阅读说明：本技术 换道方法和系统、存储介质以及车辆 (Lane changing method and system, storage medium, and vehicle ) 是由 周平 孙思忱 于 2021-10-27 设计创作，主要内容包括：本申请涉及换道方法和系统、存储介质以及车辆,所述换道方法包括如下步骤：接收连续多帧条件信息,其中所述条件信息包括当前车辆的速度信息、相邻车辆状态信息以及车道线信息；以所述条件信息为神经网络的输入,并经由所述神经网络处理得到初始换道策略；以及基于预定规则和所述条件信息对所述初始换道策略进行校正以生成校正换道策略并输出。根据该换道方法可以在自动驾驶或者辅助驾驶过程中可以实现智能、安全和高效的换道。(The application relates to a lane changing method and system, a storage medium and a vehicle, wherein the lane changing method comprises the following steps: receiving continuous multi-frame condition information, wherein the condition information comprises speed information of a current vehicle, adjacent vehicle state information and lane line information; taking the condition information as the input of a neural network, and processing the condition information by the neural network to obtain an initial lane changing strategy; and correcting the initial lane changing strategy based on a preset rule and the condition information to generate and output a corrected lane changing strategy. According to the lane changing method, intelligent, safe and efficient lane changing can be realized in the automatic driving or auxiliary driving process.)

1. A lane change method, comprising the steps of:

receiving condition information, wherein the condition information comprises speed information of a current vehicle, adjacent vehicle state information and lane line information;

taking the condition information as the input of a neural network, and processing the condition information by the neural network to obtain an initial lane changing strategy; and

and correcting the initial lane changing strategy based on a preset rule and the condition information to generate and output a corrected lane changing strategy.

2. The method of claim 1, wherein the adjacent vehicles include immediately adjacent vehicles that are forward, rearward, left, right, above left, above right, below left, and below right in the current direction of vehicle travel.

3. The method of claim 1, wherein the status information comprises: the lateral and longitudinal speeds of the adjacent vehicle, the lateral and longitudinal distances of the adjacent vehicle from the current vehicle.

4. The method of claim 1, wherein the lane line information comprises coefficients of a lane line fit curve of the lane in which the current vehicle is located and its neighboring lanes.

5. The method of claim 1, wherein the neural network is a long-short term memory neural network.

6. The method of claim 1, wherein the predetermined rule comprises at least one of:

speed difference suppression rule: under the condition that the difference value between the expected speed of the current vehicle and the speed of the vehicle in front of the lane where the current vehicle is located is higher than a first preset value, increasing the probability of changing lanes to the adjacent lane in the initial lane changing strategy and reducing the probability of keeping the original lane;

the expressway lane priority rule is as follows: under the condition that the probability of the original lane is lower than a second preset value and the difference value between the probability of changing lanes to the adjacent left lane and the probability of changing lanes to the adjacent right lane is lower than a third threshold value, increasing the probability value of changing lanes to the left and reducing the probability value of changing lanes to the right in the initial lane changing strategy; and

and (4) deciding a cooling rule: and inhibiting the lane change to the adjacent lane in the initial lane change strategy within a preset time after the current vehicle finishes the lane change to the adjacent left lane last time.

7. A lane-change system, the system comprising:

a receiving unit configured to receive condition information, wherein the condition information includes speed information of a current vehicle, adjacent vehicle state information, and lane line information;

a neural network unit configured to take the condition information as input and generate an initial lane change policy output; and

an expert rule unit configured to correct the initial lane change policy based on a predetermined rule and the condition information to generate and output a corrected lane change policy.

8. The system of claim 7, wherein the adjacent vehicles comprise immediately adjacent vehicles that are forward, rearward, left, right, above left, above right, below left, and below right in the current direction of vehicle travel.

9. The system of claim 7, wherein the status information comprises: the lateral and longitudinal speeds of the adjacent vehicle, the lateral and longitudinal distances of the adjacent vehicle from the current vehicle.

