Vehicle control method and device, electronic equipment and storage medium

By responding to collision warning in an automatic emergency steering system, and controlling the vehicle with the target sampling trajectory, the problem of poor obstacle avoidance effect caused by solid steering control in the prior art is solved, and the safety and obstacle avoidance ability of the vehicle are improved.

CN118928378APending Publication Date: 2024-11-12CHONGQING SELIS PHOENIX INTELLIGENT INNOVATION TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411144522.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing automatic emergency steering system can only perform fixed steering control, resulting in unsatisfactory obstacle avoidance.

Method used

By responding to the collision warning between the vehicle and the target obstacle, the sampling area is determined according to the location of the obstacle, the sampling point is selected and the sampling trajectory is constructed, the target sampling trajectory is determined, and the vehicle is controlled according to the track, thereby improving the flexibility of the automatic emergency steering system.

Benefits of technology

It improves the flexibility of vehicle control when triggered by automatic emergency steering system, avoids poor obstacle avoidance effects caused by fixed steering control, and enhances the safety and obstacle avoidance capabilities of the vehicle.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928378A_ABST
    Figure CN118928378A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of vehicle control, and provides a vehicle control method and device, electronic equipment and a storage medium. According to the method, in response to collision early warning of a vehicle and a target obstacle, a sampling area is determined according to the position of the target obstacle, at least one sampling point is selected from the sampling area, and a sampling track corresponding to each sampling point is constructed according to the current position of the vehicle and each sampling point; the target sampling track is determined from the constructed sampling track, the vehicle is controlled according to the target sampling track, and when the automatic emergency steering system is triggered subsequently, the vehicle can move along with the target sampling track, so that the vehicle control flexibility is improved when the automatic emergency steering system is triggered, and the vehicle safety is improved. The problem that when the vehicle triggers the automatic emergency steering system, the automatic emergency steering system can only execute fixed steering control, and consequently the obstacle avoidance effect is poor is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle control method, device, electronic device and storage medium. Background Art

[0002] With the advancement of technology, the level of automobile intelligence has been significantly improved, and users have become more stringent in their requirements for vehicle safety. As an important active safety technology, the Automatic Emergency Steering System (AES) has become an important configuration of modern vehicles.

[0003] The AES system actively changes the direction of travel when the vehicle is about to collide with an obstacle to avoid or mitigate the collision. However, the AES system in the prior art can usually only perform fixed steering control, which is prone to collision with other obstacles, resulting in unsatisfactory obstacle avoidance effects. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a vehicle control method, device, electronic device and storage medium to solve the problem in the prior art that the automatic emergency steering system can only perform fixed steering control, resulting in poor obstacle avoidance effect.

[0005] According to a first aspect of an embodiment of the present application, a vehicle control method is provided, the method comprising: in response to a collision warning between a vehicle and a target obstacle, determining a sampling area according to the position of the target obstacle, the target obstacle being an obstacle whose probability of collision with the vehicle exceeds a collision threshold during vehicle driving; selecting at least one sampling point from the sampling area, and constructing a sampling trajectory corresponding to each sampling point according to the current position of the vehicle and each sampling point; determining a target sampling trajectory from the constructed sampling trajectories, and controlling the vehicle according to the target sampling trajectory.

[0006] According to a second aspect of an embodiment of the present application, a vehicle control device is provided, which includes: a sampling module, which is used to respond to a collision warning between a vehicle and a target obstacle, and determine a sampling area according to the position of the target obstacle, wherein the target obstacle is an obstacle whose collision probability with the vehicle exceeds a collision threshold during the vehicle's driving process; a trajectory module, which is used to select at least one sampling point from the sampling area, and construct a sampling trajectory corresponding to each sampling point according to the current position of the vehicle and each sampling point; and a control module, which is used to determine a target sampling trajectory from the constructed sampling trajectories, and control the vehicle according to the target sampling trajectory.

[0007] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0008] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0009] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the method in the embodiments of the present application responds to the collision warning between the vehicle and the target obstacle, determines the sampling area according to the position of the target obstacle, selects at least one sampling point from the sampling area, and constructs a sampling trajectory corresponding to each sampling point according to the current position of the vehicle and each sampling point; determines the target sampling trajectory from the constructed sampling trajectory, and controls the vehicle according to the target sampling trajectory, so that when the automatic emergency steering system is subsequently triggered, the vehicle can move along the target sampling trajectory, thereby improving the flexibility of vehicle control when the automatic emergency steering system is triggered, and avoiding the problem that when the vehicle triggers the automatic emergency steering system, the automatic emergency steering system can only perform fixed steering control, resulting in poor obstacle avoidance effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0011] Figure 1 is a flow chart of a vehicle control method provided in an embodiment of the present application;

