CN115384501A

CN115384501A - Automatic lane changing method and device for vehicle, vehicle and storage medium

Info

Publication number: CN115384501A
Application number: CN202210999296.7A
Authority: CN
Inventors: 于永杰; 梁锋华; 谭秀全; 卢斌; 肖雄
Original assignee: Chongqing Changan Automobile Co Ltd
Current assignee: Chongqing Changan Automobile Co Ltd
Priority date: 2022-08-19
Filing date: 2022-08-19
Publication date: 2022-11-25
Anticipated expiration: 2042-08-19
Also published as: CN115384501B

Abstract

The application relates to the technical field of automobile travel, in particular to an automatic lane changing method and device for a vehicle, the vehicle and a storage medium, wherein the method comprises the following steps: when a lane change request of the vehicle is identified, acquiring environmental information around the vehicle; identifying the actual position of at least one target around the vehicle according to the environment information, and dividing the periphery of the vehicle into at least one sub-area according to the actual position of each target; and matching the safety grade and the traffic efficiency grade of the lane change of the vehicle based on the position relationship between each sub-area and the vehicle, judging that the vehicle meets the lane change condition when the safety grade and the traffic efficiency grade are both greater than the preset danger grade, and controlling the vehicle to execute the preset lane change action so as to change the lane to the target lane. Therefore, the problems that in the related art, the automatic lane changing function of the vehicle cannot accurately judge the environmental information around the vehicle, the safety of a user and the passing efficiency of the vehicle cannot be guaranteed, and the vehicle using experience of the user is reduced are solved.

Description

Automatic lane changing method and device for vehicle, vehicle and storage medium

Technical Field

The present disclosure relates to the field of automobile travel technologies, and in particular, to an automatic lane changing method and apparatus for a vehicle, and a storage medium.

Background

Along with the improvement of the intelligent degree of the automobile, the configuration of a front sensor and an actuator of the automobile is more and more abundant, the self-automobile sensing capability is more and more strong, the functions of lane keeping, autonomous cruising, auxiliary lane changing and the like can be realized, the driver can be helped to realize more driving functions, the driving fatigue of the driver is relieved, and the driver can concentrate more attention on observing the surrounding emergency.

In the related art, the automatic driving technology of the vehicle can ensure that the vehicle runs in a single lane, but the vehicle cannot accurately judge the environmental information and the like around the vehicle on the automatic lane changing function due to too many environmental factors around the vehicle, incapability of capturing the state of a driver, incomprehensive vehicle information and the like, the safety of a user and the traffic efficiency of the vehicle cannot be ensured, and the vehicle using experience of the user is reduced.

Disclosure of Invention

The application provides an automatic lane changing method and device for a vehicle, the vehicle and a storage medium, and aims to solve the problems that in the related art, the automatic lane changing function of the vehicle cannot accurately judge the environmental information around the vehicle, the safety of a user and the traffic efficiency of the vehicle cannot be guaranteed, the vehicle using experience of the user is reduced, and the like.

An embodiment of a first aspect of the present application provides an automatic lane changing method for a vehicle, including the following steps: when a lane change request of a vehicle is identified, acquiring environmental information around the vehicle; identifying the actual position of at least one target around the vehicle according to the environment information, and dividing the periphery of the vehicle into at least one sub-area according to the actual position of each target; matching the safety grade and the traffic efficiency grade of the lane change of the vehicle based on the position relation between each sub-area and the vehicle, judging that the vehicle meets the lane change condition when the safety grade and the traffic efficiency grade are both greater than the preset danger grade, and controlling the vehicle to execute the preset lane change action so as to change the lane to the target lane.

According to the technical means, when a lane change request of a vehicle is identified, the surrounding environment is reconstructed by acquiring the surrounding environment information of the vehicle, the surrounding environment is divided according to a certain rule, the vehicle autonomously judges the relative position relation between the vehicle and the surrounding environment, whether the lane change of the vehicle is safe and has traffic efficiency is judged, if the safety level is high and the traffic efficiency is high and the lane change condition is met, the vehicle is controlled to execute the lane change, otherwise the lane change is not carried out, the optimal lane change decision result is made, and the driving safety and the use experience of a user are ensured.

Further, the dividing the periphery of the vehicle into at least one sub-area according to the actual position of each target includes: when the target is a vehicle target, recognizing that any vehicle target is located in a left lane area and/or a right lane area of the vehicle, and dividing the left lane area and/or the right lane area of the vehicle into at least one sub-area; when the target is a non-vehicle target and any non-vehicle target is identified to be located in a front area of the lane where the vehicle is located, dividing the front area of the lane where the vehicle is located into at least one sub-area.

