Vehicle control method and device, vehicle and storage medium

Abstract

The invention provides a vehicle control method and device, a vehicle and a storage medium. The method comprises the steps of obtaining position information of a target obstacle in a preset range of a vehicle; wherein the target obstacle comprises a dynamic obstacle and a static obstacle; determining a dynamic risk field of the dynamic obstacle and a static risk field of the static obstacle based on the position information; acquiring a traffic rule risk field in a preset range; based on the dynamic risk field, the static risk field and the traffic rule risk field, determining a space-time risk field in a preset range, and forming a space-time risk field distribution map; and controlling the vehicle to execute a corresponding response strategy based on the space-time risk field distribution diagram. According to the method, the space-time risk field distribution in the preset range of the vehicle is jointly determined through the dynamic risk field, the static risk field and the traffic rule risk field, dynamic obstacles can be quickly tried, sudden dangers can be handled, the risk perception ability of the vehicle can be improved, the emergency obstacle avoidance ability of the vehicle can be improved, and the safety of the vehicle can be improved.

Description

Technical Field

[0001] This application relates to the field of display technology, specifically to a vehicle control method, device, vehicle, and storage medium. Background Technology

[0002] With the development of intelligent and connected vehicles, the application of vehicle assistance technology in vehicles is becoming more and more common. Among them, emergency obstacle avoidance is one of the important aspects of vehicle assistance technology.

[0003] However, the emergency obstacle avoidance capabilities of vehicles still need to be improved in the current technology. Summary of the Invention

[0004] In view of the above, embodiments of this application provide a vehicle control method, apparatus, vehicle, and storage medium.

[0005] The first aspect of this application provides a vehicle control method, including acquiring the location information of target obstacles within a preset range of the vehicle; wherein the target obstacles include dynamic obstacles and static obstacles; determining the dynamic risk field of the dynamic obstacles and the static risk field of the static obstacles based on the location information; acquiring the traffic rule risk field within the preset range; determining the spatiotemporal risk field within the preset range based on the dynamic risk field, the static risk field and the traffic rule risk field, forming a spatiotemporal risk field distribution map; and controlling the vehicle to execute a corresponding response strategy based on the spatiotemporal risk field distribution map.

[0006] In one embodiment, the spatiotemporal risk field distribution map includes risk gradient, risk change rate, and collision time; based on the spatiotemporal risk distribution map, controlling the vehicle to execute different response strategies includes: if the risk gradient is greater than or equal to a first gradient threshold and the risk change rate is greater than or equal to a first change rate threshold, then controlling the vehicle to issue a warning message; if the risk gradient is greater than or equal to a second gradient threshold and the collision time is less than a first time threshold, then controlling the vehicle to travel along the target path.

[0007] In one embodiment, if the risk gradient is greater than or equal to a second gradient threshold and the collision time is less than a first time threshold, controlling the vehicle to travel along the target path includes: if the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, obtaining multiple candidate locations in the spatiotemporal risk field distribution map where the spatiotemporal risk field is less than or equal to the risk field threshold; determining driving information for the vehicle to travel to the candidate locations based on the candidate locations; wherein the driving information includes the vehicle's acceleration and path offset; determining the target location based on the spatiotemporal risk field and driving information of the multiple candidate locations; determining the target path for the vehicle to travel to the target location, and controlling the vehicle to travel along the target path.

[0008] In one embodiment, determining the target location based on the spatiotemporal risk field and driving information of multiple candidate locations includes: if the risk gradient is greater than or equal to a second gradient threshold and the collision time is less than a first time threshold, then assigning a first weight to the spatiotemporal risk field and a second weight to the driving information; if the risk gradient is greater than or equal to a third gradient threshold and the collision time is less than the second time threshold, then assigning a third weight to the spatiotemporal risk field and a fourth weight to the driving information; wherein the first weight is greater than the third weight and the fourth weight is less than the second weight; and the target location is determined based on the weighted spatiotemporal risk field and driving information.

[0009] In one embodiment, controlling the vehicle to travel along a target path includes: calculating the vehicle's critical steering angle in real time; if the vehicle's steering angle is less than or equal to the critical steering angle, controlling the vehicle to steer according to the steering angle; if the vehicle's steering angle is greater than the critical steering angle, controlling the vehicle to steer according to the critical steering angle.

[0010] In one embodiment, controlling a vehicle to travel along a target path includes: acquiring the vehicle's driving state; wherein the driving state includes the vehicle's yaw rate, lateral acceleration, wheel speed, and body slip angle, and the driving state includes a target driving state and an actual driving state; calculating the vehicle's corrective yaw moment based on the target driving state and the actual driving state; distributing grip force to the vehicle's wheels based on the corrective yaw moment; and controlling the vehicle to travel along the target path based on the grip force.

[0011] In one embodiment, the vehicle includes a vision sensor, a first position sensor, and a second position sensor; obtaining the position information of a target obstacle within a preset range of the vehicle includes: determining whether a target obstacle exists within the preset range based on the vision sensor; if a target obstacle exists within the preset range, obtaining a first detection result from the first position sensor and a second detection result from the second position sensor; and determining the position information of the target obstacle based on the first and second detection results.

[0012] A second aspect of this application provides a vehicle control device, including a first acquisition module for acquiring position information of target obstacles within a preset range of the vehicle; wherein the target obstacles include dynamic obstacles and static obstacles; a first determination module for determining the dynamic risk field of the dynamic obstacles and the static risk field of the static obstacles based on the position information; a second acquisition module for acquiring a traffic rule risk field within the preset range; a second determination module for determining a spatiotemporal risk field within the preset range based on the dynamic risk field, the static risk field, and the traffic rule risk field, forming a spatiotemporal risk field distribution map; and a control module for controlling the vehicle to execute a corresponding response strategy based on the risk field distribution map.