[0012] Figure 2 It is a basic schematic diagram of a coordinate system of a sampling trajectory provided in an embodiment of the present application;

[0013] Figure 3 is a flow chart of another vehicle control method provided in an embodiment of the present application;

[0014] Figure 4 It is a basic schematic diagram of a trajectory length iteration provided in an embodiment of the present application;

[0015] Figure 5 is a flow chart of another vehicle control method provided in an embodiment of the present application;

[0016] Figure 6 It is a flow chart of another vehicle control method provided in an embodiment of the present application;

[0017] Figure 7 is a flow chart of another vehicle control method provided in an embodiment of the present application;

[0018] Figure 8 is a flow chart of another optional vehicle control method provided in an embodiment of the present application;

[0019] Fig. 9 is a flow chart of another optional vehicle control method provided in an embodiment of the present application;

[0020] Fig.10 is a flow chart of another optional vehicle control method provided in an embodiment of the present application;

[0021] Fig.11 is a structural schematic diagram of a vehicle control device provided in an embodiment of the present application;

[0022] Fig.12 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0024] A vehicle control method and device according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 A vehicle control method provided by an embodiment of the present application is as follows: Figure 1 As shown, the method includes:

[0026] S101, in response to a collision warning between a vehicle and a target obstacle, determining a sampling area according to a position of the target obstacle, where the target obstacle is an obstacle whose collision probability with the vehicle exceeds a collision threshold during the vehicle's driving process;

[0027] S102, selecting at least one sampling point from the sampling area, and constructing a sampling trajectory corresponding to each sampling point according to the current position of the vehicle and each sampling point;

[0028] S103 : Determine a target sampling trajectory from the constructed sampling trajectories, and control the vehicle according to the target sampling trajectory.

[0029] It can be understood that the above-mentioned vehicle control method provided in this example is applied to vehicles, and the above-mentioned vehicles include vehicles with automatic driving or intelligent driving (including vehicles with manned functions (such as cars, buses, large buses, minibuses, etc.), vehicles with cargo functions (such as ordinary trucks, vans, trailers, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, special structure trucks), special vehicles (such as logistics distribution vehicles, automatic guided transport vehicles AGV, patrol cars, cranes, cranes, excavators, bulldozers, forklifts, rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor washing vehicles, sprinkler trucks, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.), vehicles with entertainment functions (such as entertainment vehicles, amusement park automatic driving devices, balance cars, etc.), rescue vehicles (such as fire trucks, ambulances, power repair vehicles, engineering rescue vehicles, etc.)), etc.

[0030] Specifically, the vehicle will predict its future driving trajectory during driving, and detect the road where the future driving trajectory is located through sensors such as cameras, lidar, and infrared radar to determine whether there are any obstacles on the road where the future driving trajectory is located.

[0031] It can be understood that the vehicle can determine the future driving trajectory of the vehicle based on at least one factor of the lane line where the vehicle is located, the system state of the vehicle (speed, acceleration, etc.), the navigation route, etc. For example, if there is a lane line on the current driving route of the vehicle, the vehicle predicts based on the lane line to obtain the above-mentioned future driving trajectory; if there is no lane line on the driving route of the vehicle, the vehicle predicts based on its own system state to obtain the above-mentioned future driving trajectory.

[0032] After determining that there are obstacles on the road where the future driving trajectory lies, the vehicle will further determine the probability of collision between itself and the obstacle on the road where the future driving trajectory lies; specifically, based on its own system state (speed, acceleration, current position, etc.), the future driving trajectory and the motion trajectory of the obstacle, the vehicle analyzes the relationship between the vehicle and the obstacle in time and space, and calculates the probability of a possible collision between the vehicle and the obstacle in the future.

[0033] It can be understood that this example does not limit the specific method of analyzing the relationship between the vehicle and the obstacle in time and space, and calculating the probability that the vehicle and the obstacle may collide in the future. For example, the vehicle calculates the probability that the vehicle and the obstacle may collide in the future through Monte Carlo simulation, Bayesian network and other methods.

[0034] After determining the collision probability between each obstacle and the vehicle, this example compares the collision probability with a preset collision threshold. If the collision probability between the obstacle and the vehicle exceeds the collision threshold, the obstacle is used as a target obstacle. It can be understood that the collision threshold is a value set by relevant personnel according to actual needs. Exemplarily, the collision threshold ranges from 50% to 100%. Preferably, the collision threshold is one of 60%, 70%, 80%, and 90%.

[0035] After determining the target obstacle, the vehicle will issue a collision warning with the target obstacle, so that the driver can be informed that the vehicle may collide with the target obstacle. In order to avoid or reduce the collision between the vehicle and the target obstacle, the vehicle will further perform trajectory planning, so that after triggering the automatic emergency steering system, the vehicle can be controlled according to the determined target sampling trajectory, thereby improving the safety of the vehicle.