According to the technical means, when the environment target is the vehicle target, the relative position of any target vehicle and the vehicle is identified, and the position area where the target vehicle is located is divided; and when the environment target is a non-vehicle target, identifying and dividing the area in front of the lane where the vehicle is located, reconstructing the surrounding environment of the vehicle, dividing according to the rule, and preprocessing the sensing information in order to reduce the calculation amount in the subsequent reinforcement learning model training.

Further, when the safety level and/or the traffic efficiency level is less than or equal to the preset level, the method includes: identifying whether the target lane is a lane close to a destination; and if the target lane is a lane close to the destination, judging that the vehicle meets the lane change condition, otherwise, judging that the vehicle does not meet the lane change condition.

According to the technical means, when the safety level and the traffic efficiency of lane changing of the vehicle are high, when the target lane is recognized to be the lane near the destination, the vehicle meets the lane changing condition, if the target lane is not the lane near the destination, the vehicle does not meet the lane changing condition, safety and traffic efficiency are considered, the lane changing decision required by the vehicle to reach the destination is taken into consideration, and the vehicle using experience of the user is improved.

Further, before determining that the host vehicle satisfies a lane change condition, the method further includes: identifying whether the target lane is a preset dangerous lane or not; and if the target lane is a preset dangerous lane, judging that the vehicle does not meet the lane changing condition, otherwise, judging that the vehicle meets the lane changing condition.

According to the technical means, the lane changing method and the lane changing device have the advantages that whether the target lane to be changed reaches the dangerous level or not is recognized, if the target lane is the preset dangerous lane, the vehicle and the adjacent vehicle on the target lane are in collision risk, the vehicle is judged not to meet the lane changing condition, otherwise, the vehicle can be changed, the collision risk possibly occurring to the vehicle is avoided, and the vehicle using safety and the vehicle using experience of a user are guaranteed.

Further, before determining that the host vehicle satisfies a lane change condition, the method further includes: identifying a current state of a driver; and if the current state is identified to be a preset fatigue state or a preset distraction state, judging that the vehicle does not meet the lane changing condition, and otherwise, judging that the vehicle meets the lane changing condition.

According to the technical means, the state of the driver is recognized, when the driver is in a fatigue driving state or a distraction state, the vehicle is judged not to meet the lane change condition, when the driver is in a special driving state, the vehicle is judged to meet the lane change condition, lane change when the driver is in the fatigue distraction state is avoided, the driver cannot take over the vehicle in time when an accident happens, and vehicle using safety and vehicle using experience of a user are guaranteed.

An embodiment of a second aspect of the present application provides an automatic lane changing device for a vehicle, including: the acquisition module is used for acquiring the environmental information around the vehicle when a lane change request of the vehicle is identified; the dividing module is used for identifying the actual position of at least one target around the vehicle according to the environment information and dividing the periphery of the vehicle into at least one sub-area according to the actual position of each target; and the control module is used for matching the safety grade and the traffic efficiency grade of the lane change of the vehicle based on the position relation between each sub-area and the vehicle, judging that the vehicle meets the lane change condition when the safety grade and the traffic efficiency grade are both greater than the preset danger grade, and controlling the vehicle to execute the preset lane change action so as to change the lane to the target lane.

Further, the dividing module is configured to: when the target is a vehicle target, recognizing that any vehicle target is located in a left lane area and/or a right lane area of the vehicle, and dividing the left lane area and/or the right lane area of the vehicle into at least one sub-area; when the target is a non-vehicle target and any non-vehicle target is identified to be located in a front area of the lane where the vehicle is located, dividing the front area of the lane where the vehicle is located into at least one sub-area.

Further, the control module is configured to: identifying whether the target lane is a lane close to a destination; and if the target vehicle is a lane close to the destination, judging that the vehicle meets the lane changing condition, otherwise, judging that the vehicle does not meet the lane changing condition.

Further, the method also comprises the following steps: the first judgment module is used for identifying whether the target lane is a preset dangerous lane or not before judging that the vehicle meets lane changing conditions; and if the target lane is a preset dangerous lane, judging that the vehicle does not meet the lane changing condition, otherwise, judging that the vehicle meets the lane changing condition.