[0013] A third aspect of this application provides a vehicle including one or more processors and a memory; one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs being configured to perform the control method described above.

[0014] A fourth aspect of this application provides a computer-readable storage medium storing processor-executable program code, the computer-readable storage medium including stored program code, wherein the above-described control method is executed when the program code is run.

[0015] This application provides a vehicle control method, device, vehicle, and storage medium. The method involves acquiring the location information of target obstacles within a preset range of the vehicle; wherein the target obstacles include dynamic obstacles and static obstacles; determining the dynamic risk field of the dynamic obstacles and the static risk field of the static obstacles based on the location information; acquiring the traffic rule risk field within the preset range; determining the spatiotemporal risk field within the preset range based on the dynamic risk field, static risk field, and traffic rule risk field, forming a spatiotemporal risk field distribution map; and controlling the vehicle to execute corresponding response strategies based on the spatiotemporal risk field distribution map. This method, by jointly determining the spatiotemporal risk field distribution within the preset range of the vehicle using the dynamic risk field, static risk field, and traffic rule risk field, can quickly identify dynamic obstacles, respond to sudden dangers (such as the sudden appearance of a vehicle or a pedestrian suddenly turning), improve the vehicle's risk perception capability, enhance its emergency obstacle avoidance capability, and improve vehicle safety. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the application environment for a vehicle control method proposed in this application.

[0018] Figure 2 This is a schematic flowchart of a vehicle control method provided in the first embodiment of this application.

[0019] Figure 3 This is a flowchart illustrating a vehicle control method provided in the second embodiment of this application.

[0020] Figure 4 This is a flowchart illustrating a vehicle control method provided in the third embodiment of this application.

[0021] Figure 5This is a flowchart illustrating a vehicle control method provided in the fourth embodiment of this application.

[0022] Figure 6 This is a structural block diagram of a vehicle control device provided in this application.

[0023] Figure 7 This is a structural block diagram of a vehicle provided in this application.

[0024] Figure 8 This is a structural block diagram of a computer-readable storage medium proposed in an embodiment of this application. Detailed Implementation

[0025] With the development of intelligent and connected vehicles, the application of vehicle-assisted driving technology is becoming increasingly common. Among these technologies, emergency obstacle avoidance is a crucial component. However, current technologies still have limitations in emergency obstacle avoidance, exhibiting drawbacks such as perception limitations, static risk assessment, and decision-making delays.

[0026] To address the aforementioned problems, this application provides a vehicle control method, device, vehicle, and storage medium. The method involves acquiring the location information of target obstacles within a preset range of the vehicle; wherein the target obstacles include dynamic obstacles and static obstacles; determining the dynamic risk field of the dynamic obstacles and the static risk field of the static obstacles based on the location information; acquiring the traffic rule risk field within the preset range; determining the spatiotemporal risk field within the preset range based on the dynamic risk field, static risk field, and traffic rule risk field, forming a spatiotemporal risk field distribution map; and controlling the vehicle to execute corresponding response strategies based on the spatiotemporal risk field distribution map. This method, by jointly determining the spatiotemporal risk field distribution within the preset range of the vehicle using the dynamic risk field, static risk field, and traffic rule risk field, can quickly identify dynamic obstacles, respond to sudden dangers (such as the sudden appearance of a vehicle or a pedestrian suddenly turning), improve the vehicle's risk perception capability, enhance its emergency obstacle avoidance capability, and improve vehicle safety.

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] Furthermore, to better illustrate this application, numerous specific details are provided in the following detailed embodiments. Those skilled in the art should understand that this application can be implemented even without certain specific details. In some instances, methods and means well-known to those skilled in the art have not been described in detail in order to highlight the main points of this application.

[0029] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0030] Furthermore, the terms "first" and "second" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0031] Unless the context otherwise requires, throughout this specification, "a plurality of" means "at least two," and "including" is interpreted as open-ended or encompassing, that is, "including, but not limited to." In the description of this specification, terms such as "one embodiment," "some embodiments," "exemplary embodiment," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this specification. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example.

[0032] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0033] To facilitate a detailed explanation of the present application, the application environment of the embodiments of the present application will be described below with reference to the accompanying drawings. Please refer to... Figure 1 , Figure 1 This is a schematic diagram illustrating the application environment of a vehicle control method proposed in this application. For example... Figure 1 As shown, the vehicle control method provided in this application is applied to vehicle 10. In terms of energy, vehicle 10 can be an electric vehicle, a fuel vehicle, or a hybrid electric vehicle, etc. This application does not limit it.

[0034] The vehicle 10 may include a vehicle controller 110 and a control system 120. In the method provided in this application embodiment, the vehicle controller 110 and the control system 120 may be communicatively connected or / and electrically connected to each other. The vehicle controller 110 is used to determine the single adjustment amount of the air suspension based on the driving data of the vehicle 10, and the control system 120 controls the power of the vehicle 10, such as controlling the vehicle 10 to drive along a preset path.

[0035] The vehicle controller 110 is typically a vehicle center console, and its explicit control can be displayed through the vehicle 10's central control screen and / or control panel. In other embodiments, such as for autonomous vehicles, the vehicle controller 110 may also be based on a control center such as a server or a microcomputer control chip, but it is not limited to these. The server can be a standalone physical server, a server cluster consisting of multiple physical servers, or a distributed system. The microcomputer control chip can be an analog integrated circuit chip, a digital integrated circuit chip, or a mixed-signal integrated circuit chip. The vehicle controller 110 may be equipped with a transceiver or signal transmission interface, through which the vehicle controller 110 can receive detection data sent by the sensors configured on the vehicle 10 and send control signals to the control system 120.

