阅读说明：本技术 用于运行自动化车辆的方法和设备 (Method and device for operating an automated vehicle ) 是由 S·阿拉蒙 S·拉乌 N·富尼耶 T·万多梅莱 U·威廉 于 2020-02-10 设计创作，主要内容包括：一种用于运行自动化车辆的方法,包括以下步骤：感测车辆的环境；提供所感测的环境的环境数据；环境数据被馈送给状况感测装置,该状况感测装置具有大于一的限定数量的状况感测元件；借助状况感测元件对车辆的环境进行计算建模；使用状况感测元件的模型的输出数据来操控驾驶员辅助系统；借助决策装置决策：将状况感测元件的模型的哪些输出数据用于对车辆的促动装置进行操控；使用决策出的输出数据来操控车辆的促动装置。(A method for operating an automated vehicle, comprising the steps of: sensing an environment of a vehicle; providing environmental data of the sensed environment; the environmental data is fed to a condition sensing device having a defined number of condition sensing elements greater than one; computationally modeling an environment of the vehicle with the condition sensing element; using output data of the model of the condition sensing element to steer the driver assistance system; deciding by means of a decision means: using which output data of the model of the condition sensing element for operating an actuating device of the vehicle; using the determined output data to operate an actuation device of the vehicle.)

1. A method for operating an automated vehicle, the method having the steps of:

-sensing an environment of the vehicle;

-providing environment data (20) of the sensed environment;

-feeding a condition sensing device (50) with a defined number of condition sensing elements (51a … … 51n) greater than one with said environmental data (20);

-computationally modelling an environment of the vehicle by means of the condition sensing elements (51a … … 51 n);

-using output data of a model of the condition sensing element (51a … … 51n) for steering of a driver assistance system (30a … … 30 n);

-deciding by means of decision means (61): -using which output data of the model of the condition sensing element (51a … … 51n) for manipulating an actuating device (40) of the vehicle; and

-using the decided output data to operate the actuation means (40) of the vehicle.

2. The method of claim 1, wherein the models of the condition sensing elements (51a … … 51n) are solved synchronously independently of each other, wherein the models of the condition sensing elements (51a … … 51n) at least partially overlap.

3. The method according to claim 1 or 2, wherein the driver assistance systems (30a … … 30n) are implemented independently and synchronously with each other.

4. The method according to any one of the preceding claims, characterized in that different condition sensing elements (51a … … 51n) are provided with different data by sensors of the environmental sensor device (10).

5. The method according to any one of the preceding claims, wherein by means of the self-evaluation device (52a … … 52n) of each condition sensing element (51a … … 51n) it is sought: how trustworthy the model of the corresponding condition sensing element (51a … … 51n) is.

6. The method according to any one of the preceding claims, wherein data is provided for all driver assistance systems (30a … … 30n) by means of the model of the condition sensing element (51a … … 51 n).

7. The method of claim 6, wherein the driver assistance system (30a … … 30n) decides which data of which condition sensing element (51a … … 51n) it processes.

8. The method according to claim 7, wherein the decision means (61) of the functional means (60) decides: which driver assistance system (30a … … 30n) processes which data.

9. The method according to any of the preceding claims, wherein each condition sensing element (51a … … 51n) evaluates the vehicle's behaviour data with the same metric, respectively, wherein the metric of the condition sensing element (51a … … 51n) comprises at least one of: collision probability, resource saving, sustainable environmental development and legality.

10. An apparatus (100) for operating an automated vehicle, the apparatus having:

-an environment sensor arrangement (10) for sensing an environment of the vehicle and for providing environment data (20) of the sensed environment;

-a condition sensing device (50) having a defined number of condition sensing elements (51a … … 51n) greater than one, to which the environmental data (20) can be fed, wherein a computational modeling of the environment of the vehicle can be carried out by means of the condition sensing elements (51a … … 51 n);

-a driver assistance system (30a … … 30n) being manipulable with output data of a model of the condition sensing element (51a … … 51 n);

-decision means (61) by means of which it is possible to decide: -using which output data of the model of the condition sensing element (51a … … 51n) for steering an actuation device (40) of the vehicle; and

-actuating means (40) of the vehicle, which can be operated with the decided output data.

11. The apparatus (100) of claim 10, configured as an electronic controller of the vehicle.

12. Computer program product with program code means for carrying out the method according to one of claims 1 to 9, when the program code means is executed on an electronic device (100) for operating an automated vehicle or is stored on a computer-readable data carrier.

Background

Nowadays, data from environmental sensors have been used in order to undertake specific driving tasks of the vehicle. For example, the environmental sensor data are used, for example, to Control Emergency Braking assistance (AEB, english: Autonomous Emergency Braking) or a pitch Cruise Control (ACC, english: Adaptive Cruise Control). Typically, environmental sensor data for implementing functions such as AEB or ACC are determined by radar sensors and/or cameras. Common to all these functions is that their area of action is severely limited.