Further, still include: the second judgment module is used for identifying the current state of the driver before judging that the vehicle meets the lane changing condition; and if the current state is identified to be a preset fatigue state or a preset distraction state, judging that the vehicle does not meet the lane changing condition, and otherwise, judging that the vehicle meets the lane changing condition.

An embodiment of a third aspect of the present application provides a vehicle, comprising: the automatic lane changing method for the vehicle comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the automatic lane changing method for the vehicle according to the embodiment.

A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the automatic lane changing method for a vehicle as described in the foregoing embodiments.

Therefore, the application has at least the following beneficial effects:

(1) When a lane change request of a vehicle is identified, the surrounding environment is reconstructed by acquiring the surrounding environment information of the vehicle, the surrounding environment is subjected to area division according to a certain rule, the vehicle autonomously judges the relative position relation between the vehicle and the surrounding environment, whether the lane change of the vehicle is safe and has traffic efficiency is judged, if the safety level is high and the traffic efficiency is high and the lane change condition is met, the vehicle is controlled to execute the lane change, otherwise, the lane change is not carried out, an optimal lane change decision result is made, and the driving safety and the use experience of a user are ensured.

(2) In the embodiment of the application, when the environmental target is a vehicle target, the relative position of any target vehicle and the vehicle is identified, and the position area where the target vehicle is located is divided; and when the environmental target is a non-vehicle target, identifying and dividing the area in front of the lane where the vehicle is located, reconstructing the surrounding environment of the vehicle, dividing according to the rule, and preprocessing the sensing information in order to reduce the calculation amount during subsequent reinforcement learning model training.

(3) According to the lane changing method and device, when the safety level and the traffic efficiency of the lane changing of the vehicle are high, when the target lane is identified to be the lane near the destination, the vehicle meets the lane changing condition, if the target lane is not the lane near the destination, the vehicle does not meet the lane changing condition, safety and traffic efficiency are considered, meanwhile, the lane changing decision required by the vehicle to reach the vicinity of the destination is taken into consideration, and vehicle using experience of a user is improved.

(4) According to the lane changing method and the lane changing device, whether the target lane to be changed reaches the danger level or not is identified, if the target lane is the preset dangerous lane and the vehicle and the adjacent vehicle on the target lane have the risk of collision, the situation that the vehicle does not meet the lane changing condition is judged, otherwise, the situation that the vehicle can change the lane is judged, the collision risk possibly occurring to the vehicle is avoided, and the vehicle using safety and the vehicle using experience of a user are guaranteed.

(5) According to the lane changing method and device, the state of the driver is recognized, when the driver is in a fatigue driving state or a distraction state, the vehicle is judged not to meet the lane changing condition, when the driver is in a special driving state, the vehicle is judged to meet the lane changing condition, the situation that the driver cannot take over the vehicle in time when the driver is in the fatigue distraction state and an accident happens is avoided, and the vehicle using safety and the vehicle using experience of a user are guaranteed.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

FIG. 1 is a flow chart of an automatic lane-change method for a vehicle according to an embodiment of the present application;

FIG. 2 is a diagram of a configuration of sensors onboard a smart-drive vehicle according to an embodiment of the present application;

FIG. 3 is a block diagram of preprocessing sensed information according to an embodiment of the present application;

FIG. 4 is a decision flow diagram for automatic lane change reinforcement learning according to an embodiment of the present application;

FIG. 5 is a block diagram of an automatic lane-changing system of an automatic lane-changing method of a vehicle according to an embodiment of the present application;

FIG. 6 is an exemplary diagram of an automatic lane-changing device of a vehicle according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a vehicle according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are illustrative and intended to explain the present application and should not be construed as limiting the present application.

Along with the improvement of the intelligent degree of the automobile, the configuration of a front sensor and an actuator of the automobile is more and more abundant, the self-automobile sensing capability is more and more strong, the functions of lane keeping, autonomous cruising, auxiliary lane changing and the like can be realized, the driver can be helped to realize more driving functions, the driving fatigue of the driver is relieved, and the driver can concentrate more attention on observing surrounding emergency events.

The current intelligent automobile automatic lane change behavior decision method can be divided into a data driving method and a non-data driving method according to a decision mechanism, wherein the non-data driving method mainly utilizes specific rule logic to comprehensively judge the relative position relation between a vehicle and the surrounding environment, the driving intention of a driver and the task of automatic driving planning, and carries out automatic lane change decision by constructing a finite state machine.