[0036] Vehicle 10 may include a main body, accelerator pedal, brake pedal, steering wheel, wheels, etc. The accelerator pedal, brake pedal, steering wheel, and wheels are all associated with control system 120 (either through direct physical connection or electrical connection, such as through a CAN communication line). Control system 120 may be equipped with a transceiver, which is used to receive control signals sent by vehicle controller 110 through the transceiver and respond to the control signals to control vehicle 10.

[0037] The control system 120 may include a power drive system and a braking control system. It should be understood that the power drive system involved in this application embodiment refers to a series of components on the vehicle 10 that generate power and transmit that power to the road surface. For new energy vehicles, the power drive system may include a traction motor, a motor controller, a reducer, and auxiliary mechanical transmission devices, etc. In this application embodiment, the power drive system may be a centralized power drive system or a distributed power drive system; this application embodiment does not specifically limit this. The braking control system may be a distributed braking control system. For example, the braking control system may include components such as a power supply, a brake wheel controller, a brake master cylinder, a master cylinder displacement sensor, a brake pedal, a pedal displacement sensor, and an electric power assist device, etc. This application does not limit this.

[0038] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0039] Please see Figure 2 , Figure 2 This is a schematic flowchart of a vehicle control method provided in the first embodiment of this application. The method may include the following steps S210 to S250.

[0040] Step S210: Obtain the location information of the target obstacle within the preset range of the vehicle.

[0041] The target obstacles include both dynamic and static obstacles.

[0042] The preset range defines the spatial boundaries, such as 100 meters in front of the vehicle and 30 meters on each side. This can be a rectangular area or a fan-shaped area.

[0043] Target obstacles refer to any objects that may interact with or conflict with the vehicle.

[0044] Dynamic obstacles can refer to other vehicles, pedestrians, bicycles, motorcycles, etc.

[0045] Static obstacles can refer to roadside guardrails, curbs, roadblocks, construction areas, illegally parked vehicles, etc.

[0046] Location information includes, but is not limited to, absolute coordinates (e.g., latitude and longitude) or relative coordinates (e.g., longitudinal and lateral distances relative to the vehicle), as well as information such as the speed, acceleration, heading angle, and trajectory prediction of dynamic obstacles.

[0047] In one approach, the vehicle controller can obtain the location information of the target obstacle using a single sensor.

[0048] In one approach, the vehicle controller can acquire the location information of the target obstacle through multi-sensor fusion. For example, the vehicle controller can acquire the location information of the target obstacle through multi-sensor fusion.

[0049] Step S220: Based on location information, determine the dynamic risk field of dynamic obstacles and the static risk field of static obstacles.

[0050] In this embodiment, the vehicle controller determines the dynamic risk field of the dynamic obstacle based on the location information of the dynamic obstacle.

[0051] Specifically, the vehicle controller can quantify the motion uncertainty of dynamic obstacles and calculate the dynamic risk field of the obstacles based on the location information of the dynamic obstacles and using a preset calculation relationship (such as an LSTM-GMM trajectory prediction model). For example, the dynamic risk field... It can be calculated based on the following formula: in, () represents the coordinates of a point in space. For time, The number of dynamic obstacles within a preset range. Indexing obstacles Let i be the risk weight of the i-th dynamic obstacle. Let be the predicted position coordinates of the i-th dynamic obstacle. For the i-th dynamic obstacle in time Standard deviation of positional uncertainty This is the squared distance from the current calculation point to the predicted location of the dynamic obstacle.

[0052] in, It can be dynamically adjusted based on the speed of dynamic obstacles and the prediction confidence level. Specifically... The speed of the dynamic obstacle is directly proportional to its velocity and inversely proportional to the confidence level of the perception module's prediction of that obstacle. In other words, the faster the dynamic obstacle moves, the higher its speed. The larger the value, the better.

[0053] Based on the type of dynamic obstacle (e.g., pedestrians) Vehicles Differential assignments (e.g.) are not restricted in this application.

[0054] In this embodiment, the vehicle controller determines the static risk field of the static obstacle based on its location information. For example, the risk center is located on the geometric boundary of the static obstacle and gradually decreases with the distance from the static obstacle.

[0055] Step S230: Obtain the traffic rule risk field within the preset range.

[0056] Among them, the traffic rule risk field is defined by the road structure and traffic rules, and includes, but is not limited to, lane line risk field, road boundary risk field, traffic sign / signal risk field, speed limit risk field, etc.

[0057] In one approach, the vehicle controller can obtain traffic rule risk fields within a preset range based on maps and positioning modules. For example, if lane lines, stop lines, speed limits, and other information are pre-marked on the map, the vehicle controller can determine its position relative to these rule elements through precise positioning, thereby querying the corresponding traffic rule risk fields.

[0058] Step S240: Based on the dynamic risk field, static risk field and traffic rule risk field, determine the spatiotemporal risk field within the preset range and form a spatiotemporal risk field distribution map.

[0059] The spatiotemporal risk distribution map includes the risk field distribution of each point within the prediction range as it changes over time.

[0060] The vehicle controller can determine the spatiotemporal risk field within a preset range based on the dynamic risk field, static risk field, and traffic rule risk field.