DE102015222605a1 discloses a method for assisted driving, partially automated driving, highly automated driving, fully automated driving or unmanned driving of a motor vehicle. It can be provided that all subsystems have a monitoring function and transmit their operating capability to the controller, wherein it can also be provided that individual subsystems transmit their operating capability in number and other subsystems transmit their operating capability only in quality.

EP1369288a2 discloses a vehicle control arrangement comprising a vehicle control subsystem.

Disclosure of Invention

The object of the present invention is to provide an improved method for operating an automated vehicle.

According to a first aspect, the object is achieved by a method for operating an automated vehicle, having the following steps:

-sensing an environment of the vehicle;

-providing environmental data of the sensed environment;

-feeding the environmental data to a condition sensing device having a defined number of condition sensing elements greater than one;

-computationally modelling the environment of the vehicle by means of the condition sensing elements;

-using output data of the model of the condition sensing element for the manipulation of the driver assistance system;

-deciding, by means of decision means: using which output data of the model of the condition sensing element for operating an actuating device of the vehicle; and

-using the determined output data for operating an actuation device of the vehicle.

Advantageously, in this way, automated driving vehicles (autonomous vehicles) up to level 5 can be realized. Advantageously, this can be achieved with the invention by using hardware resources sparingly, whereby the method can be implemented with a relatively small controller. This reduces the computation effort and enables faster computation cycles. As a result, a system for operating an automated vehicle with real-time capability is provided.

According to a second aspect, the object is achieved with a device for operating an automated vehicle, having:

-an environment sensor arrangement for sensing an environment of the vehicle and for providing environment data of the sensed environment;

-a condition sensing device having a defined number of condition sensing elements greater than one to which environmental data is fed, wherein computational modeling of the environment of the vehicle can be carried out by means of the condition sensing elements;

-a driver assistance system being manipulable with output data of the model of the condition sensing element;

-decision means by means of which it is possible to decide: which output data of the model of the condition sensing element are used for operating an actuating device of the vehicle; and

-actuating means of the vehicle, said actuating means being operable with the determined output data.

Advantageous embodiments of the method are the subject matter of the dependent claims.

An advantageous development of the method provides that the models of the condition-sensing elements are ascertained independently of one another in synchronism, wherein the models of the condition-sensing elements at least partially overlap. This results in a robust assistance system, since the driver assistance system which is activated in the event of a failure of one condition sensing element can continue to operate.

In a further advantageous development of the method, it is provided that the driver assistance systems are implemented independently of one another and synchronously. Thereby also aiding the independence and robustness of the method.

A further advantageous development of the method provides that the sensors of the surroundings sensor device provide different data for different condition sensing elements. For example, it can be provided that a video camera is used for the recognition of the lane and the object, wherein the different information is used by the different condition-sensing elements.

A further advantageous development of the method is characterized in that the following is determined by means of a self-evaluation device for each condition-sensing element: how trustworthy the model of the corresponding condition sensing element is. Thus, the decision carrier is provided with decision assistance of "which condition sensing element is authentic, then the condition sensing element is selected".

A further advantageous development of the method is characterized in that all driver assistance systems are provided with data by means of a model of the condition-sensing element. Thereby, all driver assistance systems are handled using the same condition sensing element data, thereby also assisting the robustness of the method.

In a further advantageous embodiment of the method, the driver assistance system makes decisions: the driver assistance system processes which data of which condition sensing element. The robustness of the method is thereby advantageously also increased.

A further advantageous development of the method is characterized in that the decision means of the functional means decide: which driver assistance system processes which data. Thus, the final decision: which data is processed and which actuator is fed with data.

In a further advantageous development of the method, provision is made for each condition sensing element to evaluate the vehicle behavior data with the same respective metric, wherein the metric of the condition sensing element comprises at least one of the following: collision probability, resource saving, sustainable environmental development and legality. The most important measure here is the smallest possible collision probability with which a collision of the vehicle can be avoided as far as possible.

Drawings

The invention is described in detail below with the aid of several figures and with additional features and advantages. The technical features and advantages of the device are derived here in a similar manner from the technical features and devices from the method.

Shown in the attached drawings:

fig. 1 shows a schematic diagram of a conventional device for operating an automated vehicle;

FIG. 2 shows another view of another conventional apparatus for operating an automated vehicle;

fig. 3 shows a schematic diagram of a first embodiment of the proposed device for operating an automated vehicle; and

fig. 4 shows a schematic diagram of a flowchart of the proposed method for operating an automated vehicle.

