request quantity in the first operating state, the average waiting duration corresponding to each request quantity in the second operating state, the first state saturation probability, and the second state saturation probability, and take over the average waiting duration corresponding to the request as the average waiting duration corresponding to the saturated operating state. Specifically, the following formula can be referred to:

in the above-mentioned formula,may be used to represent the probability of being in the first operating state when the number of pending requests currently held in the request queue of the remote control device reaches the maximum acceptable number (in the saturated operating state).May be used to represent the probability of being in the second operating state when the number of pending requests currently held in the request queue of the remote control device reaches the maximum acceptable number (in the saturated operating state). From the above formula, it can be seen thatThe method can be used for indicating that when the number of the to-be-processed requests currently held in the request queue of the remote control device is determined to reach the maximum acceptable number, under the condition that whether the candidate remote control device is currently in the first working state or the second working state is unknown, the average waiting time required for the takeover request to wait for the remote control device to process is increased.

In practical applications, the best processing time is not missed in order to avoid taking over requests. The remote control system may determine a revenue value for each candidate remote control device to which the takeover request corresponds. The benefit value referred to herein is a measure of how long it will wait for a takeover request to be processed. And if the profit value is larger than the set profit value threshold value, the remote control equipment is considered to be capable of processing the pipe connection request in time. The higher the profit value is, the shorter the time required for the remote control system to process the takeover request is, and conversely, the lower the profit value is, the longer the time required for the remote control system to process the takeover request is.

Further, if the profit value is smaller than the set profit value threshold, the remote control device is considered to be unable to process the pipe connection request in time. The set profit margin threshold mentioned herein may be set manually. Specifically, the following formula can be referred to:

in the above-mentioned formula,may be used to represent a revenue value for the processing of the takeover request at the candidate remote control device for measuring the remaining time period for which the takeover request is to be processed.May be used to represent a preset base value of revenue, where the base value of revenue referred to herein may be set manually, with each takeover request corresponding to the same base value of revenue.May be used to indicate the corresponding priority of the takeover request.Can be used to represent the average waiting time required by the remote control device to wait for the remote control device to process when the number of the takeover requests is n. It can be seen from the above formula that, in order to ensure that the remote control device can process the takeover request in time, the higher the priority corresponding to the takeover request is, the smaller the number of takeover requests corresponding to the remote control device is.

Of course, the remote control system may also determine the profit value of each candidate remote control device corresponding to the takeover request directly according to the average waiting time corresponding to the number of the requests to be processed currently in the request queue corresponding to the candidate remote control device. Specifically, the following formula can be referred to:

it can be seen from the above formula that the profit value of each candidate remote control device corresponding to the takeover request is only related to the takeover request number corresponding to the remote control device, and the smaller the takeover request number corresponding to the remote control device is, the higher the priority corresponding to the takeover request is.

S106: and selecting target remote control equipment from the candidate remote control equipment according to the profit value of the candidate remote control equipment for the takeover request, and controlling the unmanned equipment through the target remote control equipment.

In this embodiment, the remote control system may select a target remote control device from the candidate remote control devices according to a profit value of each candidate remote control device for the takeover request, and control the unmanned device through the target remote control device.

In practical application, in order to improve the processing efficiency of each remote control device in processing the takeover request, the remote control system may select the remote control device with the highest profit value from the profit values of each remote control device corresponding to the takeover request, so as to process the takeover request.

In the embodiment of the present specification, according to the profit value of each candidate remote control device for the takeover request, a candidate remote control device whose profit value is greater than a set profit value threshold and whose number of requests to be processed currently held in the request queue of each candidate remote control device is less than the determined maximum receivable number of requests is selected from each candidate remote control device as the target remote control device.

In practical application, the average waiting time required for the remote control device to wait for the remote control device to process due to the newly added takeover request under the normal condition of the remote control device is different from the average waiting time required for the remote control device to wait for the remote control device to process due to the newly added takeover request under the saturated working state of the remote control device. It may occur that the take-over request is greater than the set benefit value threshold at the remote control device, but the remote control device is already in a saturated operating state. Thus, the remote control system also needs to determine the maximum acceptable number of pending requests currently held in the remote control device request queue during the process of allocating takeover requests.