The method based on data driving can obtain an automatic lane change decision model of an optimal lane change decision through learning of driving data of a driver and safety boundary conditions set by a developer independently, but different input training data have different influences on the calculation amount and complexity of subsequent model training, when the automatic lane change decision is carried out in a data driving mode, extraction environmental data can represent surrounding vehicles, lanes and obstacles in a grid mode through sensor data, a punishment and reward mechanism in the lane change process is set to construct a deep reinforcement learning network model, grid data in the driving process is input into a neural network model to learn, and finally the automatic lane change decision model is obtained.

The processing of constructing the grid data needs to carry out refined modeling on the environment, the size of the grid also has different influences on the calculated amount, the smaller the grid is, the more refined the construction of the environment is, and better decision and planning are facilitated.

In the constructed road (clear lane lines and obvious road boundary isolation), a vehicle-mounted sensor is used for identifying a target vehicle, the lane lines, guardrails, static barriers and the like, the environment is reconstructed by using the sensing information of a target level, and after a reinforcement learning model is constructed, the information of the target level is used as the input of a network model, so that the calculated amount is greatly simplified, and the hardware design requirement on a vehicle-mounted controller is reduced.

Specifically, fig. 1 is a schematic flow chart of an automatic lane changing method for a vehicle according to an embodiment of the present disclosure.

As shown in fig. 1, the automatic lane changing method of the vehicle includes the steps of:

in step S101, when a lane change request of the host vehicle is recognized, environment information around the host vehicle is acquired.

The environment information includes information of target vehicles, pedestrians, obstacles in a certain distance before and after the current road, lane line information, information of each lane of the current road, information of ramp, convergence, confluence, and the like, which are not specifically limited herein.

It is understood that, when it is recognized that there is a lane change request, the embodiments of the present application acquire environment information around the host vehicle by an on-vehicle sensor or the like provided on the vehicle, and determine whether the lane change is possible based on the environment information.

Specifically, as shown in the configuration diagram of the vehicle-mounted sensor of the intelligent driving vehicle shown in fig. 2, the sensor arranged on the vehicle mainly includes a front radar, a front camera, an angle radar, a look-around camera, a high-precision map, a driver monitoring camera, and the like, and also includes a sensing device for the state information of the vehicle, including sensors attached to each actuator, including a wheel speed sensor, a brake pressure sensor, a steering wheel turning moment, a turning angle sensor, and the like; the vehicle-mounted sensor is mainly used for collecting environmental information and vehicle information, wherein data collection of target vehicles, pedestrians and static obstacles mainly depends on a camera and a radar sensor, the surrounding environments are identified under different road conditions and weather states according to sensor attributes of different sensors, lane lines are mainly identified according to the camera, targets, obstacles and the like can be identified through the camera and the radar sensor, then target information obtained by different sensors is subjected to information fusion, the target position is subjected to coordinate conversion, the center of a front bumper of the vehicle is taken as the origin of coordinates of the vehicle, an ISO coordinate system is referred, the target information is converted into the coordinate system of the vehicle, and a lane change decision is made by judging the safety in the driving process based on the coordinate system and making a lane change decision instruction; if the sensor and the actuator of the vehicle have faults, the system stops the judgment processing of the relevant lane changing function logic, so that the calculated amount in the driving process is reduced, and the load of the controller is lightened.

In step S102, the actual position of at least one target around the host vehicle is identified based on the environmental information, and the surroundings of the host vehicle are divided into at least one sub-area based on the actual position of each target.

The target includes a vehicle target and a non-vehicle target, wherein the vehicle target mainly refers to other vehicles, and the non-vehicle target may be a pedestrian, a stationary obstacle, or the like, which is not specifically limited herein.

It can be understood that, in the embodiment of the present application, the acquired environmental information is divided, the area division is performed by recognizing the relative position of the target vehicle, pedestrian, stationary obstacle, or the like, to the host vehicle, or the actual position of the target at this time, the grid data is constructed around, and the sensing information is preprocessed in order to reduce the amount of calculation in the subsequent reinforcement learning model training.

In the embodiment of the present application, dividing the periphery of the host vehicle into at least one sub-area according to the actual position of each target includes: when the target is a vehicle target, recognizing that any vehicle target is located in a left lane area and/or a right lane area of the vehicle, and dividing the left lane area and/or the right lane area of the vehicle into at least one sub-area; when the target is a non-vehicle target and any non-vehicle target is recognized to be located in a front area of the lane where the vehicle is located, the front area of the lane where the vehicle is located is divided into at least one sub-area.

