Vehicle control method and device and storage medium

Abstract

The invention discloses a vehicle control method and device and a storage medium, and relates to the technical field of automatic driving, and the vehicle control method comprises the steps that whether target vehicles exist on the two sides of a vehicle or not is determined; if the target vehicles exist on the two sides of the own vehicle, determining an included angle between the own vehicle and the target vehicles based on the current image frame of the own vehicle; if the included angle is greater than a preset angle, updating a frame count value of a frame counter corresponding to the image frame; if the frame count value of the frame counter is greater than a preset value, acquiring relative position information and collision time between the own vehicle and the target vehicle; and determining a speed change strategy of the vehicle based on the relative position information and the collision time, and executing the speed change strategy. The detection accuracy of the lane change intrusion intention of other vehicles in the intersection turning scene is improved, the misjudgment rate of lane change intrusion in the intersection turning scene is reduced, and the safety and efficiency of vehicle driving in the intersection turning scene are improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a vehicle control method, device and storage medium. Background Technology

[0002] In recent years, autonomous driving technology has developed rapidly, gradually moving from the technology verification stage in laboratories to the stage of commercial mass production and implementation. Its functional forms have also been evolving from low-level driving assistance functions such as lane centering assist to mid-to-high-level autonomous driving functions represented by CNOA (City Navigation On Autopilot). Among these, the turning scenario of autonomous vehicles at intersections is a highly unique functional scenario in CNOA. Specifically, intersections often lack lane line references, making it difficult for autonomous vehicles to maintain lane centering and losing important path references. Furthermore, the vehicle's trajectory changes significantly during the turning process, and the driving intentions of adjacent vehicles are difficult to predict. Especially when other vehicles are turning simultaneously, path crossing and intrusion are highly likely to occur.

[0003] In intersection turning scenarios, accurately detecting the lane-changing intrusion intentions of adjacent vehicles and making correct driving decisions based on this is of paramount importance. It directly relates to the safety and smoothness of autonomous vehicles turning at intersections, and is a key link in ensuring the reliable implementation of CNOA (Cross-Operated Autonomous Vehicle) functionality and enhancing user trust.

[0004] Therefore, improving the accuracy of detecting the lane-changing and intrusion intentions of other vehicles in intersection turning scenarios is an urgent problem to be solved.

[0005] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main objective of this application is to provide a vehicle control method, device, and storage medium, which aims to solve the technical problem of how to improve the detection accuracy of other vehicles' lane-changing intrusion intentions in intersection turning scenarios.

[0007] To achieve the above objectives, this application proposes a vehicle control method, the vehicle control method comprising: When the vehicle is detected to be in the intersection area, determine whether there are target vehicles on either side of the vehicle; If there are target vehicles on both sides of the vehicle, the angle between the vehicle and the target vehicle is determined based on the current image frame of the vehicle. If the included angle is greater than the preset angle, then update the frame count value of the frame counter corresponding to the image frame; If the frame count value of the frame counter is greater than the preset value, then the relative position information between the vehicle and the target vehicle and the collision time are obtained. The vehicle's speed change strategy is determined based on the relative position information and the collision time, and the speed change strategy is executed.

[0008] In one embodiment, the step of determining the vehicle's shifting strategy based on the relative position information and the collision time includes: If the target vehicle is determined to be behind the vehicle based on the relative position information, then the speed change strategy is determined to be constant speed driving or acceleration based on the first acceleration.

[0009] In one embodiment, the step of determining the vehicle's shifting strategy based on the relative position information and the collision time further includes: If, based on the relative position information, it is determined that the target vehicle is in front of the vehicle, and the collision time is greater than or equal to the first preset time, then the speed change strategy is determined to be constant speed driving or deceleration based on the second acceleration. If, based on the relative position information, it is determined that the target vehicle is in front of the vehicle, and the collision time is less than a first preset time and greater than or equal to a second preset time, then the speed change strategy is determined to be deceleration based on a third acceleration; or... If the target vehicle is determined to be in front of the vehicle based on the relative position information, and the collision time is less than the second preset time, then the speed change strategy is determined to be an emergency stop. Wherein, the first preset time is greater than the second preset time, and the third acceleration is greater than the second acceleration.