In this embodiment, the remote control system may determine, according to the historical data, that the remote control device is in the saturated operating state, and take over an average waiting duration corresponding to the request, as the average waiting duration corresponding to the saturated operating state, where the saturated operating state is used to represent an operating state corresponding to the remote control device when the number of requests in the request queue reaches the maximum number of receivable requests. And the remote control system determines the maximum receivable number according to the average waiting time corresponding to the saturated working state and the priority corresponding to the takeover request. Specifically, the following formula can be referred to:

in the above-mentioned formula,can be used for indicating that the number of the pending requests currently held in the remote control equipment request queue reaches the maximum acceptable numberAnd newly adding the average waiting time for the remote control equipment to wait for processing by the pipe request. As can be seen from the above equation, when the revenue value of the takeover request processed at the remote control device is equal to the set revenue value threshold, i.e., when the takeover request is processed at the remote control deviceThe maximum acceptable number can be determined。

The method can determine the profit value of the candidate remote control device for the takeover request according to the complexity of the road condition of the road where the unmanned device corresponding to the takeover request is located and the average waiting time corresponding to the predetermined number of the to-be-processed requests currently held in the request queue corresponding to the candidate remote control device, and controls the unmanned device through the selected target remote control device meeting the set condition. Compared with the prior art, the newly added takeover request needs to be queued in a request queue corresponding to the remote control system to wait for being processed. The method can reasonably distribute the takeover request to the remote control equipment through the income value of each candidate remote control equipment aiming at the takeover request, thereby ensuring that the takeover request can be processed in time, avoiding the takeover request needing to be processed preferentially missing the optimal processing time and further improving the efficiency of processing the takeover request.

Based on the same idea, the method for remotely controlling the unmanned equipment provided by one or more embodiments of the present specification also provides a corresponding device for remotely controlling the unmanned equipment, as shown in fig. 3.

Fig. 3 is a schematic structural diagram of an apparatus for remotely controlling an unmanned device according to an embodiment of the present disclosure, where the apparatus is applied to the field of unmanned, and specifically includes:

the receiving module 300 is configured to receive a takeover request sent by an unmanned aerial vehicle, where the takeover request includes sensing data of the unmanned aerial vehicle in a current state;

an input module 302, configured to input the sensing data into a pre-trained risk model, and determine a priority corresponding to the takeover request, where the priority is used to reflect a complexity of a road condition of a road where the unmanned device is currently located, and the higher the complexity of the road condition is, the higher the priority is;

a determining module 304, configured to determine, for each candidate remote control device, a profit value of the candidate remote control device for the takeover request according to the priority corresponding to the takeover request and an average waiting duration corresponding to a predetermined number of to-be-processed requests currently held in a request queue corresponding to the candidate remote control device;

a control module 306, configured to select a target remote control device from the candidate remote control devices according to the profit value of the candidate remote control devices for the takeover request, and control the unmanned device through the target remote control device.

Optionally, the determining module 304 is specifically configured to obtain historical data, where the historical data includes: processing the time consumed by the historical takeover request in a first working state and processing the time consumed by the historical takeover request in a second working state, wherein the first working state is used for representing that the unmanned equipment is controlled by the remote control equipment, the second working state is used for representing that the unmanned equipment is controlled by the remote control equipment and tracking and monitoring the running state of the controlled unmanned equipment, the time consumed by processing the historical takeover request in the first working state is less than the time consumed by processing the historical takeover request in the second working state, and for each request quantity which can be held by the remote control equipment in a request queue, when the remote control equipment is determined to be in the first working state under the condition that the request quantity is held in the request queue according to the historical data, and when the remote control device is in the second working state under the condition that the request quantity is held in the request queue, newly adding an average waiting time length required by the remote control device for waiting the remote control device for processing, wherein the average waiting time length is taken as the average waiting time length required by the remote control device for waiting the remote control device for processing, and the average waiting time length is taken as the average waiting time length corresponding to the request quantity in the second working state, and determining the average waiting time length corresponding to the candidate remote control device under the condition that the request quantity to be processed is held in the request queue corresponding to the candidate remote control device currently according to the average waiting time length corresponding to each request quantity in the first working state and the average waiting time length corresponding to each request quantity in the second working state.

Optionally, the history data further comprises: operating state related data, the operating state related data comprising: at least one of duration of the second operating state and operating state transition probability;

the determining module 304 is specifically configured to determine, according to the average waiting duration of each request quantity in the first working state, the average waiting duration of each request quantity in the second working state, and the working state related data, the average waiting duration corresponding to the candidate remote control device on the premise that the number of to-be-processed requests currently held in the request queue corresponding to the candidate remote control device is determined.

Optionally, the determining module 304 is specifically configured to determine, according to the historical data, a probability that the candidate remote control device is in the first working state in the number of the to-be-processed requests as a first state probability, and a probability that the candidate remote control device is in the second working state in the number of the to-be-processed requests as a second state probability, and determine, according to an average waiting duration corresponding to each request number in the first working state, an average waiting duration corresponding to each request number in the second working state, the first state probability, and the second state probability, an average waiting duration corresponding to the candidate remote control device in the number of the to-be-processed requests.