It can be understood that, in the embodiment of the present application, when an environmental target is a vehicle target, a relative position between any target vehicle and a host vehicle is identified, and a position area where the target vehicle is located is divided; when the environment target is a non-vehicle target, identifying and dividing the front area of the lane where the vehicle is located, reconstructing the surrounding environment of the vehicle, mainly comprising area position division of target vehicles, pedestrians and obstacles, and preprocessing the sensing information in order to reduce the calculation amount in the subsequent reinforcement learning model training.

Specifically, taking an environmental target as a vehicle target as an example, as shown in a block diagram of preprocessing the sensing information shown in fig. 3, the target vehicle is divided into regions according to positions, where the relationship between the regions and the positions for the regions is as follows:

zone 1 target: a target right in front of the vehicle in the road;

zone 2 target: a front target of the No. 1 target of the lane;

zone 3 target: a target in front of the head of the vehicle in the left lane;

zone 4 target: a target in front of the head of the vehicle in the right lane;

zone 5 target: a front target of the left lane No. 3 target;

zone 6 target: a target in front of the target No. 4 on the right lane;

zone 7 target: a target with a left lane parallel to the host vehicle;

zone 8 target: a target with a right lane parallel to the vehicle;

zone 9 target: a target immediately behind the tail of the vehicle behind the left lane;

zone 10 target: a target immediately behind the vehicle parking space behind the right lane;

regarding pedestrians and obstacles, the target pedestrians and obstacles in front of the head of the vehicle are mainly concerned, and at the moment, area division is carried out according to lanes, wherein the area division and the corresponding position relation are as follows:

region No. 1: the front of the vehicle head of the lane;

region No. 2: the left lane is in front of the head of the vehicle;

region No. 3: the front of the vehicle head of the right lane;

in step S103, the safety level and the traffic efficiency level of the lane change of the host vehicle are matched based on the position relationship between each sub-area and the host vehicle, and when both the safety level and the traffic efficiency level are greater than the preset danger level, it is determined that the host vehicle meets the lane change condition, and the host vehicle is controlled to execute the preset lane change action to change the lane to the target lane.

Here, the positional relationship may be a relative positional relationship between the target and the host vehicle in each sub-region.

The preset danger level may be a level set by a user in advance, or may be a level obtained by calculating data for multiple times, for example: the safety level is two-level, the traffic efficiency reaches 50%, and the like, and the safety level is not particularly limited.

It can be understood that, in the embodiment of the application, the safety level and the traffic efficiency level of the lane change of the vehicle are matched based on the relative position relationship between each sub-region and the vehicle, whether the lane change of the vehicle is safe and the traffic efficiency is high is judged, if the safety level is high and the traffic efficiency is high and the lane change condition is met, the vehicle is controlled to execute the lane change, otherwise, the lane change is not carried out, the optimal lane change decision result is made, and the driving safety and the use experience of a user are ensured.

In this application embodiment, when the security level and/or the traffic efficiency level is less than or equal to the preset level, the method includes: identifying whether the target lane is a lane close to the destination; and if the target lane is a lane close to the destination, judging that the vehicle meets the lane change condition, otherwise, judging that the vehicle does not meet the lane change condition.

It can be understood that, in the embodiment of the application, when the safety level and the traffic efficiency of the lane change of the vehicle are low, when it is recognized that the target lane is a lane near the destination, the vehicle meets the lane change condition, and if the target lane is not a lane near the destination, the vehicle does not meet the lane change condition.

It is understood that, in the embodiment of the present application, whether the host vehicle meets the lane change condition may be determined in various ways, which is not specifically limited, and the following specifically describes a possible implementation method, which is as follows:

as a possible implementation manner, identifying whether the target lane is a preset dangerous lane; and if the target lane is a preset dangerous lane, judging that the vehicle does not meet the lane changing condition, otherwise, judging that the vehicle meets the lane changing condition.

The preset dangerous lanes can be combined and converged, and are not particularly limited herein.

It can be understood that, in the embodiment of the application, by identifying whether the target lane to be changed reaches the dangerous level, if the target lane is a preset dangerous lane, and at this time, the vehicle has a risk of collision with an adjacent vehicle on the target lane, it is determined that the vehicle does not meet the lane change condition, and otherwise, it is determined that the vehicle can change lanes, so that the risk of collision that the vehicle may have is avoided, and the driving safety and the vehicle using experience of a user are ensured.