10. The system of claim 7, wherein the lane line information comprises coefficients of a lane line fit curve for the lane in which the current vehicle is located and its neighboring lanes.

11. The system of claim 7, wherein the neural network element is comprised of a long-short term memory neural network.

12. The system of claim 7, wherein the predetermined rules include at least one of:

speed difference suppression rule: under the condition that the difference value between the expected speed of the current vehicle and the speed of the vehicle in front of the lane where the current vehicle is located is higher than a first preset value, increasing the probability of changing lanes to the adjacent lane in the initial lane changing strategy and reducing the probability of keeping the original lane;

the expressway lane priority rule is as follows: under the condition that the probability of the original lane is lower than a second preset value and the difference value between the probability of changing lanes to the adjacent left lane and the probability of changing lanes to the adjacent right lane is lower than a third threshold value, increasing the probability value of changing lanes to the left and reducing the probability value of changing lanes to the right in the initial lane changing strategy; and

and (4) deciding a cooling rule: and inhibiting the lane change to the adjacent lane in the initial lane change strategy within a preset time after the current vehicle finishes the lane change to the adjacent left lane last time.

13. A computer-readable storage medium having instructions stored therein, which when executed by a processor, cause the processor to perform the method of any one of claims 1-6.

14. A vehicle, characterized in that it comprises a lane-change system according to any one of claims 7-12.

Technical Field

The present application relates to the field of vehicle autonomous driving/assisted driving, and more particularly, to a lane change method, a lane change system, a storage medium, and a vehicle.

Background

Lane changing is a common decision-making behavior in an automatic driving (or assisted driving, the same applies below). How to make an intelligent and safe lane change decision in a complex and variable driving environment is an important subject of automatic driving and is one of important indexes of the automatic driving technology which is in a higher level. In an actual driving scene, the current vehicle and the surrounding environment are in a highly interactive state, and meanwhile, the surrounding vehicles may have driving behaviors such as acceleration, deceleration, lane change and the like, so that a high requirement is provided for a decision-making system (particularly an intelligent lane change function) for automatic driving.

In the prior art, the scheme for generating the intelligent lane change decision is provided in the following way. One solution is to implement lane changes by artificial design rules. However, since the driving scene is too complex, the rules cannot exhaust all the lane changing conditions, and thus, the scheme is difficult to implement in practical application. In another scheme, a machine learning model for channel change decision is established by using a machine learning technology, and intelligent channel change decision is made under different scenes through the model.

Disclosure of Invention

The embodiment of the application provides a lane changing method, a lane changing system, a storage medium and a vehicle, so that intelligent, safe and efficient lane changing can be realized in an automatic driving or auxiliary driving process.

According to an aspect of the present application, there is provided a lane change method, including the steps of: receiving condition information, wherein the condition information comprises speed information of a current vehicle, adjacent vehicle state information and lane line information; taking the condition information as the input of a neural network, and processing the condition information by the neural network to obtain an initial lane changing strategy; and correcting the initial lane changing strategy based on a preset rule and the condition information to generate and output a corrected lane changing strategy.

In some embodiments of the present application, optionally, the adjacent vehicles comprise immediately adjacent vehicles ahead, behind, to the left, to the right, above left, above right, below left, and below right in the current direction of vehicle travel.

In some embodiments of the present application, optionally, the status information includes: the lateral and longitudinal speeds of the adjacent vehicle, the lateral and longitudinal distances of the adjacent vehicle from the current vehicle.

In some embodiments of the present application, optionally, the lane line information includes coefficients of a lane line fitting curve of a lane where the current vehicle is located and a lane adjacent to the current vehicle.

In some embodiments of the present application, optionally, the neural network is a long-short term memory neural network.