[0061] Specifically, the vehicle controller can calculate the spatiotemporal risk field of dynamic obstacles based on the dynamic risk field, static risk field, and traffic rule risk field, using preset calculation relationships. For example, the spatiotemporal risk field... It can be calculated based on the following formula: in, , , These are the normalized weighted coefficients. For static risk fields, As a dynamic risk field, It is a risky area for traffic rules.

[0062] in, This is used to adjust the contribution of different risk sources. , , It can be set according to the actual situation, for example, This application does not impose any restrictions.

[0063] As a scalar field, its value is determined by the semantics of traffic rules. For example, when the light is red, the risk value of the area behind the stop line is 0, the risk value of the intersection area in front of the stop line increases sharply, and the risk value in the restricted area (such as curbs and construction fences) is a fixed maximum value.

[0064] Step S250: Based on the spatiotemporal risk field distribution map, control the vehicle to execute the corresponding response strategy.

[0065] Based on the spatiotemporal risk field distribution map, the vehicle controller controls the vehicle to execute corresponding response strategies. These response strategies may include controlling the vehicle to issue warning information or controlling the vehicle to travel along the target path.

[0066] As one approach, if the risk gradient is greater than or equal to the first gradient threshold and the risk change rate is greater than or equal to the change rate threshold, then the vehicle is controlled to issue a warning message.

[0067] As one approach, if the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, the vehicle is controlled to travel along the target path.

[0068] This application provides a vehicle control method that determines the spatiotemporal risk field distribution within a preset range of the vehicle by jointly determining the dynamic risk field, static risk field, and traffic rule risk field. This method can quickly identify dynamic obstacles, respond to sudden dangers (such as the sudden appearance of a vehicle or a pedestrian suddenly turning), improve the vehicle's risk perception ability, enhance the vehicle's emergency obstacle avoidance ability, and improve the vehicle's safety.

[0069] Please see Figure 3 , Figure 3This is a flowchart illustrating a vehicle control method according to a second embodiment of this application. In this embodiment, the vehicle includes a vision sensor, a first position sensor, and a second position sensor. Obtaining the position information of a target obstacle within a preset range of the vehicle (step S210) may include: Step S310: Based on the visual sensor, determine whether there is a target obstacle within the preset range.

[0070] In this embodiment, the visual sensor can be an event camera, which can continuously monitor the brightness change event stream within a preset field of view.

[0071] The vehicle controller can determine whether there are target obstacles within a preset range based on the event camera.

[0072] Specifically, the event camera can collect event streams within a very short time window (e.g., 5 milliseconds), and then use algorithms such as DBSCAN, K-Means, or distance-based connected component analysis to cluster events that are close in time and space into a group. Then, by analyzing the shape, size, and aspect ratio of the clustered event clusters, it can initially distinguish whether they are "clump-shaped" (pedestrians) or "strip-shaped" (vehicle sides). Finally, it outputs one or more motion patches, including their 2D image location, size, and motion vector.

[0073] Step S320: If there is a target obstacle within the preset range, then obtain the first detection result of the first position sensor and the second detection result of the second position sensor.

[0074] In this embodiment, the first position sensor can be a 4D millimeter-wave radar, which can output 4D information of the target obstacle (velocity, acceleration, azimuth angle, and pitch angle).

[0075] Therefore, the first detection result includes 4D information of the target obstacle (velocity, acceleration, azimuth, pitch).

[0076] In this embodiment, the second position sensor can be a solid-state lidar, which can generate a dense point cloud of the surrounding environment by scanning with a laser beam, and can accurately depict the outline, shape and surface details of obstacles.

[0077] Therefore, the second detection result includes the outline, shape, and surface details of the target obstacle.

[0078] Step S330: Based on the first detection result and the second detection result, determine the location information of the target obstacle.

[0079] After the vehicle controller obtains the first and second detection results, it can determine the location information of the target obstacle through BEV feature fusion.

[0080] Specifically, the vehicle controller extracts depth features from millimeter-wave radar point clouds, lidar point clouds, and camera images through point cloud backbone networks and visual backbone networks, respectively. Then, the multimodal features are uniformly mapped to a bird's-eye view space—radar and lidar point cloud features directly generate a BEV feature map, while image features are converted into BEV feature representations through depth estimation-based projection or Transformer-based view transformation methods. Next, the aligned multimodal features in the BEV space are deeply fused, typically using channel stitching combined with convolution or cross-modal attention mechanisms to achieve complementary enhancement of geometric, texture, and motion information. Finally, based on the fused unified BEV feature map, the precise 3D position, size, heading angle, and velocity vector of the target obstacle are directly regressed using a 3D detection decoder, forming a perception result with both spatial accuracy and semantic integrity, thus obtaining the target obstacle's position information.

[0081] This application provides a vehicle control method. In this method, based on a visual sensor, it is determined whether a target obstacle exists within a preset range; if a target obstacle exists within the preset range, a first detection result from a first position sensor and a second detection result from a second position sensor are acquired; based on the first and second detection results, the position information of the target obstacle is determined. This method utilizes a combination of an event camera and a lidar system. For example, the event camera captures the initial motion state of the target obstacle (such as a pedestrian lifting their leg), and the lidar completes the outline of the target obstacle, solving the problem of detection delay for sudden movements by traditional sensors and improving the vehicle's risk prediction capability.

[0082] Please see Figure 4 , Figure 4 This is a flowchart illustrating a vehicle control method according to a third embodiment of this application. In this embodiment, the spatiotemporal risk field distribution map includes risk gradient, risk change rate, and collision time. Based on the spatiotemporal risk field distribution map, controlling the vehicle to execute the corresponding response strategy (step 250) may include: Step S410: If the risk gradient is greater than or equal to the first gradient threshold and the risk change rate is greater than or equal to the change rate threshold, then control the vehicle to issue a warning message.