Detailed Description

The core concept of the invention is, in particular, to achieve driving tasks in the largest possible range of use of the automated vehicle. Advantageously, a method for autonomous driving up to level 5 (level 5 being defined autonomous driving) can be implemented in this way (definition of level 5: "all aspects of the dynamic driving task are carried out without exception by the automated driving system under all driving and environmental conditions that a human driver can cope with").

To this end, a so-called "multi-agent scheme" (multi-agent-Ansatz) is proposed according to the invention, which enables autonomous driving up to level 5. Here, each so-called "agent" in the form of a condition sensing element 51a … … 51n uses a mathematical model to be determined approximately accurately to simplify the so-called "open world problem" (possible level 5 autonomous driving worldwide). In this case, the different agents or condition-sensing elements 51a … … 51n are designed in such a way that their models use approximately independent states. For example, one condition sensing element 51a … … 51n is dedicated to sensing of lanes, another condition sensing element 51a … … 51n is dedicated to sensing of objects, and so on. The sum of all the condition sensing elements 51a … … 51n thus covers the entire region of action required by the automated vehicle for autonomous driving.

It is therefore advantageously possible to implement a solution to the open-world problem in real time with limited hardware resources by simplifying to a model to be determined mathematically approximately exactly.

Today, vehicles are often equipped with different environmental sensors (e.g. radar, camera, ultrasound, lidar, infrared cameras, etc.). The environmental data is sensed by means of these environmental sensors. Then, a function for completing a specific travel task can be implemented based on the environment data. In general, certain environmental sensors are used specifically for specific driving tasks, for example ultrasonic sensors for parking tasks, radar sensors for distance-regulating speed controllers, etc.

In terms of the autonomous driving function, it is proposed to provide a combination from a plurality of different environmental sensors in order to achieve hardware redundancy. A method is proposed for enabling autonomous driving with technical redundancy of hardware and software.

A driver assistance system is a system which is intended to solve driving tasks, such as lane keeping. Typically, the driver assistance system functions as shown in fig. 1.

The environment sensor device 10 is used to determine environment data 20. The environment data 20 are analyzed in the driver assistance system 30a, wherein a solution to the driving task is proposed on the basis of the result of the analysis. The driving task solution is then used to actuate an actuating device 40, for example in the form of a steering device and/or a braking device of the vehicle (not shown). If the vehicle has multiple driver assistance systems 30a … … 30n, there may also be multiple parallel levels of such logic, for example as shown in FIG. 2.

Fig. 3 shows an embodiment of the device 100 for operating an automated vehicle according to the invention. It can be seen that in the approach presented herein, the condition sensing device 50 is additionally embedded in a closed loop (closed loop) information path. As in the case of the driver assistance system 30a … … 30n described above, the information flow starts at the surroundings sensor device 10.

The environment sensor device determines environment data 20, wherein the reliability of the environment data from the various environment sensors (e.g. ultrasound, radar, lidar, cameras, etc.) of the environment sensor device 10 is checked and fused. The environmental data 20 is preferably provided by different types of sensors, whereby the sensor data of the different sensors are compared. If an object is identified, for example by a radar sensor and by a video sensor, the probability of "the object is actually present" is high. The information thus fused and trustworthy verified is forwarded to condition sensing device 50. In the condition sensing device 50, these pre-processed environmental data 20 are further processed by a plurality of agents in the form of condition sensing elements 51a … … 51 n.

The condition sensing elements 51a … … 51n of the condition sensing device 50 abstract the environment of the vehicle into a simplified mathematical model. Here, each condition sensing element 51a … … 51n of condition sensing device 50 is constructed or programmed such that the condition sensing elements use approximately independent information. For example, the degree of freedom of the object can be defined by means of the condition sensing elements 51a … … 51n, for example excluding movement in the Z direction when the vehicle is travelling straight on a flat highway. Thus, for example, one condition sensing element 51a … … 51n may be provided for identifying lane markings or lanes based on the environmental data preprocessed as described above, while the other condition sensing element 51a … … 51n finds the interrelationship between moving objects based on the environmental data, and so on. Thus, each condition sensing element 51a … … 51n undertakes the following tasks: different vehicle behaviors are evaluated by means of specific metrics (e.g., collision probability, resource savings, environmental sustainability, vehicle behavior legitimacy, etc.). Here, the metric "collision probability between objects" is generally given the highest priority. Preferably, all condition sensing elements 51a … … 51n use the same metric, so that different condition sensing elements 51a … … 51n and the resulting behavior can be compared to each other thereby.

Exemplary vehicle behaviors are "driving in a lane", "implementing a lane change", "braking", "accelerating", "driving into a parking space", and the like. For example, the following condition sensing elements 51a … … 51n may have overlapping regions of action:

condition sensing element a: observing all objects that can be associated with a lane;

condition sensing element B: all objects are observed.