In some embodiments of the present application, optionally, the predetermined rule comprises at least one of: speed difference suppression rule: under the condition that the difference value between the expected speed of the current vehicle and the speed of the vehicle in front of the lane where the current vehicle is located is higher than a first preset value, increasing the probability of changing lanes to the adjacent lane in the initial lane changing strategy and reducing the probability of keeping the original lane; the expressway lane priority rule is as follows: under the condition that the probability of the original lane is lower than a second preset value and the difference value between the probability of changing lanes to the adjacent left lane and the probability of changing lanes to the adjacent right lane is lower than a third threshold value, increasing the probability value of changing lanes to the left and reducing the probability value of changing lanes to the right in the initial lane changing strategy; and deciding a cooling rule: and inhibiting the lane change to the adjacent lane in the initial lane change strategy within a preset time after the current vehicle finishes the lane change to the adjacent left lane last time.

According to another aspect of the present application, there is provided a lane change system, including: a receiving unit configured to receive condition information, wherein the condition information includes speed information of a current vehicle, adjacent vehicle state information, and lane line information; a neural network unit configured to take the condition information as input and generate an initial lane change policy output; and an expert rule unit configured to correct the initial lane change policy based on a predetermined rule and the condition information to generate and output a corrected lane change policy.

In some embodiments of the present application, optionally, the adjacent vehicles comprise immediately adjacent vehicles ahead, behind, to the left, to the right, above left, above right, below left, and below right in the current direction of vehicle travel.

In some embodiments of the present application, optionally, the status information includes: the lateral and longitudinal speeds of the adjacent vehicle, the lateral and longitudinal distances of the adjacent vehicle from the current vehicle.

In some embodiments of the present application, optionally, the lane line information includes coefficients of a lane line fitting curve of a lane where the current vehicle is located and a lane adjacent to the current vehicle.

In some embodiments of the present application, optionally, the neural network element is constituted by a long-short term memory neural network.

In some embodiments of the present application, optionally, the predetermined rule comprises at least one of: speed difference suppression rule: under the condition that the difference value between the expected speed of the current vehicle and the speed of the vehicle in front of the lane where the current vehicle is located is higher than a first preset value, increasing the probability of changing lanes to the adjacent lane in the initial lane changing strategy and reducing the probability of keeping the original lane; the expressway lane priority rule is as follows: under the condition that the probability of the original lane is lower than a second preset value and the difference value between the probability of changing lanes to the adjacent left lane and the probability of changing lanes to the adjacent right lane is lower than a third threshold value, increasing the probability value of changing lanes to the left and reducing the probability value of changing lanes to the right in the initial lane changing strategy; and deciding a cooling rule: and inhibiting the lane change to the adjacent lane in the initial lane change strategy within a preset time after the current vehicle finishes the lane change to the adjacent left lane last time.

According to another aspect of the present application, there is provided a computer-readable storage medium having instructions stored therein, wherein the instructions, when executed by a processor, cause the processor to perform any of the lane changing methods as described above.

According to another aspect of the present application, there is provided a vehicle comprising any of the lane-changing systems described above.

Drawings

The above and other objects and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings, in which like or similar elements are designated by like reference numerals.

FIG. 1 illustrates a lane-change method according to one embodiment of the present application.

FIG. 2 illustrates a lane-change system according to one embodiment of the present application.

FIG. 3 illustrates a lane-change scenario according to one embodiment of the present application.

Detailed Description

For the purposes of brevity and explanation, the principles of the present application are described herein with reference primarily to exemplary embodiments thereof. However, those skilled in the art will readily recognize that the same principles are equally applicable to all types of lane changing methods, lane changing systems, storage media, and vehicles, and that these same or similar principles may be implemented therein, with any such variations not departing from the true spirit and scope of the present application.

One aspect of the present application provides a lane change method. As shown in fig. 1, the lane-change method 10 includes the following steps: receiving condition information in step S102; in step S104, obtaining an initial lane changing strategy by taking the condition information as the input of the neural network; and correcting the initial lane-changing strategy based on the predetermined rule and the condition information in step S106. The lane changing strategy comprises the steps of keeping the original lane, changing the lane to the left and changing the lane to the right, and each strategy is accompanied by a certain probability. In some examples, the policy output with the highest probability may be selected when the policy is ultimately determined. It should be noted that "correcting" herein includes the special case of maintaining the original result.