[0083] The first gradient threshold can be set by default by the vehicle controller or by the user. Generally, the first gradient threshold can be 0.6, 0.7, 0.8, 0.9, etc. For example, the first gradient threshold is 0.8.

[0084] The rate of change threshold can be a default setting of the vehicle controller or a user-defined setting. Generally, the rate of change threshold can be 1.3, 1.4, 1.5, 1.6, etc. For example, the rate of change threshold is 1.5.

[0085] When the vehicle controller determines that the risk gradient is greater than or equal to 0.8 and the risk change rate is greater than or equal to 1.5, it controls the vehicle to issue a warning message.

[0086] Warning information may include voice prompts, in-vehicle displays, etc.

[0087] Step S420: If the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, then control the vehicle to travel along the target path.

[0088] The second gradient threshold can be set by default by the vehicle controller or by the user. Generally, the second gradient threshold can be 1.3, 1.4, 1.5, 1.6, etc. For example, the second gradient threshold is 1.5.

[0089] The first time threshold can be set by default by the vehicle controller or by the user. Generally, the first time threshold can be 1.8 seconds, 1.9 seconds, 2 seconds, 2.1 seconds, etc. For example, the first time threshold is 2 seconds.

[0090] When the vehicle controller determines that the risk gradient is greater than or equal to 1.5 and the collision time is less than 2 seconds, it controls the vehicle to travel along the target path.

[0091] In one approach, when the vehicle controller determines that the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, it controls the vehicle to make local path adjustments, such as controlling the vehicle to deviate laterally.

[0092] In one approach, when the vehicle controller determines that the risk gradient is greater than or equal to the third gradient threshold and the collision time is less than the second time threshold, combined braking and steering take over the vehicle in an emergency.

[0093] The third gradient threshold can be set by default by the vehicle controller or by the user. Generally, the third gradient threshold can be 2.3, 2.4, 2.5, 2.6, etc. For example, the third gradient threshold is 2.5.

[0094] The second time threshold can be a default setting of the vehicle controller or a user-defined setting. Generally, the second time threshold can be 0.6 seconds, 0.7 seconds, 0.8 seconds, 0.9 seconds, etc. For example, the second time threshold is 0.8 seconds.

[0095] When the vehicle controller determines that the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the second time threshold, the combined braking and steering take over the vehicle in an emergency.

[0096] This application provides a vehicle control method. In this method, if the risk gradient is greater than or equal to a first gradient threshold and the risk change rate is greater than or equal to a change rate threshold, the vehicle is controlled to issue a warning message; if the risk gradient is greater than or equal to a second gradient threshold and the collision time is less than a first time threshold, the vehicle is controlled to travel along the target path. This method determines the corresponding response strategy to be executed by the vehicle based on the risk gradient, risk change rate, and collision time, thereby improving vehicle safety.

[0097] Please see Figure 5 , Figure 5 This is a flowchart illustrating a vehicle control method provided in the fourth embodiment of this application. If the risk gradient is greater than or equal to a second gradient threshold, and the collision time is less than a first time threshold, then controlling the vehicle to travel along the target path (step S420) includes: Step S510: If the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, then obtain multiple candidate positions in the spatiotemporal risk field distribution map where the spatiotemporal risk field is less than or equal to the risk field threshold.

[0098] If the vehicle controller determines that the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, then it obtains multiple candidate locations in the spatiotemporal risk field distribution map where the spatiotemporal risk field is less than or equal to the risk field threshold.

[0099] The risk field threshold can be either the default setting of the vehicle controller or a user-defined setting.

[0100] Candidate positions can be either side of the vehicle's current lane, adjacent lanes, etc.

[0101] Step S520: Determine the driving information of the vehicle to the candidate position based on the candidate position; wherein, the driving information includes the vehicle's acceleration and path offset.

[0102] Here, vehicle acceleration refers to longitudinal acceleration (i.e., the intensity of braking or acceleration). A specific velocity change curve is required to reach a candidate position from the current position. More aggressive (larger negative values) deceleration results in faster deceleration but may affect comfort and stability; slight acceleration may be used for "accelerated maneuvering."

[0103] Path offset refers to lateral offset (i.e., lateral displacement corresponding to the steering wheel angle), which determines how far the vehicle needs to deviate from the original path to the left or right.

[0104] In one approach, the vehicle controller can use a vehicle kinematics or dynamics model to determine the driving information for the vehicle to travel to a candidate position.

[0105] Step S530: Determine the target location based on the spatiotemporal risk field and driving information of multiple candidate locations.

[0106] The vehicle controller can calculate a weighted sum of risk and comfort at multiple candidate locations based on the spatiotemporal risk field and driving information, using a preset calculation relationship. The candidate location with the smallest weighted sum is then selected as the target location. Specifically, the weighted sum of the target location can be calculated using the following formula: in, This represents a candidate trajectory consisting of N path points. For candidate position index, For trajectory To the left of the k-th path point, For the spacetime risk field Risk field gradient at the location, Let be the longitudinal acceleration of the vehicle on the k-th path. Let be the yaw rate of the vehicle on the k-th path. It is a balance coefficient between risk and comfort.

[0107] in, This represents the direction and intensity of the risk change; minimizing this means the trajectory should shift towards the lower wind direction.

[0108] and Minimizing is to avoid sudden acceleration, deceleration, and sharp turns, thus ensuring vehicle comfort.