As another possible implementation, the current state of the driver is identified; and when the current state is identified to be the preset fatigue state or the preset distraction state, judging that the vehicle does not meet the lane changing condition, otherwise, judging that the vehicle meets the lane changing condition.

The fatigue state may be determined whether the fatigue state is the fatigue state according to the actual time of closing the eyes of the driver, and the preset fatigue state may be that the eye closing time exceeds 5s or 6s, which is not specifically limited herein.

The preset distraction state may be that the camera detects that the driver is in a call receiving and making state, and the like, which is not specifically limited herein.

It can be understood that, in the embodiment of the application, by identifying the state of the driver, when the driver is in a fatigue driving state or a distraction state, it is determined that the vehicle does not meet the lane change condition, and when the driver is in a special driving state, it is determined that the vehicle meets the lane change condition, so that the situation that the vehicle is changed when the driver is in the fatigue distraction state and the driver cannot take over the vehicle in time when an accident occurs is avoided, and the vehicle using safety and the vehicle using experience of a user are ensured.

According to the automatic lane changing method for the vehicle, when a lane changing request of the vehicle is recognized, the surrounding environment is reconstructed by obtaining the environment information around the vehicle, the surrounding environment is divided according to a certain rule, the vehicle autonomously judges the relative position relation between the vehicle and the surrounding environment, whether the lane changing of the vehicle is safe or not and the traffic efficiency are high are judged, if the lane changing is safe and the traffic efficiency is high, the vehicle is controlled to carry out the lane changing, otherwise, the lane changing is not carried out, the optimal lane changing decision result is made, and the driving safety and the use experience of a user are guaranteed. Therefore, the problems that in the related art, the automatic lane changing function of the vehicle cannot accurately judge the environmental information around the vehicle, the safety of a user and the passing efficiency of the vehicle cannot be guaranteed, and the vehicle using experience of the user is reduced are solved.

In a specific application, as shown in fig. 4, the reinforcement learning-based automatic lane change decision method reconstructs a driving environment, performs lane change action triggering, lane change safety environment judgment and vehicle driving state judgment based on a current driving environment, and when a condition of safe lane change is met, a system automatically triggers a vehicle to change lanes to ensure that the vehicle runs on a lane with high traffic efficiency and driving safety, specifically as follows:

1. the lane change decision input information is as follows:

1) The current-time vehicle information of the vehicle: target vehicle, pedestrian and obstacle information in a certain distance before and after the current road, lane line information, information of each lane of the current road, ramp, confluence information and the like.

2) The current state of the driver: fatigue, distraction, or concentration, etc.

3) The current time environment information of the vehicle: the operating states of various associated systems include the engine, transmission, braking system, steering system, etc.

2. And a reward-punishment mechanism, wherein after the driver issues the navigation planning task, the system automatically judges the relative position relationship between the vehicle and the surrounding environment, and whether the navigation driving task can be more effectively completed or not, and makes an optimal lane change decision result, which is specifically as follows:

1) Efficiency of lane passage

2) Whether there is a collision risk

3) Whether or not to lean on the front destination lane

4) Whether to approach the merging and converging dangerous lane

3. Outputting information:

a lane change direction decision instruction: after receiving the automatic lane changing request, the lane changing decision system needs to finally output a lane changing action command by combining the current driving environment, the vehicle state and the driver state:

1) When a driver is attentive to driving, and the traffic efficiency of the target lane is high, when the vehicle does not have collision risk between the vehicle and the target lane, when the target lane is close to the lane where the destination is located, and when the target lane is not close to the confluence dangerous lane, the vehicle can be controlled to send out a lane changing instruction, otherwise, the lane changing instruction is not sent out.

2) When the driver is in a fatigue and distraction state, the system does not send a control request command to the actuator, so that the situation that the driver changes lanes when the driver is in the fatigue and distraction state and cannot take over the vehicle in time when an accident happens is avoided.

3) When a static obstacle, a pedestrian or a target vehicle at the rear of the target lane approaches quickly, the system does not start lane changing, and when the dangerous condition is relieved, the system starts to execute lane changing action.