[0036] Continuing from the above example, in the process of trajectory planning, the vehicle first determines the sampling area according to the location of the target obstacle. It can be understood that the determined sampling area includes all the target obstacles. And the boundary of the sampling area is the boundary of the road that the vehicle can travel when the vehicle drives to the location of the target obstacle.

[0037] It can be understood that this example converts the detected target obstacle into the SL coordinate system of the sampling trajectory. In this coordinate system, the relative position and motion of the vehicle and the target obstacle can be more intuitively seen, such as Figure 2 As shown, there are two target obstacles in the SL coordinate system. In this example, the area where the two target obstacles are located is used as the sampling area, and the boundary of the vehicle's driving road is used as the boundary of the sampling area.

[0038] After the sampling area is determined, this example selects at least one sampling point from the sampling area. It is understandable that how to select the sampling point from the sampling area will be described in detail later and will not be repeated here.

[0039] After determining the sampling points, this example constructs a sampling trajectory corresponding to each sampling point based on the current position of the vehicle and each sampling point. For example, if there are three sampling points A, B, and C, a sampling trajectory is constructed based on the current position of the vehicle and sampling point A, a sampling trajectory is constructed based on the current position of the vehicle and sampling point B, and a sampling trajectory is constructed based on the current position of the vehicle and sampling point C.

[0040] In this example, after the vehicle constructs the sampling trajectory corresponding to each sampling point, it will determine the target sampling trajectory from the constructed sampling trajectory. The target sampling trajectory is a trajectory that can reduce or avoid the collision between the vehicle and the target obstacle. When the automatic emergency steering system is subsequently triggered, the vehicle is controlled according to the target sampling trajectory so that the vehicle can move along the target sampling trajectory, thereby improving the flexibility of vehicle control when the automatic emergency steering system is triggered, and avoiding the problem that when the vehicle triggers the automatic emergency steering system, the automatic emergency steering system can only perform fixed steering control, resulting in poor obstacle avoidance effect.

[0041] According to the technical solution provided in the embodiment of the present application, in response to a collision warning between a vehicle and a target obstacle, a sampling area is determined according to the position of the target obstacle, at least one sampling point is selected from the sampling area, and a sampling trajectory corresponding to each sampling point is constructed according to the current position of the vehicle and each sampling point; a target sampling trajectory is determined from the constructed sampling trajectory, and the vehicle is controlled according to the target sampling trajectory, so that when the automatic emergency steering system is subsequently triggered, the vehicle can move along the target sampling trajectory, thereby improving the flexibility of vehicle control when the automatic emergency steering system is triggered, and avoiding the problem that when the vehicle triggers the automatic emergency steering system, the automatic emergency steering system can only perform fixed steering control, resulting in poor obstacle avoidance effect.

[0042] In some embodiments, Figure 3 As shown, according to the current position of the vehicle and each sampling point, a sampling trajectory corresponding to each sampling point is constructed, including:

[0043] S301, taking the current position as the starting point and the sampling point as the end point, and constructing an initial trajectory according to the starting point and the end point, the initial trajectory being a continuous and differentiable trajectory;

[0044] S302: Obtain the system state and system input of the vehicle, adjust the initial trajectory according to the system state and system input, and obtain a sampling trajectory corresponding to the sampling point.

[0045] Specifically, this example takes the current position of the vehicle as the starting point, the acquired sampling point as the end point, and constructs an initial trajectory based on the determined starting point and end point. The initial trajectory is a continuous and reachable trajectory. It can be understood that in the process of constructing the initial trajectory, the future driving trajectory of the vehicle can also be used as a reference trajectory to quickly construct the above initial trajectory.

[0046] In some examples, after determining the initial trajectory, the example also obtains the system state and system input of the vehicle, adjusts the initial trajectory according to the system state and system input, and obtains the sampling trajectory corresponding to the sampling point. Specifically, the system state includes: gear position, speed, acceleration, etc., and the system input includes: gear position, steering angle.

[0047] In order to better understand the present method, this embodiment provides a more specific example for illustration, wherein the present example uses the current position of the vehicle as the coordinate pole, then connects the coordinate pole and the sampling point through the boundary state optimization algorithm, and uses the future driving trajectory of the vehicle as the reference trajectory to generate the initial trajectory. The process of generating the sampling trajectory can be implemented by an optimization algorithm, such as a convex optimization algorithm, wherein the vehicle system differential equation is assumed to be as follows:

[0048]

[0049] Among them, x is the system state of the vehicle, which includes the target position, speed, acceleration, etc., and u represents the input of the vehicle system, including gear position and steering angle. The entire trajectory generation is to generate a continuous and differentiable state trajectory connecting the first and last states based on the current position (starting point) and sampling point (end point) state of the known vehicle, and s is the trajectory length. It can be understood that the premise of the generation of the entire sampling trajectory is that the control quantity is a variable of an unknown parameter and is a polynomial about the trajectory length s. Among them, the polynomial mathematical expression of the trajectory length s is as follows:

[0050]

[0051] Δ represents the target accuracy of optimization. The whole process represents the process from the initial state Xo to the target state Xt, as shown in Figure 4 As shown, other processes that have not reached the end are iterative processes.