[0010] In one embodiment, the step of obtaining the relative position information between the vehicle and the target vehicle and the collision time if the frame count value is greater than a preset value includes: If the frame count value is greater than the preset value, then the first speed of the vehicle is obtained; The relative position information and the second speed of the target vehicle are determined based on the image frame; The collision time is determined based on the first velocity, the second velocity, and the relative position information.

[0011] In one embodiment, after the step of determining the angle between the vehicle and the target vehicle based on the current image frame of the vehicle, the vehicle control method further includes: If the included angle is less than or equal to a preset angle, then the frame counter is reset.

[0012] In one embodiment, after the step of updating the frame count value of the frame counter corresponding to the image frame, the vehicle control method further includes: If the frame count value of the frame counter is less than or equal to the pre-designed value, then the next image frame corresponding to the current image frame of the vehicle is taken as the current image frame of the vehicle, and the process returns to the step of determining the angle between the vehicle and the target vehicle based on the current image frame of the vehicle.

[0013] In one embodiment, the step of determining whether there are target vehicles on both sides of the vehicle when the vehicle is detected to be in an intersection area includes: When a vehicle is detected to be in an intersection area, a virtual reference line is constructed within the intersection area based on the road information of the intersection area; Based on the current image frame of the vehicle, the virtual reference lines on both sides of the vehicle are dynamically detected to determine whether the target vehicle exists on both sides of the vehicle.

[0014] In one embodiment, the included angle includes a virtual reference line included angle, and the step of determining the included angle between the vehicle and the target vehicle based on the current image frame of the vehicle if there are target vehicles on both sides of the vehicle includes: If there are target vehicles on both sides of the vehicle, the heading vector corresponding to the target vehicle and the direction vector of the virtual reference line where the vehicle is located are obtained based on the image frame. Based on the heading vector and the direction vector, the virtual reference line angle between the vehicle and the target vehicle is determined.

[0015] In addition, to achieve the above objectives, this application also proposes a vehicle control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the aforementioned vehicle control method.

[0016] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the aforementioned vehicle control method.

[0017] One or more technical solutions proposed in this application have at least the following technical effects: When the vehicle is detected to be in an intersection area, it is determined whether there are target vehicles on either side of the vehicle. If target vehicles are present, the angle between the vehicle and the target vehicle is determined based on the current image frame. If the angle is greater than a preset angle, the frame count value of the corresponding frame counter is updated. If the frame count value is greater than a preset value, the relative position information and collision time between the vehicle and the target vehicle are obtained. Finally, the vehicle's speed-changing strategy is determined based on the relative position information and the collision time, and the speed-changing strategy is executed. When the angle between the vehicle and the adjacent target vehicle is greater than a preset angle in multiple consecutive image frames, it is determined that the vehicle intends to change lanes and intrude into the vehicle's turning path. Then, based on the relative position information and collision time, the vehicle is controlled to execute the corresponding speed change strategy. By focusing on the dynamic change characteristics of vehicle heading in intersection turning scenarios, and verifying through multiple consecutive image frames to avoid misjudgments caused by brief changes in vehicle posture, the detection accuracy of other vehicles' lane-changing intrusion intentions in intersection turning scenarios is improved, the false judgment rate of lane-changing intrusion in intersection turning scenarios is reduced, and the safety and efficiency of vehicle driving in intersection turning scenarios are improved. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the vehicle control method of this application. Figure 2 This is a schematic diagram of a scenario according to an embodiment of the vehicle control method of this application; Figure 3 This is a schematic diagram of another embodiment of the vehicle control method of this application; Figure 4 This is a schematic diagram of the module structure of a vehicle control method according to an embodiment of the present application, where the target vehicle is located behind the vehicle. Figure 5 This is a schematic diagram of the module structure of the vehicle control method of this application, showing the target vehicle located in front of the vehicle. Figure 6 This is a schematic diagram of the module structure of the target vehicle located in front of the vehicle, according to another embodiment of the vehicle control method of this application; Figure 7This is a schematic diagram of the module structure of the target vehicle located in front of the vehicle in another embodiment of the vehicle control method of this application; Figure 8 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the vehicle control method in the embodiments of this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] The main solution of this application embodiment is as follows: when the vehicle is detected to be in an intersection area, it is determined whether there are target vehicles on both sides of the vehicle; if there are target vehicles on both sides of the vehicle, the angle between the vehicle and the target vehicle is determined based on the current image frame of the vehicle; if the angle is greater than a preset angle, the frame count value of the frame counter corresponding to the image frame is updated; if the frame count value of the frame counter is greater than a preset value, the relative position information and collision time between the vehicle and the target vehicle are obtained; the vehicle's speed change strategy is determined based on the relative position information and the collision time, and the speed change strategy is executed.