The lane-changing method 10 according to some aspects of the present invention receives condition information for consecutive frames acquired with an image sensor or the like during driving, for example, in step S102. The condition information includes speed information of the current vehicle, adjacent vehicle state information, and lane line information. In this context, a current vehicle refers to a vehicle implementing lane change method 10, and a neighboring vehicle refers to a vehicle that is adjacent to the current vehicle and may have an impact on lane change decisions. The condition information received in step S102 above is the basic data for implementing the lane-change method 10, and thus reliable condition information is a prerequisite for generating a scientific lane-change strategy. It should be noted that the main consideration here is to switch lanes in the same direction, so that the lanes and the vehicles thereon are not under the scope of research.

In some examples, the neighboring vehicle may be a vehicle within a detectable range of an on-board detector (e.g., millimeter wave radar, lidar, vision sensor, etc.). The number of adjacent vehicles within the detectable range may vary depending on the type and number of detectors. The advantage of choosing neighboring vehicles in this way is that the data is richer and thus the reliability of the decision may be higher. But this may affect decision efficiency if the number of considered neighboring vehicles is too large for calculation.

In some embodiments of the present application, a number of vehicles most relevant to lane change may be selected as neighboring vehicles among the vehicles within the detectable range of the detector. For example, as shown in fig. 3, the adjacent vehicles may be a front immediate vehicle C2, a rear immediate vehicle C7, a left immediate vehicle C4, a right immediate vehicle C5, a left upper immediate vehicle C1, a right upper immediate vehicle C3, a left lower immediate vehicle C6, and a right lower immediate vehicle C8 in the traveling direction of the current vehicle C0 (the arrow direction of the vehicle head in the drawing). The adjacent vehicle is a vehicle that can be considered theoretically, and the implementation of the present invention is not affected if such a vehicle does not exist in actual circumstances. For example, if the detector does not detect the immediate lower right hand vehicle C8 of the illustrated location within a predetermined range, then the location is "empty" when the various steps of the present invention are performed.

In some embodiments of the present application, with continued reference to FIG. 3, the neighboring vehicle status information includes the lateral and longitudinal speed of the neighboring vehicle, the lateral and longitudinal distance of the neighboring vehicle from the current vehicle. Taking the immediate left vehicle C4 as an example, its current speed is V, which can be decomposed into a horizontal component V_x(lateral velocity) and vertical component V_y(longitudinal velocity). The immediate left vehicle C4 is at a lateral distance X and a longitudinal distance Y from the current vehicle C0. The state information is beneficial to describing the state of each adjacent vehicle, and therefore an accurate lane changing strategy can be generated.

In some embodiments of the present application, the lane line information includes coefficients of a lane line fit curve for the lane in which the current vehicle is located and its neighboring lanes (if any). With continued reference to fig. 3, the lane M in which the current vehicle C0 is located shares a lane line L2 with the left adjacent lane K and a lane line L3 with the right adjacent lane N. The left adjacent lane K also includes a lane line L1, and the right adjacent lane N also includes a lane line L4. In some examples of the present invention, the illustrated lane lines L1, L2, L3, and L4 are mainly studied, and thus the lane line information includes coefficients of a fitted curve of each of the lane lines L1, L2, L3, and L4.

The lane-changing method 10 according to some aspects of the present invention uses the condition information as an input of the neural network, and obtains an initial lane-changing strategy through the neural network processing in step S104. The neural network may be trained using human driving experience data before the neural network is used to process real-time input data and generate an initial lane-change strategy. The related training process can be developed according to the prior art, and is not described in detail herein.