[0052] Among them, Figure 2 As shown, Figure 2 As shown in the figure, sampling trajectories corresponding to multiple sampling points are constructed according to the above method.

[0053] According to the technical solution provided in the embodiment of the present application, the current position is taken as the starting point, the sampling point is taken as the end point, and an initial trajectory is constructed based on the starting point and the end point, and the initial trajectory is a continuously differentiable trajectory; the system state and system input of the vehicle are obtained, and the initial trajectory is adjusted according to the system state and the system input to obtain the sampling trajectory corresponding to the sampling point, thereby realizing the fast and accurate construction of the sampling trajectory between the current position and each sampling point.

[0054] In some embodiments, Figure 5 As shown, the target sampling trajectory is determined from the constructed sampling trajectory, including:

[0055] S501, performing performance evaluation on each constructed sampling trajectory to obtain a performance evaluation result corresponding to each sampling trajectory;

[0056] S502 , sorting the constructed sampling trajectories in order according to the performance evaluation results, and taking the sampling trajectory with the highest ranking as the target sampling trajectory.

[0057] Specifically, relevant technical personnel can perform performance evaluation on each sampled trajectory from the perspectives of collision risk coefficient, curvature, comfort, etc., which is not limited in this example.

[0058] After performing performance evaluation on each sampling trajectory and obtaining the performance evaluation results corresponding to each sampling trajectory, this example will sort the constructed sampling trajectories in order according to the performance evaluation results, and use the sampling trajectory with the highest ranking as the target sampling trajectory.

[0059] Exemplarily, there are three sampling points A, B, and C, and the sampling trajectories corresponding to the three sampling points A, B, and C are recorded as J, K, and L, respectively, wherein performance evaluation is performed on J, K, and L, respectively, to obtain performance evaluation results corresponding to J, K, and L, respectively, and the performance evaluation results are in the form of numerical values, and the performance evaluation results corresponding to J, K, and L are recorded as X, Y, and Z, respectively.

[0060] Finally, X, Y, and Z are compared. If X>Y and X>Z, the J sampling trajectory corresponding to X is used as the target sampling trajectory; if Y>X and Y>Z, the K sampling trajectory corresponding to Y is used as the target sampling trajectory; if Z>Y and Z>X, the L sampling trajectory corresponding to Z is used as the target sampling trajectory.

[0061] According to the technical solution provided in the embodiment of the present application, a performance evaluation is performed on each constructed sampling trajectory to obtain a performance evaluation result corresponding to each sampling trajectory; the constructed sampling trajectories are sorted in order according to the performance evaluation results, and the sampling trajectory with the highest ranking is used as the target sampling trajectory, thereby achieving the determination of the optimal sampling trajectory from the sampling trajectories as the target sampling trajectory.

[0062] In some embodiments, Figure 6 As shown, a performance evaluation is performed on each constructed sampling trajectory to obtain a performance evaluation result corresponding to each sampling trajectory, including:

[0063] S601, performing collision risk coefficient evaluation, curvature evaluation and comfort evaluation on each sampling trajectory to obtain a collision risk value, a curvature value and a comfort value corresponding to each sampling trajectory;

[0064] S602: Obtain weights corresponding to the collision risk value, the curvature value, and the comfort value, respectively, and perform weighted summation on the collision risk value, the curvature value, and the comfort value according to the obtained weights to obtain a performance evaluation result.

[0065] Specifically, this example evaluates the performance of each sampled trajectory from the perspectives of collision risk coefficient, curvature, and comfort; illustratively, the collision risk coefficient evaluation can be obtained by calculating the collision risk value between the vehicle and other objects, as follows:

[0066]

[0067] Among them, J collision is the collision risk value corresponding to the sampled trajectory.

[0068] Similarly, curvature evaluation can be obtained by calculating the curvature of the sampled trajectory as follows:

[0069]

[0070] Among them, J curve is the curvature value corresponding to the sampling trajectory. The comfort value evaluation is similar, so it will not be repeated in this example.

[0071] After obtaining the above-mentioned collision risk value, curvature value and comfort value, this example will obtain the weights corresponding to the collision risk value, curvature value and comfort value respectively; in some examples, the weights of the collision risk value, curvature value and comfort value are determined according to historical data; in some examples, the weights of the collision risk value, curvature value and comfort value are determined by relevant personnel according to the actual situation of the vehicle.