[0025] In this embodiment, for ease of description, the vehicle control device will be used as the execution subject in the following description.

[0026] In recent years, autonomous driving technology has developed rapidly, gradually moving from the technology verification stage in laboratories to the stage of commercial mass production and implementation. Its functional forms have also been evolving from low-level driving assistance functions such as lane centering assist to mid-to-high-level autonomous driving functions represented by CNOA (City Navigation On Autopilot). Among these, the turning scenario of autonomous vehicles at intersections is a highly unique functional scenario in CNOA. Specifically, intersections often lack lane line references, making it difficult for autonomous vehicles to maintain lane centering and losing important path references. Furthermore, the vehicle's trajectory changes significantly during the turning process, and the driving intentions of adjacent vehicles are difficult to predict. Especially when other vehicles are turning simultaneously, path crossing and intrusion are highly likely to occur.

[0027] In intersection turning scenarios, accurately detecting the lane-changing intrusion intentions of adjacent vehicles and making correct driving decisions based on this is of paramount importance. It directly relates to the safety and smoothness of autonomous vehicles turning at intersections, and is a key link in ensuring the reliable implementation of CNOA (Cross-Operated Autonomous Vehicle) functionality and enhancing user trust.

[0028] Among related technologies, autonomous driving decision-making in intersection turning scenarios includes reusing straight-line solutions, master-slave solutions, and distance-based direct avoidance solutions.

[0029] The straight-line reuse solution directly applies the lane-change intention detection and decision-making logic from the straight-line scenario to the intersection turning scenario. Specifically, it determines whether an adjacent vehicle intends to change lanes by detecting indicators such as the degree to which it deviates from its virtual reference line, its heading angle, or whether it crosses the virtual lane line. If a lane-change intention is determined, a decision to slow down and avoid the vehicle is made based on the predicted trajectory of that vehicle. However, due to the lack of lane lines at intersections and the presence of turning operations and irregular geometric shapes, vehicles are prone to briefly deviating from the virtual reference line, changing their heading angle, or crossing the virtual lane line when turning at intersections. The straight-line reuse solution does not adapt to the special characteristics of intersections lacking lane lines, and the large changes in vehicle turning trajectories and irregular geometric shapes. If the logic of determining lane-change intention by detecting the degree to which a vehicle deviates from the virtual reference line, its heading angle, or whether it crosses the lane line is directly reused in the straight-line scenario, the misjudgment rate of lane-change intrusion intentions will be significantly increased, which will seriously affect the accuracy and timeliness of subsequent decisions and fail to meet the safety decision-making requirements of autonomous vehicles when turning at intersections.

[0030] In the master-slave approach, the trajectories of other vehicles in the vicinity are first predicted. Then, based on the prediction results, the free space of the vehicle is defined, and finally, a driving path is planned for the vehicle within this free space. This simplifies the interaction between the vehicle and surrounding vehicles into a "master-slave" relationship, unilaterally predicting the trajectories of surrounding vehicles and defining the free space to plan the path. It ignores the complex dynamic game and interaction characteristics between vehicles in real driving scenarios. In the intersection turning scenario, the driving decisions of vehicles are mutually influential, and one party does not completely wait for the other party to make a decision before acting. This results in insufficient rationality and real-time performance of the decisions, making it unable to cope with the complex dynamic interaction of vehicles in intersections.