In some embodiments of the present application, an initial lane-change strategy is generated in step S104 using a Long Short Term Memory (LSTM) neural network. Long-short term memory is a special Recurrent Neural Network (RNN) that performs better in longer sequences than normal recurrent neural networks. The inventor finds that the long-short term memory neural network has a better effect in the process of processing the vehicle autonomous lane changing strategy compared with other types of neural networks, the efficiency is higher, and the generated lane changing strategy is more satisfactory.

The lane-change method 10 according to some aspects of the present invention corrects the initial lane-change strategy based on the predetermined rule and the condition information to generate and output a corrected lane-change strategy in step S106. After obtaining the probability of the initial lane-change strategy (e.g., keeping straight, changing lanes left and right) of the current vehicle in a real-time environment through step S104, the probability value may be further processed through a customized expert system. The expert system can optimize the results generated in step S104 using the existing knowledge or experience, thereby providing a better effect on complex decision problems. Specifically, the expert system can optimize the output lane change decision by combining the intuitive driving experience of human in the driving process on the basis of the output result of the neural network.

The advantage of using an expert system is that the intelligent lane change decision output can be made to better meet the expectations of drivers by adding/modifying/deleting experience in the system in a customized manner, and maintenance and iteration of the decision machine are facilitated.

In some embodiments of the present application, the predetermined rule mentioned in step S106 may include the following:

(1) and (5) suppressing the rule by the speed difference. The neural network uses the driving data of human drivers during learning, and different drivers have different lane changing conditions when facing a front slow vehicle. When the expert system processes the lane change probability given by the neural network, firstly, a decision scene is defined as that a vehicle exists in front, the difference value between the speed of the vehicle and the expected running speed of the current vehicle is larger than a certain threshold value, and the vehicle is kept for a certain time. Wherein the current desired driving speed of the vehicle may be represented by the current cruising speed set by the driver. The individual output probabilities of the neural network can be revised when the speed difference suppression condition is satisfied. For example, for a scene with a large difference from the front vehicle speed, the probability value of the left/right lane change is increased and the probability value of the straight line is decreased as appropriate. Specifically, the probability of changing lanes to the adjacent lane in the initial lane change strategy is increased and the probability of keeping the original lane is decreased in the case where the difference between the desired speed of the current vehicle and the speed of the vehicle ahead of the lane in which the current vehicle is located is higher than a first predetermined value.

(2) And (4) a highway priority rule. When the probability of the lane change to one side of the neural network output is far greater than that of the other two outputs, most drivers can select to change the lane to the side in the scene, and the expert system selects the direction as the direction of the lane change decision to output. When the probability of the output of the neural network going straight is extremely small, but the probability of changing the lane to the two sides is proper, the lane changing to the left/right at the moment can be considered to be in accordance with the expectation of the driver. Considering that most roads have the left lane as a fast lane and the right lane may have a slow vehicle ahead which is not observed yet, the expert system will increase the output probability of changing lanes to the left and decrease the output probability of changing lanes to the right appropriately, so that the overall decision is more inclined to drive to the fast lane. Specifically, in the initial lane changing strategy, the probability value of changing lanes to the left is increased and the probability value of changing lanes to the right is decreased under the condition that the probability of the original lane is lower than a second preset value and the difference value of the probability of changing lanes to the adjacent left lane and the probability of changing lanes to the adjacent right lane is lower than a third threshold value.

(3) And (6) deciding a cooling rule. During the driving process, due to the switching of the current vehicle among various states, scenes exist in which frequent lane changing decisions are not desired even if the conditions for triggering intelligent lane changing are met. For example, when the vehicle has just completed a lane change, the lane change will increase the driver's insecurity. For such scenarios, the expert system will recognize on the fly and set the cooling time according to each scenario category. During the cooling time, the intelligent lane change decision is also suppressed by the expert system even if the driving scene is in accordance. Specifically, the lane change to the adjacent lane in the initial lane change strategy is inhibited within a predetermined time since the last lane change to the adjacent left lane by the current vehicle.