[0072] After obtaining the weights corresponding to the collision risk value, the curvature value, and the comfort value, respectively, this example performs a weighted summation of the collision risk value, the curvature value, and the comfort value according to the obtained weights to obtain a performance evaluation result.

[0073] For example, the weights corresponding to the collision risk value, curvature value, and comfort value are O, P, and Q, respectively, and the collision risk value, curvature value, and comfort value are J, respectively. collision , J curve , J comfort , then the performance evaluation result of the sampling trajectory = O*J collision +P*J curve +Q*J comfort .

[0074] According to the technical solution provided in the embodiment of the present application, collision risk coefficient evaluation, curvature evaluation and comfort evaluation are performed on each sampling trajectory to obtain a collision risk value, curvature value and comfort value corresponding to each sampling trajectory; weights corresponding to the collision risk value, curvature value and comfort value are obtained, respectively, and the collision risk value, curvature value and comfort value are weighted and summed according to the obtained weights to obtain a performance evaluation result. Among them, the method evaluates the sampling trajectory from three perspectives: collision risk coefficient evaluation, curvature evaluation and comfort, and realizes accurate acquisition of the performance evaluation result corresponding to the sampling trajectory.

[0075] In some embodiments, Figure 7 As shown, selecting at least one sampling point from the sampling area includes:

[0076] S701, obtaining the road complexity of the vehicle's driving road and the vehicle's current driving speed;

[0077] S702: Determine the number of sampling points according to the road complexity and the current driving speed, and determine sampling points corresponding to the number of sampling points in the sampling area.

[0078] Specifically, this example will obtain the road complexity of the vehicle's driving road and the vehicle's current driving speed. The driving road is the road where the vehicle's future driving trajectory is located. The above road complexity can be determined based on the road type, road curvature, road width and number of lanes of the driving road as well as environmental obstacles.

[0079] Specifically, the complexity will vary based on the type of road (such as urban streets, highways, and rural roads), among which urban streets and rural roads are more complex than highways; road curvature is an important indicator to measure road complexity, higher road curvature (such as sharp turns, roundabouts) indicates that the road is more complex, conversely, lower road curvature (for example, roads tending to be straight) indicates lower road complexity; narrower roads or multiple lanes indicate higher road complexity, conversely, wider roads or fewer lanes indicate lower road complexity; based on the above principles, relevant personnel can set the vehicle to calculate the road complexity of the driving road based on the road type, road curvature, road width and number of lanes, as well as environmental obstacles.

[0080] After determining the road complexity, this example determines the number of sampling points based on the road complexity and the current driving speed, and determines the sampling points corresponding to the number of sampling points from the sampling area, so that the sampling points are evenly distributed in the sampling area.

[0081] Exemplarily, for example, if the number of sampling points determined according to the road complexity and the current driving speed of the vehicle is N, then N sampling points will be selected in the sampling area, and the selected N sampling points are evenly distributed in the sampling area.

[0082] According to the technical solution provided in the embodiment of the present application, the road complexity of the vehicle's driving road and the current driving speed of the vehicle are obtained; the number of sampling points is determined according to the road complexity and the current driving speed, and the sampling points corresponding to the number of sampling points are determined from the sampling area, so that the number of sampling points comprehensively considers the road complexity and the current driving speed of the vehicle, thereby avoiding the problem of too many sampling points causing the vehicle to calculate the target sampling trajectory too slowly, or avoiding the problem of too few sampling points causing the sampling points to fail to cover the area where the vehicle may travel in the sampling area.

[0083] In some embodiments, Figure 8 As shown in the figure, the number of sampling points is determined according to the road complexity and the current driving speed, including:

[0084] S801, obtaining the number of basic sampling points, and determining the number of initial sampling points according to the number of basic sampling points and road complexity;

[0085] S802: Determine the number of sampling points according to the initial sampling points and the current driving speed.

[0086] It can be understood that the higher the road complexity of the driving road, the more sampling points are needed to construct the sampling trajectory, so that the target sampling trajectory determined subsequently can achieve the effect of reducing or avoiding collisions; conversely, the lower the road complexity of the driving road, the fewer sampling points are needed.

[0087] When the vehicle speed is low, the sampling points can be distributed more densely (more) so that the vehicle can be controlled to respond to slight turns or speed changes according to the determined sampling trajectory. When the vehicle speed is high, the sampling points are appropriately reduced to improve the vehicle's calculation speed, avoiding the problem of too many sampling points causing the vehicle to calculate the target sampling trajectory too slowly.