Optionally, the determining module 304 is specifically configured to use the number of the to-be-processed requests and the first working state as a first state combination, and determine, according to an adjacent state combination of the first state combination, a probability that the candidate remote control device is in the first working state under the number of the to-be-processed requests, where the adjacent state combination of the first state combination includes: the method comprises the following steps of being in a first working state, state combinations with the number of requests in a request queue adjacent to the number of requests to be processed, state combinations with the number of requests in the request queue identical to the number of requests to be processed and in a second working state, and state combinations with the number of requests in the request queue smaller than the number of requests to be processed and adjacent to the number of requests to be processed, wherein the number of requests to be processed and the second working state are used as second state combinations, and the probability that the candidate remote control equipment is in the second working state under the number of requests to be processed is determined according to the adjacent state combinations of the second state combinations, wherein the adjacent state combinations of the second state combinations comprise: the state combination is in the second working state, the number of the requests in the request queue is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, the state combination is in the first working state, and the number of the requests in the request queue is larger than the number of the requests to be processed and is adjacent to the number of the requests to be processed.

Optionally, the control module 306 is specifically configured to, according to the profit value of each candidate remote control device for the takeover request, select, as the target remote control device, a candidate remote control device from the candidate remote control devices, where the profit value is greater than a set profit value threshold, and a number of requests to be processed currently held in a request queue of each candidate remote control device is smaller than the determined maximum receivable number of requests.

Optionally, the control module 306 is specifically configured to determine, according to the historical data, that the remote control device is in a saturated working state, where the average waiting duration corresponding to the takeover request is used as the average waiting duration corresponding to the saturated working state, and the saturated working state is used to represent a working state corresponding to the remote control device when the number of requests in the request queue reaches the maximum receivable number, and determine the maximum receivable number according to the average waiting duration corresponding to the saturated working state and the priority corresponding to the takeover request.

Optionally, the control module 306 is specifically configured to determine, according to the historical data, a probability that the candidate remote control device is in the saturated working state and in the first working state as a first state saturation probability, a probability that the candidate remote control device is in the saturated working state and in the second working state as a second state saturation probability, and determine, according to an average waiting duration corresponding to each request quantity in the first working state, an average waiting duration corresponding to each request quantity in the second working state, the first state saturation probability, and the second state saturation probability, that the target remote control device is in the saturated working state, an average waiting duration corresponding to the takeover request as an average waiting duration corresponding to the saturated working state.

Optionally, the control module 306 is specifically configured to use the saturated operating state and the first operating state as a first saturated state combination, and determine, according to an adjacent state combination of the first saturated state combination, a probability that the candidate remote control device is in the saturated operating state and in the first operating state when the candidate remote control device is in the saturated operating state, where the adjacent state combination of the first saturated state combination includes: in the first working state, the number of requests in the request queue is less than the number of requests to be processed, and the state combination is adjacent to the number of the requests to be processed, the number of the requests in the request queue is the same as the number of the requests to be processed, and the state combination is in the second working state, and in the second working state, the number of requests in the request queue is less than the number of requests to be processed, and the state combinations adjacent to the number of the requests to be processed are used as the second saturation state combination, determining that the candidate remote control device is in the saturated operating state based on the adjacent state combination of the second saturated state combination, and a probability of being in the second operating state, wherein a neighboring state combination of the second saturated state combination comprises: and the state combination is in the second working state, the number of the requests in the request queue is smaller than the number of the requests to be processed and is adjacent to the number of the requests to be processed, and the number of the requests in the request queue is the same as the number of the requests to be processed and is in the first working state.

Optionally, the apparatus further comprises:

the training module 508 is configured to obtain a training sample, where the training sample includes a historical takeover request sent by the drone and historical sensing data acquired by the drone when the historical takeover request is sent, input the historical takeover request into a risk model to be trained, determine a priority corresponding to the historical takeover request, and train the risk model with minimizing a deviation between the priority corresponding to the historical takeover request and label information determined by the historical sensing data as an optimization target.

The present specification also provides a computer readable storage medium having stored thereon a computer program operable to execute the method for remotely controlling an unmanned aerial device as provided in fig. 1 above.

This specification also provides a schematic block diagram of an electronic device corresponding to that of figure 1, shown in figure 4. As shown in fig. 4, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads a corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the method for remotely controlling an unmanned aerial vehicle described above with reference to fig. 1. Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.