Another aspect of the present application provides a lane-change system. As shown in fig. 2, lane-changing system 20 includes a receiving unit 202, a neural network unit 204, and an expert rules unit 206. Although shown as separate units, these unit modules may be implemented integrally. For example, the neural network unit 204, the expert rules unit 206 may be implemented with a dedicated or general processor (with the necessary storage devices attached).

The receiving unit 202 of the lane change system 20 is configured to receive condition information on consecutive multiple frames acquired with an image sensor or the like during driving, for example, wherein the condition information includes speed information of the current vehicle, adjacent vehicle state information, and lane line information. In this context, the current vehicle may be the vehicle to which lane-change system 20 belongs, and the neighboring vehicles may be vehicles that are adjacent to the current vehicle and may have an impact on lane-change decisions. The condition information received by the receiving unit 202 is the basic data on which the lane-changing system 20 can continue to operate, and thus reliable condition information is a prerequisite for generating a scientific lane-changing strategy. It should be noted that the main consideration here is to switch lanes in the same direction, so that the lanes and the vehicles thereon are not under the scope of research.

In some examples, the neighboring vehicle may be a vehicle within a detectable range of an on-board detector (e.g., millimeter wave radar, lidar, vision sensor, etc.). The number of adjacent vehicles within the detectable range may vary depending on the type and number of detectors. The advantage of choosing neighboring vehicles in this way is that the data is richer and thus the reliability of the decision may be higher. But this may affect decision efficiency if the number of considered neighboring vehicles is too large for calculation.

In some embodiments of the present application, lane-change system 20 may select, as neighboring vehicles, the vehicles that are most relevant to a lane change from among the vehicles within detectable range of a vehicle detector (not shown). For example, as shown in fig. 3, the adjacent vehicles may be a front immediate vehicle C2, a rear immediate vehicle C7, a left immediate vehicle C4, a right immediate vehicle C5, a left upper immediate vehicle C1, a right upper immediate vehicle C3, a left lower immediate vehicle C6, and a right lower immediate vehicle C8 in the traveling direction of the current vehicle C0 (the arrow direction of the vehicle head in the drawing). The adjacent vehicle is a vehicle that can be considered theoretically, and the implementation of the present invention is not affected if such a vehicle does not exist in actual circumstances. For example, if the detector does not detect the immediate proximity of vehicle C8 to the lower right of the illustrated position within a predetermined range, then the lane-change system 20 may "null" the position.

In some embodiments of the present application, with continued reference to FIG. 3, the neighboring vehicle status information includes the lateral and longitudinal speed of the neighboring vehicle, the lateral and longitudinal distance of the neighboring vehicle from the current vehicle. Taking the immediate left vehicle C4 as an example, its current speed is V, which can be decomposed into a horizontal component V_x(lateral velocity) and vertical component V_y(longitudinal velocity). The immediate left vehicle C4 is at a lateral distance X and a longitudinal distance Y from the current vehicle C0. The state information will facilitate the mapping of the state of each adjacent vehicle, from which lane-change system 20 can generate an accurate lane-change strategy.

In some embodiments of the present application, the lane line information includes coefficients of a lane line fit curve for the lane in which the current vehicle is located and its neighboring lanes (if any). With continued reference to fig. 3, the lane M in which the current vehicle C0 is located shares a lane line L2 with the left adjacent lane K and a lane line L3 with the right adjacent lane N. The left adjacent lane K also includes a lane line L1, and the right adjacent lane N also includes a lane line L4. In some examples of the present invention, the illustrated lane lines L1, L2, L3, and L4 are primarily studied, and thus the lane line information taken into account by lane-change system 20 includes coefficients of a curve fit for each of lane lines L1, L2, L3, and L4.

The neural network element 204 of the lane-change system 20 is configured to take the condition information as input and generate an initial lane-change policy output. The neural network element 204 may be trained with human driving experience data before the neural network element 204 is used to process real-time input data and generate an initial lane-change strategy. The related training process can be developed according to the prior art, and is not described in detail herein.