The following will describe the automatic lane changing of the vehicle in detail with reference to the automatic lane changing system shown in fig. 5, specifically as follows:

(1) Firstly, initializing a system when a vehicle is started, mainly acquiring surrounding environment information and vehicle information of the vehicle by a vehicle-mounted sensor on the vehicle during driving, and carrying out region division on the surrounding environment of the vehicle;

(2) Then when the driver triggers lane changing, whether the vehicle meets the condition of safe lane changing is judged, if the target lane does not meet the condition of safe lane changing, namely the target lane is relatively congested, the vehicle between the vehicle and the target lane has a collision risk, the target lane is close to a converging and converging dangerous lane, or the driver drives in a fatigue way, and the like, the lane changing is cancelled;

(3) If the target lane temporarily does not meet the condition of safe lane changing, namely the target lane has a static obstacle, pedestrians or a target vehicle at the rear approaches quickly, the lane changing is cancelled, but when the dangerous condition is relieved, the system can start to execute the lane changing action;

(4) If the target lane meets the safe lane changing condition, the system starts lane changing, the vehicle automatically judges whether the vehicle state meeting the safe lane changing condition is normal or not, if so, the lane changing is continuously executed, if not, the necessity of the vehicle entering the target lane is judged, if so, the lane changing instruction is continuously executed, and if not, the lane changing is cancelled.

Next, an automatic lane changing device for a vehicle according to an embodiment of the present application will be described with reference to the drawings.

Fig. 6 is a block diagram schematically illustrating an automatic lane-changing device of a vehicle according to an embodiment of the present application.

As shown in fig. 6, the automatic lane-changing device 10 of the vehicle includes: an acquisition module 100, a partitioning module 200, and a control module 300.

The acquiring module 100 is configured to acquire environmental information around a host vehicle when a lane change request of the host vehicle is identified; the dividing module 200 is configured to identify an actual position of at least one target around the host vehicle according to the environment information, and divide the periphery of the host vehicle into at least one sub-region according to the actual position of each target; the control module 300 is configured to match the safety level and the traffic efficiency level of the lane change of the host vehicle based on the position relationship between each sub-region and the host vehicle, determine that the host vehicle meets the lane change condition when both the safety level and the traffic efficiency level are greater than the preset danger level, and control the host vehicle to execute a preset lane change action to change the lane to the target lane.

In this embodiment, the dividing module 200 is configured to: when the target is a vehicle target, recognizing that any vehicle target is located in a left lane area and/or a right lane area of the vehicle, and dividing the left lane area and/or the right lane area of the vehicle into at least one sub-area; when the target is a non-vehicle target and any non-vehicle target is recognized to be located in a front area of the lane where the vehicle is located, the front area of the lane where the vehicle is located is divided into at least one sub-area.

In the embodiment of the present application, the control module 300 is configured to: identifying whether the target lane is a lane close to the destination; and if the target vehicle is a lane close to the destination, judging that the vehicle meets the lane changing condition, otherwise, judging that the vehicle does not meet the lane changing condition.

In the embodiment of the present application, the method further includes: a first judgment module: the system is used for identifying whether the target lane is a preset dangerous lane or not; and if the target lane is a preset dangerous lane, judging that the vehicle does not meet the lane changing condition, otherwise, judging that the vehicle meets the lane changing condition.

In the embodiment of the present application, the method further includes: a second judging module: for identifying a current state of the driver; and if the current state is identified to be the preset fatigue state or the preset distraction state, judging that the vehicle does not meet the lane changing condition, otherwise, judging that the vehicle meets the lane changing condition.

It should be noted that the foregoing explanation of the embodiment of the automatic lane changing method for a vehicle is also applicable to the automatic lane changing device for a vehicle in this embodiment, and is not repeated here.

According to the automatic lane changing device for the vehicle, when a lane changing request of the vehicle is recognized, the device reconstructs the surrounding environment by acquiring the environmental information around the vehicle, and performs area division on the surrounding environment according to a certain rule, the vehicle autonomously judges the relative position relation between the vehicle and the surrounding environment, whether the lane changing of the vehicle is safe and has the traffic efficiency is judged, if the lane changing is safe and the traffic efficiency is high, the vehicle is controlled to execute the lane changing, otherwise the lane changing is not performed, the optimal lane changing decision result is made, and the driving safety and the use experience of a user are ensured. Therefore, the problems that the automatic lane changing function of the vehicle in the related technology cannot accurately judge the environmental information around the vehicle, cannot guarantee the safety of a user and the passing efficiency of the vehicle, and reduces the vehicle using experience of the user and the like are solved.

Fig. 7 is a schematic structural diagram of a vehicle according to an embodiment of the present application. The vehicle may include:

memory 701, processor 702, and a computer program stored on memory 701 and executable on processor 702.