[0088] Based on the above principles, this example will set a basic sampling point number N base , which is the default number of sampling points under standard driving conditions (such as straight roads and moderate speeds).

[0089] Then, the number of initial sampling points is determined according to the number of basic sampling points and the road complexity. Specifically, the number of initial sampling points is the product of the number of basic sampling points and the road complexity, where the road complexity is C road , the initial number of sampling points is N complex , then N complex =C road *N base .

[0090] After determining the above-mentioned initial number of sampling points, this example will further adjust the initial number of sampling points according to the current driving speed to obtain the final number of sampling points; specifically, this example first determines the speed factor according to the current driving speed, and the speed factor is divided according to the speed area of ​​the vehicle and is an inverse proportional function of the vehicle driving speed; illustratively, the speed factor is set to F speed , then F speed It decreases with the increase of the current driving speed and increases with the decrease of the current driving speed. It can be understood that F speed The value range is (0, 2], that is, F speed Greater than 0 and less than 2; after determining the speed factor, multiply the speed factor by the initial number of sampling points, and round the product to get the final number of sampling points, where the number of sampling points is recorded as N final , then N final =round(N complex *F speed ).

[0091] According to the technical solution provided in the embodiment of the present application, the number of basic sampling points is obtained, and the number of initial sampling points is determined based on the number of basic sampling points and the road complexity; the number of sampling points is determined based on the initial sampling points and the current driving speed, thereby achieving the joint determination of the number of sampling points based on the road complexity and the current driving speed.

[0092] In some embodiments, Fig. 9 As shown, controlling the vehicle according to the target sampling trajectory includes:

[0093] S901, predicting the probability of a vehicle colliding with a target obstacle after an automatic emergency braking system of the vehicle is activated;

[0094] S902: After the automatic emergency braking system is activated, if the probability of a collision between the vehicle and the target obstacle exceeds a collision threshold, the vehicle is controlled according to the target sampling trajectory.

[0095] Specifically, after the vehicle issues a collision warning with a target obstacle, it will first predict the probability of a collision between the vehicle and the target obstacle after the vehicle's automatic emergency braking system (AEB) is activated. When the probability of a collision between the vehicle and the target obstacle exceeds the collision threshold, it indicates that the automatic emergency braking system cannot avoid or mitigate the collision between the vehicle and the target obstacle. At this time, it is necessary to activate the automatic emergency steering system and control the vehicle to steer according to the target sampling trajectory.

[0096] In order to better understand the present method, this embodiment provides a more specific example for illustration. Fig.10As shown, the vehicle detects obstacles while driving. If the probability of collision between the vehicle itself and an obstacle on the driving road where the future driving trajectory is located exceeds the collision threshold, a collision warning is issued. After the collision warning is issued, the probability of collision between the vehicle and the target obstacle is predicted after AEB is activated. During this process, target sampling trajectory planning is performed simultaneously, and the target sampling trajectory is used for the AES system to control the vehicle. After the vehicle predicts that the probability of collision between the vehicle and the target obstacle exceeds the collision threshold after AEB is activated, AES is triggered to force the vehicle to track the target sampling trajectory and brake appropriately to achieve the AES obstacle avoidance effect. It can be understood that in the later stage of AES triggering, AEB also needs to be activated at the same time, thereby ensuring that the vehicle stops, and further ensuring the safety of people involved in traffic.

[0097] It can be understood that the above process can be implemented by the vehicle control system, such as the electronic stability control system (ESC), the electric power steering system (EPS), etc. In this embodiment, all parameter settings and algorithm implementations can be adjusted according to actual needs to adapt to different environments and situations. For example, the number and distribution of sampling points corresponding to the sampling points can be adjusted according to the complexity of the road, and the collision risk coefficient assessment can be adjusted according to the speed of the vehicle and the distance from other objects.

[0098] This method adds trajectory planning to AES, which can effectively reduce the risk of collision with other obstacles due to fixed steering. This method detects the coordinates, size and other states of other obstacles through sensors such as cameras and radars, converts the obstacles into the SL coordinate system of the predicted trajectory to establish a planning map, and then scatters evenly distributed state sampling points in front of the vehicle trajectory. The sampling trajectory is generated by connecting the current position of the vehicle and the sampling points through boundary state optimization, and the performance of the sampling trajectory is evaluated based on collision risk value, comfort value, etc. Finally, the target sampling trajectory is obtained, and the vehicle is forced to track the target sampling trajectory while braking appropriately to achieve the AES obstacle avoidance effect, thereby improving the safety and comfort of AES.