In some embodiments of the present application, the neural network element 204 is comprised of a long-short term memory neural network. The long-short term memory is a special recurrent neural network, and compared with the common recurrent neural network, the long-short term memory neural network can perform better in a longer sequence. The inventor finds that the long-short term memory neural network has a better effect in the process of processing the vehicle autonomous lane changing strategy compared with other types of neural networks, the efficiency is higher, and the generated lane changing strategy is more satisfactory.

The expert rules unit 206 of the lane-change system 20 is configured to correct the initial lane-change policy based on predetermined rules and condition information to generate and output a corrected lane-change policy. After the neural network unit 204 obtains the probability of the initial lane-change strategy (e.g., keeping straight, changing lanes left and right) of the current vehicle in a real-time environment, the probability value can be further processed by a customized expert rules unit 206. The expert rules unit 206 may optimize the results generated by the neural network unit 204 using existing knowledge or experience, thereby providing a better result for complex decision-making problems. Specifically, the expert rule unit 206 may optimize the output lane change decision based on the output result of the neural network unit 204 in combination with the intuitive driving experience of human beings during driving.

The advantage of using an expert system is that the intelligent lane change decision output can be made to better meet the expectations of drivers by adding/modifying/deleting experience in the system in a customized manner, and maintenance and iteration of the decision machine are facilitated.

In some embodiments of the present application, the predetermined rules employed in the expert rules unit 206 may include the following. (1) The basic principle of the speed difference suppression rule can be referred to the above description, and the details are not repeated herein. Specifically, the probability of changing lanes to the adjacent lane in the initial lane change strategy is increased and the probability of keeping the original lane is decreased in the case where the difference between the desired speed of the current vehicle and the speed of the vehicle ahead of the lane in which the current vehicle is located is higher than a first predetermined value. (2) The basic principle of the highway priority rule can be referred to the above description, and the details are not repeated herein. Specifically, in the initial lane changing strategy, the probability value of changing lanes to the left is increased and the probability value of changing lanes to the right is decreased under the condition that the probability of the original lane is lower than a second preset value and the difference value of the probability of changing lanes to the adjacent left lane and the probability of changing lanes to the adjacent right lane is lower than a third threshold value. (3) The decision of the cooling rule, the basic principle of which can be referred to the above description, will not be described herein. Specifically, the lane change to the adjacent lane in the initial lane change strategy is inhibited within a predetermined time since the last lane change to the adjacent left lane by the current vehicle.

Another aspect of the application provides a vehicle comprising any of the lane-changing systems described above. The vehicle provided with the lane changing system can realize intelligent, safe and efficient lane changing in the automatic driving or auxiliary driving process.

According to another aspect of the present application, there is provided a computer readable storage medium having stored therein instructions that, when executed by a processor, cause the processor to perform any of the lane changing methods as described above. Computer-readable media as referred to in this application includes all types of computer storage media, which can be any general-purpose or special-purpose computer accessibleA medium may be used. By way of example, computer-readable media may include RAM, ROM, EPROM, E²PROM, registers, hard disk, removable disk, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other temporary or non-temporary medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general purpose or special purpose computer, or a general purpose or special purpose processor. A disk, as used herein, typically reproduces data magnetically, while a disk reproduces data optically with a laser. Combinations of the above should also be included within the scope of computer-readable media. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.

Some of the above examples of the present invention provide solutions to intelligent lane change decisions for autonomous driving of a vehicle in complex driving environments. According to the schemes, an intelligent and safe lane changing decision can be automatically generated according to the current lane line information, the continuous running state of surrounding vehicles, the continuous running state of the current vehicle and the like. The control system of the automatic driving system can realize the lane changing action according to the lane changing decision.

The above are merely specific embodiments of the present application, but the scope of the present application is not limited thereto. Other possible variations or substitutions may occur to those skilled in the art based on the teachings herein, and are intended to be covered by the present disclosure. In the present invention, the embodiments and features of the embodiments may be combined with each other without conflict. The scope of protection of the present application is subject to the description of the claims.