[0109] As a way, It can be dynamically adjusted by the driver's driving style model, within the range of [0.1]. For example, in aggressive mode, =0.7, the vehicle controller tends to take risks in exchange for more efficient obstacle avoidance; in conservative mode, =0.9, the vehicle controller should minimize risks and prioritize safety.

[0110] As a way, It can be dynamically adjusted based on risk gradients and collision events. (Assumption) As the first and third weights, These are the second and fourth weights.

[0111] Based on the spatiotemporal risk field and driving information of multiple candidate locations, the target location is determined as follows: If the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, then the spatiotemporal risk field is assigned a first weight, and the driving information is assigned a second weight. If the risk gradient is greater than or equal to the third gradient threshold and the collision time is less than the second time threshold, then the spatiotemporal risk field is assigned a third weight, and the driving information is assigned a fourth weight; wherein, the first weight is greater than the third weight, and the fourth weight is less than the second weight.

[0112] That is, if the risk gradient is greater than or equal to the second gradient threshold, and the collision time is less than the first time threshold, then... Larger Smaller; if the risk gradient is greater than or equal to the third gradient threshold, and the collision time is less than the second time threshold, then Smaller Relatively large.

[0113] The vehicle controller determines the target location based on the weighted spatiotemporal risk field and driving information.

[0114] Step S540: Determine the target path for the vehicle to travel to the target location, and control the vehicle to travel along the target path.

[0115] Based on the target location, the vehicle controller uses a vehicle kinematics or dynamics model to determine the target path for the vehicle to travel to the target location. Then, it sends control commands to the power system. The control commands carry the target path. After reading the control commands, the control system controls the vehicle to travel along the target path.

[0116] As one approach, the vehicle controller can employ a redundant design of ESP and electro-hydraulic braking to improve the vehicle's braking accuracy and reduce response time.

[0117] One method of controlling a vehicle to travel along a target path includes: calculating the vehicle's critical steering angle in real time; if the vehicle's steering angle is less than or equal to the critical steering angle, controlling the vehicle to steer according to the steering angle; if the vehicle's steering angle is greater than the critical steering angle, controlling the vehicle to steer according to the critical steering angle to prevent the vehicle from overturning.

[0118] Specifically, the critical steering angle It can be calculated using the following formula: in, For the speed of the vehicle, This represents the vehicle's turning radius. is the acceleration constant.

[0119] Specifically, vehicles can be equipped with steering angle sensors, which are used to detect the vehicle's steering angle.

[0120] As one method, controlling a vehicle to travel along a target path includes: acquiring the vehicle's driving state; wherein the driving state includes the vehicle's yaw rate, lateral acceleration, wheel speed, and body slip angle, and includes a target driving state and an actual driving state; calculating the vehicle's corrective yaw moment based on the target driving state and the actual driving state; distributing grip force to the vehicle's wheels based on the corrective yaw moment; and controlling the vehicle to travel along the target path based on the grip force to prevent oversteering.

[0121] Specifically, the vehicle may be equipped with a yaw rate sensor, a lateral acceleration sensor, a wheel speed sensor, and a body slip angle sensor. The yaw rate sensor is used to detect the yaw rate of the vehicle, the lateral acceleration sensor is used to detect the lateral acceleration of the vehicle, the wheel speed sensor is used to detect the wheel speed of the vehicle, and the body slip angle sensor is used to detect the body slip angle of the vehicle.

[0122] This application provides a vehicle control method. In this method, if the risk gradient is greater than or equal to a second gradient threshold and the collision time is less than a first time threshold, multiple candidate locations in the spatiotemporal risk field distribution map where the spatiotemporal risk field is less than or equal to the risk field threshold are obtained. Based on the candidate locations, driving information for the vehicle to travel to the candidate locations is determined; wherein, the driving information includes the vehicle's acceleration and path offset. Based on the spatiotemporal risk field and driving information of the multiple candidate locations, a target location is determined; a target path for the vehicle to travel to the target location is determined, and the vehicle is controlled to travel along the target path. The above method determines the target location and target path based on the spatiotemporal risk field and driving information, maintaining the comfort of the occupants while reducing risk.

[0123] Please see Figure 6 , Figure 6 This is a structural block diagram of a vehicle control device provided in this application. The vehicle control device 600 provided in this application includes: a first acquisition module 610, a first determination module 620, a second acquisition module 630, a second determination module 640, and a control module 650.

[0124] The first acquisition module 610 is used to acquire the location information of target obstacles within a preset range of the vehicle; wherein, the target obstacles include dynamic obstacles and static obstacles; the first determination module 620 is used to determine the dynamic risk field of dynamic obstacles and the static risk field of static obstacles based on the location information; the second acquisition module 630 is used to acquire the traffic rule risk field within the preset range; the second determination module 640 is used to determine the spatiotemporal risk field within the preset range based on the dynamic risk field, the static risk field and the traffic rule risk field, and form a spatiotemporal risk field distribution map; the control module 650 is used to control the vehicle to execute the corresponding response strategy based on the risk field distribution map.

[0125] This application provides a vehicle control device. The device acquires the location information of target obstacles within a preset range of the vehicle; wherein the target obstacles include dynamic obstacles and static obstacles; based on the location information, it determines the dynamic risk field of the dynamic obstacles and the static risk field of the static obstacles; it acquires the traffic rule risk field within the preset range; based on the dynamic risk field, static risk field, and traffic rule risk field, it determines the spatiotemporal risk field within the preset range, forming a spatiotemporal risk field distribution map; based on the spatiotemporal risk field distribution map, it controls the vehicle to execute corresponding response strategies. The above device, by jointly determining the spatiotemporal risk field distribution within the preset range of the vehicle through the dynamic risk field, static risk field, and traffic rule risk field, can quickly identify dynamic obstacles, respond to sudden dangers (such as the sudden appearance of a vehicle, a pedestrian suddenly turning, etc.), improve the vehicle's risk perception capability, and also improve the vehicle's emergency obstacle avoidance capability, thereby enhancing vehicle safety.