[0099] This method can dynamically adjust the target sampling trajectory of the vehicle according to real-time environmental information and vehicle status, so as to avoid collisions with surrounding obstacles and improve the safety of the vehicle. Especially on narrow roads, this method can effectively avoid collisions with oncoming vehicles and improve the scope of action of AES. In addition, this method evaluates the performance of the sampling trajectory based on factors such as collision risk value and comfort value, and finally obtains the target sampling trajectory, which not only considers the safety of the vehicle, but also the comfort of the vehicle. This allows the vehicle to maintain a stable driving state while avoiding collisions, improving the riding comfort of passengers.

[0100] According to the technical solution provided in the embodiment of the present application, the probability of collision between the vehicle and the target obstacle is predicted after the automatic emergency braking system of the vehicle is activated; after the automatic emergency braking system is activated, if the probability of collision between the vehicle and the target obstacle exceeds the collision threshold, the vehicle is controlled according to the target sampling trajectory. In specific scenarios where the traditional AEB system cannot effectively control the potential collision risk, this method effectively reduces the risk of collision with other obstacles due to turning by introducing the AES with trajectory planning, thereby improving the safety of the automatic emergency braking system. In addition, by introducing the use of AES with trajectory planning on narrow roads, the problem of direct collision with oncoming vehicles due to the need for large-scale turning is avoided, thereby improving driving safety; and this method realizes the selection of the optimal solution in AEB and AES for obstacle avoidance, thereby improving the safety and comfort of the vehicle.

[0101] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0102] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0103] This embodiment also provides a vehicle control device, such as Fig.11 As shown, the device comprises:

[0104] The sampling module 1101 is used to respond to the collision warning between the vehicle and the target obstacle and determine the sampling area according to the position of the target obstacle, where the target obstacle is an obstacle whose collision probability with the vehicle exceeds the collision threshold during the vehicle's driving process;

[0105] The trajectory module 1102 is used to select at least one sampling point from the sampling area, and construct a sampling trajectory corresponding to each sampling point according to the current position of the vehicle and each sampling point;

[0106] The control module 1103 is used to determine a target sampling trajectory from the constructed sampling trajectory and control the vehicle according to the target sampling trajectory.

[0107] In some examples, the trajectory module 1102 is also used to take the current position as the starting point and the sampling point as the end point, and construct an initial trajectory based on the starting point and the end point, where the initial trajectory is a continuous and differentiable trajectory; obtain the system state and system input of the vehicle, adjust the initial trajectory based on the system state and system input, and obtain the sampling trajectory corresponding to the sampling point.

[0108] In some examples, the control module 1103 is also used to perform performance evaluation on each constructed sampling trajectory to obtain a performance evaluation result corresponding to each sampling trajectory; the constructed sampling trajectories are sorted in order according to the performance evaluation results, and the sampling trajectory with the highest ranking is used as the target sampling trajectory.

[0109] In some examples, the control module 1103 is also used to perform collision risk coefficient evaluation, curvature evaluation and comfort evaluation on each sampling trajectory to obtain a collision risk value, curvature value and comfort value corresponding to each sampling trajectory; obtain weights corresponding to the collision risk value, curvature value and comfort value, respectively, and perform weighted summation of the collision risk value, curvature value and comfort value according to the obtained weights to obtain a performance evaluation result.

[0110] In some examples, the trajectory module 1102 is also used to obtain the road complexity of the vehicle's driving road and the vehicle's current driving speed; determine the number of sampling points based on the road complexity and the current driving speed, and determine the sampling points corresponding to the number of sampling points from the sampling area.

[0111] In some examples, the trajectory module 1102 is further used to obtain the number of basic sampling points, determine the number of initial sampling points according to the number of basic sampling points and road complexity; and determine the number of sampling points according to the initial sampling points and the current driving speed.

[0112] In some examples, the control module 1103 is also used to predict the probability of collision between the vehicle and the target obstacle after the automatic emergency braking system of the vehicle is activated; after the automatic emergency braking system is activated, if the probability of collision between the vehicle and the target obstacle exceeds the collision threshold, the vehicle is controlled according to the target sampling trajectory.

[0113] According to the technical solution provided in the embodiment of the present application, the vehicle control device provided in the embodiment responds to the collision warning between the vehicle and the target obstacle, determines the sampling area according to the position of the target obstacle, selects at least one sampling point from the sampling area, and constructs a sampling trajectory corresponding to each sampling point according to the current position of the vehicle and each sampling point; determines the target sampling trajectory from the constructed sampling trajectory, and controls the vehicle according to the target sampling trajectory, so that when the automatic emergency steering system is subsequently triggered, the vehicle can move along the target sampling trajectory, thereby improving the flexibility of vehicle control when the automatic emergency steering system is triggered, and avoiding the problem that when the vehicle triggers the automatic emergency steering system, the automatic emergency steering system can only perform fixed steering control, resulting in poor obstacle avoidance effect.