[0031] In the distance-based direct avoidance scheme, the vehicle maintains normal driving status and decides whether to slow down or take emergency braking action to avoid the obstacle solely based on the distance between itself and the adjacent vehicle.

[0032] Deciding whether to slow down or brake suddenly based solely on the distance between the vehicle next to it, without tracking or predicting the movement and driving intentions of the vehicle next to it, and without considering the relative position of the two vehicles to determine right-of-way, can easily lead to giving way too early or too late. It also fails to reasonably distinguish right-of-way priorities in different scenarios, affecting driving safety and efficiency.

[0033] Therefore, improving the accuracy of detecting the lane-changing and intrusion intentions of other vehicles in intersection turning scenarios is an urgent problem to be solved.

[0034] This application provides a solution that determines a vehicle's intention to change lanes and intrude into the vehicle's turning path when the angle between the vehicle and the adjacent target vehicle is greater than a preset angle in multiple consecutive image frames. Then, based on relative position information and collision time, the solution controls the vehicle to execute a corresponding speed-changing strategy. By focusing on the dynamic changes in vehicle heading in intersection turning scenarios and verifying with multiple consecutive image frames, this solution avoids misjudgments caused by brief changes in vehicle posture. This improves the accuracy of detecting other vehicles' intention to change lanes and intrude in intersection turning scenarios, reduces the false judgment rate of lane change intrusion in intersection turning scenarios, and enhances the safety and efficiency of vehicle driving in intersection turning scenarios.

[0035] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or vehicle control device capable of performing the above functions. The following description uses a vehicle control device as an example to illustrate this embodiment and the subsequent embodiments.

[0036] Based on this, embodiments of this application provide a vehicle control method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the vehicle control method of this application.

[0037] In this embodiment, the vehicle control method includes steps S110~S150: Step S110: When the vehicle is detected to be in the intersection area, determine whether there are target vehicles on both sides of the vehicle; In this embodiment, a high-definition map can be used to detect in real time whether the vehicle is in an intersection area. For example, the vehicle's GPS data can be acquired in real time, and the vehicle's entry into an intersection area can be determined based on the GPS data and the high-definition map. At the same time, the vehicle's operation data can be used to determine whether the vehicle is turning in the intersection area. For example, the vehicle's navigation data can be used to determine whether the vehicle is turning in the intersection area. If the vehicle is detected to be in an intersection area and turning in the intersection area, it can be determined whether there are target vehicles on both sides of the vehicle, that is, whether there are target vehicles turning in the same direction as the vehicle next to the vehicle.

[0038] Furthermore, in one feasible implementation, step S110 may include steps A110~A120: Step A110: When the vehicle is detected to be in an intersection area, a virtual reference line is constructed in the intersection area based on the road information of the intersection area; Step A120: Dynamically detect the virtual reference lines on both sides of the vehicle based on the current image frame of the vehicle to determine whether the target vehicle exists on both sides of the vehicle.

[0039] In this embodiment, when the vehicle turns at an intersection, road information of the intersection area is acquired, and a virtual reference line is constructed within the intersection area based on the road information. This virtual reference line includes the vehicle's turning route and reference turning routes corresponding to the roads on either side of the vehicle. Figure 2 As shown, Figure 2 In the intersection area, the solid line box represents the vehicle and the dashed line box represents the target vehicle. Both the vehicle and the target vehicle need to make a left turn in this intersection area. A virtual lane line can be constructed by using the road information of the road where the vehicle is currently located (including the road information of the vehicle and the road information of the road next to the vehicle) and the road information of the target road after the turn. The virtual lane line includes the reference turning route of the vehicle and the reference turning route of the target vehicle.