[0126] In some embodiments, the spatiotemporal risk field distribution map includes a risk gradient, a risk change rate, and a collision time; the control module 650 is further configured to control the vehicle to issue a warning message if the risk gradient is greater than or equal to a first gradient threshold and the risk change rate is greater than or equal to a change rate threshold; and to control the vehicle to travel along the target path if the risk gradient is greater than or equal to a second gradient threshold and the collision time is less than a first time threshold.

[0127] In some embodiments, the control module 650 is further configured to control the vehicle to travel along the target path if the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, including: if the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, acquiring multiple candidate locations in the spatiotemporal risk field distribution map where the spatiotemporal risk field is less than or equal to the risk field threshold; determining driving information of the vehicle to the candidate location based on the candidate location; wherein the driving information includes the vehicle's acceleration and path offset; determining the target location based on the spatiotemporal risk field of the multiple candidate locations and the driving information; determining the target path of the vehicle to the target location, and controlling the vehicle to travel along the target path.

[0128] In some embodiments, the control module 650 is further configured to assign a first weight to the spatiotemporal risk field and a second weight to the driving information if the risk gradient is greater than or equal to a second gradient threshold and the collision time is less than a first time threshold; and to assign a third weight to the spatiotemporal risk field and a fourth weight to the driving information if the risk gradient is greater than or equal to a third gradient threshold and the collision time is less than the second time threshold; wherein the first weight is greater than the third weight and the fourth weight is less than the second weight; and to determine the target location based on the weighted spatiotemporal risk field and the driving information.

[0129] In some embodiments, the control module 650 is further configured to calculate the critical steering angle of the vehicle in real time; if the vehicle's steering angle is less than or equal to the critical steering angle, the vehicle is controlled to steer according to the steering angle; if the vehicle's steering angle is greater than the critical steering angle, the vehicle is controlled to steer according to the critical steering angle.

[0130] In some embodiments, the control module 650 is further configured to acquire the vehicle's driving state; wherein the driving state includes the vehicle's yaw rate, lateral acceleration, wheel speed, and body slip angle, and the driving state includes a target driving state and an actual driving state; calculate the vehicle's corrective yaw torque based on the target driving state and the actual driving state; distribute grip force to the vehicle's wheels based on the corrective yaw torque; and control the vehicle to travel along the target path based on the grip force.

[0131] In some embodiments, the vehicle includes a vision sensor, a first position sensor, and a second position sensor; the first acquisition module 610 is further configured to determine, based on the vision sensor, whether there is a target obstacle within a preset range; if there is a target obstacle within the preset range, acquire a first detection result from the first position sensor and a second detection result from the second position sensor; and determine the position information of the target obstacle based on the first detection result and the second detection result.

[0132] This application provides a structural block diagram of a vehicle control device. It should be noted that the device embodiment in this application corresponds to the aforementioned method embodiment. The specific implementation principle of each unit in the device embodiment is similar to that in the aforementioned method embodiment. The specific content in the device embodiment can be referred to the method embodiment, while it will not be repeated in the device embodiment.

[0133] Please see Figure 7 , Figure 7 This is a structural block diagram of a vehicle provided in this application.

[0134] Based on the vehicle control method and apparatus described above, this application embodiment also provides another vehicle 700 capable of executing the aforementioned vehicle control method. The vehicle 700 can be an electric vehicle, a gasoline-powered vehicle, or other vehicle capable of running applications. The vehicle 700 includes one or more (only one shown in the figure) processors 710 and a memory 720 coupled together. The memory 720 stores programs capable of executing the contents of the aforementioned embodiments, and the processors 710 can execute the programs stored in the memory 720.

[0135] The processor 710 may include one or more cores for processing data. The processor 710 connects to various parts of the vehicle 700 via various interfaces and lines, and performs various functions and processes data of the vehicle 700 by running or executing instructions, programs, code sets, or instruction sets stored in the memory 720, and by calling data stored in the memory 720. Optionally, the processor 710 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 710 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 710 and may be implemented separately through a communication chip.

[0136] The memory 720 may include random access memory (RAM) or read-only memory (ROM). The memory 720 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 720 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described below.

[0137] This application embodiment can divide the vehicle into functional modules according to the above method embodiment. For example, each function can be assigned to a separate module, or two or more functions can be integrated into a processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. When dividing each functional module according to its corresponding function, the vehicle may include a processing module and a communication module, etc.

[0138] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here. The vehicle provided in this embodiment is used to execute the above-described vehicle control method, and therefore can achieve the same effect as the above implementation method.

[0139] Please see Figure 8 , Figure 8 This is a structural block diagram of a computer-readable storage medium according to an embodiment of this application. The computer-readable medium 800 stores program code, which can be called by a processor to execute the methods described in the above method embodiments.

[0140] The computer-readable storage medium 800 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 800 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 800 has storage space for program code 88 that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code 88 may be compressed, for example, in a suitable form.