[0114] Fig.12 Schematic diagram of an electronic device 12 provided in an embodiment of the present application. Fig.12As shown, the electronic device 12 of this embodiment includes: a processor 1201, a memory 1202, and a computer program 1203 stored in the memory 1202 and executable on the processor 1201. When the processor 1201 executes the computer program 1203, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 1201 executes the computer program 1203, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0115] The electronic device 12 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 12 may include, but is not limited to, a processor 1201 and a memory 1202. Those skilled in the art will appreciate that Fig.12 The electronic device 12 is merely an example and does not limit the electronic device 12 , and may include more or fewer components than those shown in the figure, or different components.

[0116] Processor 1201 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0117] The memory 1202 may be an internal storage unit of the electronic device 12, for example, a hard disk or memory of the electronic device 12. The memory 1202 may also be an external storage device of the electronic device 12, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the electronic device 12. The memory 1202 may also include both an internal storage unit of the electronic device 12 and an external storage device. The memory 1202 is used to store computer programs and other programs and data required by the electronic device.

[0118] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0119] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of regional requirements and patent practice. For example, in some areas, according to regional requirements and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0120] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A vehicle control method, characterized in that: The method comprises: In response to a collision warning between a vehicle and a target obstacle, a sampling area is determined according to a position of the target obstacle, wherein the target obstacle is an obstacle whose collision probability with the vehicle exceeds a collision threshold during the driving of the vehicle; Selecting at least one sampling point from the sampling area, and constructing a sampling trajectory corresponding to each sampling point according to the current position of the vehicle and each sampling point; A target sampling trajectory is determined from the constructed sampling trajectory, and the vehicle is controlled according to the target sampling trajectory.

2. The method according to claim 1, characterized in that According to the current position of the vehicle and each of the sampling points, a sampling trajectory corresponding to each of the sampling points is constructed respectively, including: Taking the current position as a starting point and the sampling point as an end point, and constructing an initial trajectory according to the starting point and the end point, wherein the initial trajectory is a continuous and differentiable trajectory; A system state and a system input of the vehicle are obtained, and the initial trajectory is adjusted according to the system state and the system input to obtain the sampling trajectory corresponding to the sampling point.

3. The method according to claim 1, characterized in that Determining a target sampling trajectory from the constructed sampling trajectory includes: Performing a performance evaluation on each of the constructed sampling trajectories to obtain a performance evaluation result corresponding to each of the sampling trajectories; The constructed sampling trajectories are sorted in order according to the performance evaluation results, and the sampling trajectory with the highest ranking is used as the target sampling trajectory.

4. The method according to claim 3, characterized in that A performance evaluation is performed on each of the constructed sampling trajectories to obtain a performance evaluation result corresponding to each of the sampling trajectories, including: Performing collision risk coefficient evaluation, curvature evaluation and comfort evaluation on each of the sampling trajectories to obtain a collision risk value, a curvature value and a comfort value corresponding to each of the sampling trajectories; The weights corresponding to the collision risk value, the curvature value, and the comfort value are obtained respectively, and the collision risk value, the curvature value, and the comfort value are weightedly summed according to the obtained weights to obtain the performance evaluation result.

5. The method according to claim 1, characterized in that Selecting at least one sampling point from the sampling area comprises: Acquire the road complexity of the road on which the vehicle is traveling and the current traveling speed of the vehicle; The number of sampling points is determined according to the road complexity and the current driving speed, and the sampling points corresponding to the number of sampling points are determined from the sampling area.

6. The method according to claim 5, characterized in that Determining the number of sampling points according to the road complexity and the current driving speed includes: Obtaining the number of basic sampling points, and determining the number of initial sampling points according to the number of basic sampling points and the road complexity; The number of sampling points is determined according to the initial sampling point and the current driving speed.

7. The method according to claim 1, characterized in that Controlling the vehicle according to the target sampling trajectory includes: predicting a probability of collision between the vehicle and the target obstacle after the automatic emergency braking system of the vehicle is activated; After the automatic emergency braking system is activated, if the probability of the vehicle colliding with the target obstacle exceeds the collision threshold, the vehicle is controlled according to the target sampling trajectory.

8. A vehicle control device, characterized in that: The device comprises: A sampling module, for responding to a collision warning between a vehicle and a target obstacle, and determining a sampling area according to a position of the target obstacle, wherein the target obstacle is an obstacle whose collision probability with the vehicle exceeds a collision threshold during the driving process of the vehicle; A trajectory module, used to select at least one sampling point from the sampling area, and construct a sampling trajectory corresponding to each sampling point according to the current position of the vehicle and each sampling point; A control module is used to determine a target sampling trajectory from the constructed sampling trajectory and control the vehicle according to the target sampling trajectory.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Method and system for controlling vehicle based on real-time information

    US20260233693A1