[0040] When the virtual reference line is constructed, the current image frame of the vehicle is acquired. Based on the current image frame, the virtual reference lines on both sides of the vehicle are dynamically detected to detect whether there is a target vehicle on the virtual reference lines on both sides of the vehicle, that is, to determine whether there is a target vehicle turning in the same direction as the vehicle on both sides of the vehicle.

[0041] It should be noted that if there are no target vehicles on either side of the vehicle, the current image frame of the vehicle is acquired in real time before the vehicle completes the turn, and the target vehicle is detected.

[0042] Step S120: If there are target vehicles on both sides of the vehicle, determine the angle between the vehicle and the target vehicle based on the current image frame of the vehicle. In this embodiment, if there are target vehicles on both sides of the vehicle, the angle between the vehicle and the target vehicle is obtained according to the current image frame. Specifically, the direction vector of the virtual reference line of the vehicle is obtained. This direction vector can be the direction vector corresponding to the current position of the vehicle on its virtual reference line. The heading vector of the target vehicle is also obtained. Specifically, this heading vector can be obtained through the current image frame. The angle between the vehicle and the target vehicle is calculated based on the heading vector and the direction vector.

[0043] Furthermore, in one feasible implementation, the included angle includes the included angle of a virtual reference line, and step S120 may include steps B110~B120: Step B110: If there are target vehicles on both sides of the vehicle, then obtain the heading vector corresponding to the target vehicle and the direction vector of the virtual reference line where the vehicle is located based on the image frame. Step B120: Based on the heading vector and the direction vector, determine the virtual reference line angle between the vehicle and the target vehicle.

[0044] In this embodiment, if there are target vehicles on both sides of the vehicle, the heading vector corresponding to the target vehicle is obtained based on the image frame. Specifically, the heading of the target vehicle is identified through the image frame, and then the heading vector of the target vehicle is determined.

[0045] After obtaining the heading vector and direction vector, the virtual reference line angle between the vehicle and the target vehicle is determined based on the heading vector and the direction vector. The formula for the virtual reference line angle can be expressed as: ; in, Angle between virtual reference lines The heading vector, It is the direction vector.

[0046] Step S130: If the included angle is greater than the preset angle, then update the frame count value of the frame counter corresponding to the image frame; When the angle between the vehicle and the target vehicle is obtained, it is determined whether the angle is greater than the preset angle. If the angle is greater than the preset angle, the frame count value of the corresponding frame counter of the image frame is updated, that is, the frame count value is increased by 1 to obtain the updated frame count value of the frame counter. The preset angle can be set reasonably.

[0047] It should be noted that in the intersection turning scenario, when a target vehicle is detected, the vehicle's frame counter is initialized. This frame counter is used to count the number of consecutive frames where the "angle is greater than the threshold". During initialization, the frame count value K can be set to an initial value, such as 0.

[0048] Furthermore, in one feasible implementation, after step S120, the vehicle control method further includes: Step S160: If the included angle is less than or equal to a preset angle, then reset the frame counter.

[0049] In this embodiment, if the included angle is less than or equal to a preset angle, it is determined that the target vehicle has no intention of changing lanes or intruding. Figure 3As shown, the frame counter is reset at this time. Specifically, when the frame count value of the frame counter is not the initial value, the frame counter is reset to reset its frame count value to the initial value, such as 0.

[0050] Furthermore, in one feasible implementation, after step S130, the vehicle control method further includes: Step S170: If the frame count value of the frame counter is less than or equal to the pre-designed value, then the next image frame corresponding to the current image frame of the vehicle is taken as the current image frame of the vehicle, and the process returns to the step of determining the angle between the vehicle and the target vehicle based on the current image frame of the vehicle.

[0051] In this embodiment, if the frame count value of the frame counter is less than or equal to the preset value, the vehicle continues to count the frame count value based on the next image frame. Specifically, the next image frame corresponding to the current image frame of the vehicle is taken as the current image frame of the vehicle, and the execution step S120 is returned to accumulate the number of consecutive image frames with an angle greater than the preset angle between the vehicle and the target vehicle. The preset value can be reasonably set.