The processor 702, when executing the program, implements the automatic lane change method for a vehicle provided in the above-described embodiments.

Further, the vehicle further includes:

a communication interface 703 for communication between the memory 701 and the processor 702.

A memory 701 for storing computer programs operable on the processor 702.

The Memory 701 may include a high-speed RAM (Random Access Memory) Memory, and may also include a non-volatile Memory, such as at least one disk Memory.

If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 may be connected to each other through a bus and perform communication with each other. The bus may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but this is not intended to represent only one bus or type of bus.

Optionally, in a specific implementation, if the memory 701, the processor 702, and the communication interface 703 are integrated on a chip, the memory 701, the processor 702, and the communication interface 703 may complete mutual communication through an internal interface.

The processor 702 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more Integrated circuits configured to implement embodiments of the present Application.

Embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and the program, when executed by a processor, implements the automatic lane changing method for a vehicle as above.

In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of implementing the embodiments of the present application.

It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a programmable gate array, a field programmable gate array, or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are exemplary and should not be construed as limiting the present application and that changes, modifications, substitutions and alterations in the above embodiments may be made by those of ordinary skill in the art within the scope of the present application.

Claims

1. An automatic lane changing method for a vehicle, comprising the steps of:

when a lane change request of the vehicle is identified, acquiring environmental information around the vehicle;

identifying the actual position of at least one target around the vehicle according to the environment information, and dividing the periphery of the vehicle into at least one sub-area according to the actual position of each target;

matching the safety grade and the traffic efficiency grade of the lane change of the vehicle based on the position relation between each sub-area and the vehicle, judging that the vehicle meets the lane change condition when the safety grade and the traffic efficiency grade are both greater than the preset danger grade, and controlling the vehicle to execute the preset lane change action so as to change the lane to the target lane.

2. The method of claim 1, wherein the targets comprise vehicle targets and non-vehicle targets, and wherein the dividing the periphery of the host vehicle into at least one sub-region according to the actual position of each target comprises:

when the target is a vehicle target, recognizing that any vehicle target is located in a left lane area and/or a right lane area of the vehicle, and dividing the left lane area and/or the right lane area of the vehicle into at least one sub-area;

when the target is a non-vehicle target and any non-vehicle target is identified to be located in a front area of the lane where the vehicle is located, dividing the front area of the lane where the vehicle is located into at least one sub-area.

3. The method according to claim 1, characterized in that when the safety level and/or the traffic efficiency level is less than or equal to the preset level, it comprises:

identifying whether the target lane is a lane close to a destination;

and if the target lane is a lane close to the destination, judging that the vehicle meets the lane change condition, otherwise, judging that the vehicle does not meet the lane change condition.

4. The method according to claim 1 or 3, before determining that the host vehicle satisfies a lane change condition, further comprising:

identifying whether the target lane is a preset dangerous lane or not;

and if the target lane is a preset dangerous lane, judging that the vehicle does not meet the lane changing condition, otherwise, judging that the vehicle meets the lane changing condition.

5. The method according to claim 1 or 3, before determining that the host vehicle satisfies a lane change condition, further comprising:

identifying a current state of a driver;

and if the current state is identified to be a preset fatigue state or a preset distraction state, judging that the vehicle does not meet the lane changing condition, and otherwise, judging that the vehicle meets the lane changing condition.

6. An automatic lane-changing device for a vehicle, comprising the steps of:

the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring environmental information around a vehicle when a lane change request of the vehicle is identified;

the dividing module is used for identifying the actual position of at least one target around the vehicle according to the environment information and dividing the periphery of the vehicle into at least one sub-area according to the actual position of each target;

and the control module is used for matching the safety grade and the traffic efficiency grade of the lane change of the vehicle based on the position relation between each sub-area and the vehicle, judging that the vehicle meets the lane change condition when the safety grade and the traffic efficiency grade are both greater than the preset danger grade, and controlling the vehicle to execute the preset lane change action so as to change the lane to the target lane.

7. The apparatus of claim 6, wherein the partitioning module is configured to:

8. The apparatus of claim 6 or 7, wherein the control module is configured to:

identifying whether the target lane is a lane close to a destination;

and if the target vehicle is a lane close to the destination, judging that the vehicle meets the lane changing condition, otherwise, judging that the vehicle does not meet the lane changing condition.

9. A vehicle, characterized by comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of automatic lane changing of a vehicle according to any of claims 1-5.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor for implementing an automatic lane change method of a vehicle according to any one of claims 1 to 5.