In this example, all objects sensed by condition sensing element a are within the region of action of condition sensing element B. Otherwise, the statement does not hold.

The evaluation of the different behaviors is achieved by a common set of metrics, with each behavior being evaluated by its own particular metric by each condition sensing element 51a … … 51 n.

In addition to the evaluation of the behavior, a further task of the individual condition-sensing elements 51a … … 51n is to output an estimate by means of the self-estimating device 52a … … 52 n. This self-estimation indicates that: how trustworthy the assessment of the behaviour is by the corresponding condition sensing element 51a … … 51 n. Preferably, the self-estimation of each condition sensing element 51a … … 51n is calculated based on the input signal quality metric utilized by the corresponding condition sensing element 51a … … 51n to make its calculations. Furthermore, it is possible to verify: the basic assumption of the condition sensing element 51a … … 51n can be observed under the current circumstances. The self-estimation of the evaluated behaviour and situation sensing elements 51a … … 51n is forwarded by the situation sensing means 50 to the functional means 60 with decision means 61.

The evaluated behavior is used in the functional device 60 in order to implement various driver assistance systems 30a … … 30n (for example AEB, ACC, LKA (english: lane keeping assist), etc.) which are intended to carry out driving tasks. In this case, only a single driver assistance system 30a … … 30n may be active at all times during a defined period of time, since the various driver assistance systems 30a … … 30n are in competition with one another. In this case, the evaluated different vehicle behaviors are compared with one another in the form of plausibility-checked and fused environmental data. In this case, a function is selected which fulfills the desired driving task as well as possible with the dependent behavior and which in this case means the lowest collision probability or collision risk for the vehicle.

If the condition sensing element 51a … … 51n reports: which is very low from the evaluation, the functional device 60 may for example ignore the evaluation of this condition sensing element 51a … … 51n and use the evaluation of the other condition sensing element 51a … … 51 n. Finally, actuators of the actuating device 40, for example in the form of a steering device and/or a braking device of the vehicle, are actuated on the basis of the decision for a behavior and the dependent function. Typically, with ACC as the selected driver assistance system 30a … … 30n, the motor of the vehicle is operated. Typically, the steering device of the vehicle is actuated with LKA as the selected driver assistance system. In this case, for example, it can be provided that the trajectory data is used to actuate the steering device. As a result, the vehicle therefore carries out its driving task according to the evaluated behavior.

Alternatively, it can also be provided that the driver assistance system 30a … … 30n is controlled by a plurality of different condition sensing elements 51a … … 51 n. It is not absolutely necessary here that each condition sensing element 51a … … 51n be capable of performing every function.

The proposed method has the following advantages in particular in relation to conventional classical driver assistance systems:

an abstraction from the environment to a simple mathematical model is implemented by the condition sensing elements 51a … … 51n, thereby saving hardware resources;

by the condition sensing element 51a … … 51n, the calculation time can be shortened and thus a system with real-time capability is provided;

in addition to the hardware redundancy caused by the plurality of environmental sensor types of the environmental sensor device 10, software redundancy is provided by the plurality of condition sensing elements 51a … … 51n having overlapping regions of action. Thus, as a result, the system continues to be functional even in the event of failure of one condition sensing element 51a … … 51 n;

specific tasks can be solved by the development of dedicated agents. For example, the following condition sensing elements may be provided: the condition sensing element is based only on the own vehicle data when, for example, all environmental sensors fail. The condition sensing element can be used to brake a vehicle or to completely turn over a driving task to a human driver.

Preferably, the device 100 is configured as an electronic control unit of the vehicle, on which a computer program product (for example in the form of C + + program code) is executed.

Fig. 4 shows a schematic flowchart of the proposed method for operating an automated vehicle.

In step 200, sensing of the environment of the vehicle is performed.

In step 210, environmental data 20 of the sensed environment is provided.

In step 220, environmental data 20 is fed to a condition sensing device 50 having a defined number of condition sensing elements 51a … … 51n greater than one.

In step 230, a computational modeling of the environment of the vehicle is carried out by means of the condition sensing elements 51a … … 51 n.

In step 240, the output data of the model of the condition sensing element 51a … … 51n is used to carry out the manipulation of the driver assistance system 30a … … 30 n.

In step 250, the decision is implemented by means of decision means 61: which output data of the model of the condition sensing element 51a … … 51n are used for the manipulation of the actuation device 40 of the vehicle.

In step 260, the determined output data is used to operate the actuation means 40 of the vehicle.

Advantageously, the method according to the invention can be implemented as software which runs, for example, on an electronic control unit in the vehicle or on a server device on the basis of the cloud. In this way, simple adaptation of the method is assisted.

The features of the invention can be modified and/or combined with each other in a suitable manner by a person skilled in the art without departing from the core of the invention.