[0141] It should be noted that the descriptions of the above embodiments of storage media, devices, and equipment are similar to the descriptions of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the embodiments of storage media, devices, and equipment of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0142] This application provides a vehicle control method, device, vehicle, and storage medium. The method involves acquiring the location information of target obstacles within a preset range of the vehicle; wherein the target obstacles include dynamic obstacles and static obstacles; determining the dynamic risk field of the dynamic obstacles and the static risk field of the static obstacles based on the location information; acquiring the traffic rule risk field within the preset range; determining the spatiotemporal risk field within the preset range based on the dynamic risk field, static risk field, and traffic rule risk field, forming a spatiotemporal risk field distribution map; and controlling the vehicle to execute corresponding response strategies based on the spatiotemporal risk field distribution map. This method, by jointly determining the spatiotemporal risk field distribution within the preset range of the vehicle using the dynamic risk field, static risk field, and traffic rule risk field, can quickly identify dynamic obstacles, respond to sudden dangers (such as the sudden appearance of a vehicle or a pedestrian suddenly turning), improve the vehicle's risk perception capability, enhance its emergency obstacle avoidance capability, and improve vehicle safety.

[0143] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0144] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for controlling a vehicle, characterized in that, include: The location information of target obstacles within a preset range of the vehicle is obtained; wherein, the target obstacles include dynamic obstacles and static obstacles; Based on the location information, the dynamic risk field of the dynamic obstacle and the static risk field of the static obstacle are determined; Obtain the traffic rule risk field within the preset range; Based on the dynamic risk field, the static risk field, and the traffic rule risk field, the spatiotemporal risk field within the preset range is determined, and a spatiotemporal risk field distribution map is formed. Based on the spatiotemporal risk field distribution map, the vehicle is controlled to execute the corresponding response strategy.

2. The control method according to claim 1, characterized in that, The spatiotemporal risk field distribution map includes risk gradient, risk change rate, and collision time; The control of the vehicle to execute different response strategies based on the spatiotemporal risk distribution map includes: If the risk gradient is greater than or equal to the first gradient threshold, and the risk change rate is greater than or equal to the change rate threshold, then the vehicle is controlled to issue a warning message. If the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, then the vehicle is controlled to travel along the target path.

3. The control method according to claim 2, characterized in that, If the risk gradient is greater than or equal to the second gradient threshold, and the collision time is less than the first time threshold, then controlling the vehicle to travel along the target path includes: If the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, then multiple candidate positions in the spatiotemporal risk field distribution map where the spatiotemporal risk field is less than or equal to the risk field threshold are obtained. Based on the candidate location, driving information of the vehicle to the candidate location is determined; wherein, the driving information includes the vehicle's acceleration and path offset; The target location is determined based on the spatiotemporal risk field of multiple candidate locations and the driving information; Determine the target path for the vehicle to travel to the target location, and control the vehicle to travel along the target path.

4. The control method according to claim 3, characterized in that, Based on the spatiotemporal risk field of multiple candidate locations and the driving information, determining the target location includes: If the risk gradient is greater than or equal to the second gradient threshold and the collision time is less than the first time threshold, then the spatiotemporal risk field is assigned a first weight and the driving information is assigned a second weight. If the risk gradient is greater than or equal to the third gradient threshold and the collision time is less than the second time threshold, then the spatiotemporal risk field is assigned a third weight and the driving information is assigned a fourth weight; wherein, the first weight is greater than the third weight and the fourth weight is less than the second weight; The target location is determined based on the weighted risk field and the driving information.

5. The control method according to claim 2, characterized in that, The control of the vehicle to travel along the target path includes: Calculate the critical steering angle of the vehicle in real time; If the vehicle's steering angle is less than or equal to the critical steering angle, then the vehicle is controlled to steer according to the steering angle. If the vehicle's steering angle is greater than the critical steering angle, then the vehicle is controlled to steer at the critical steering angle.

6. The control method according to claim 2, characterized in that, The control of the vehicle to travel along the target path includes: The driving state of the vehicle is obtained; wherein the driving state includes the yaw rate, lateral acceleration, wheel speed and body slip angle of the vehicle, and the driving state includes the target driving state and the actual driving state; The corrective sway torque of the vehicle is calculated based on the target driving state and the actual driving state; Based on the corrective yaw moment, grip force is distributed to the wheels of the vehicle; The vehicle is controlled to travel along the target path based on the grip.

7. The control method according to claim 1, characterized in that, The vehicle includes a vision sensor, a first position sensor, and a second position sensor; acquiring the position information of the target obstacle within a preset range of the vehicle includes: Based on the visual sensor, determine whether the target obstacle exists within the preset range; If the target obstacle exists within the preset range, then the first detection result of the first position sensor and the second detection result of the second position sensor are obtained; Based on the first detection result and the second detection result, the location information of the target obstacle is determined.

8. A vehicle control device, characterized in that, include: The first acquisition module is used to acquire the location information of target obstacles within a preset range of the vehicle; wherein, the target obstacles include dynamic obstacles and static obstacles; The first determining module is used to determine the dynamic risk field of the dynamic obstacle and the static risk field of the static obstacle based on the location information; The second acquisition module is used to acquire the traffic rule risk field within the preset range; The second determining module is used to determine the spatiotemporal risk field within the preset range based on the dynamic risk field, the static risk field, and the traffic rule risk field, and to form a spatiotemporal risk field distribution map; The control module is used to control the vehicle to execute the corresponding response strategy based on the risk field distribution map.

9. A vehicle, characterized in that, Includes one or more processors and memory; One or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the method of any one of claims 1-7.

10. A computer-readable storage medium storing processor-executable program code, characterized in that, The computer-readable storage medium includes stored program code, wherein the method of any one of claims 1-7 is executed when the program code is run.

Images