[0052] Step S140: If the frame count value of the frame counter is greater than the preset value, then obtain the relative position information and collision time between the vehicle and the target vehicle. In this embodiment, if the frame count value of the frame counter is greater than the pre-designed value, it is determined that the target vehicle has the intention to change lanes and intrude. At this time, the relative position information between the vehicle and the target vehicle and the collision time are obtained. Specifically, the relative position information between the vehicle and the target vehicle can be analyzed based on the Frenet coordinate system. The relative position information can be the longitudinal relative position relationship between the vehicle and the target vehicle. At the same time, the speeds of the vehicle and the target vehicle are obtained. The collision time is determined based on the relative position information and the speeds of the vehicle and the target vehicle.

[0053] Furthermore, in one feasible implementation, step S140 may include steps C110~C130: Step C110: If the frame count value is greater than the preset value, then obtain the first speed of the vehicle; Step C120: Determine the relative position information and the second speed of the target vehicle based on the image frame; Step C130: Determine the collision time based on the first velocity, the second velocity, and the relative position information.

[0054] In this embodiment, if the frame count value is greater than the preset value, the current first speed of the vehicle is obtained, the positions of the vehicle and the target vehicle are identified based on the image frames, the positions of the vehicle and the target vehicle are projected onto Frenet coordinates, and the relative position information between the vehicle and the target vehicle, such as the longitudinal relative position, is analyzed based on the Frenet coordinate system. At the same time, the second speed of the target vehicle is identified through multiple image frames corresponding to the frame count value. For example, the second speed is calculated based on the time interval between adjacent image frames and the position change of the target vehicle in adjacent image frames.

[0055] After obtaining the second speed, the collision time is determined based on the first speed, the second speed, and the relative position information. For example, the first longitudinal speed in the first speed and the second longitudinal speed in the second speed can be obtained. The longitudinal distance between the vehicle and the target vehicle is analyzed by the relative position information. The TTC (Time To Collision) is calculated based on the longitudinal distance, the first longitudinal speed, and the second longitudinal speed.

[0056] Step S150: Determine the vehicle's speed change strategy based on the relative position information and the collision time, and execute the speed change strategy.

[0057] In this embodiment, when relative position information and collision time are obtained, the vehicle's speed change strategy is determined based on the relative position information and the collision time, and the speed change strategy is executed to avoid collision between the vehicle and the target vehicle.

[0058] Furthermore, in one feasible implementation, step S150 may include step D110: Step D110: If it is determined that the target vehicle is behind the vehicle based on the relative position information, then the speed change strategy is determined to be constant speed driving or acceleration driving based on the first acceleration.

[0059] Furthermore, in one feasible implementation, step S150 may include steps D110~D140: Step D120: If it is determined based on the relative position information that the target vehicle is in front of the vehicle and the collision time is greater than or equal to the first preset time, then the speed change strategy is determined to be constant speed driving or deceleration based on the second acceleration. Step D130: If, based on the relative position information, it is determined that the target vehicle is in front of the vehicle, and the collision time is less than a first preset time and greater than or equal to a second preset time, then the speed change strategy is determined to be deceleration based on a third acceleration; or... Step D140: If it is determined based on the relative position information that the target vehicle is in front of the vehicle and the collision time is less than the second preset time, then the speed change strategy is determined to be an emergency stop. Wherein, the first preset time is greater than the second preset time, and the third acceleration is greater than the second acceleration.

[0060] In this embodiment, the relative position information is used to determine whether the target vehicle is in front of or behind the vehicle. If the target vehicle is behind the vehicle, then... Figure 4 As shown, at this time, the vehicle has the right-of-way and can turn at a constant speed or with a slight acceleration. That is, the speed change strategy is to drive at a constant speed or accelerate based on the first acceleration in order to avoid collision with the target vehicle.

[0061] If the target vehicle is determined to be in front of the vehicular vehicle based on the relative position information, then the range of the collision time is determined. If the collision time is greater than or equal to a first preset time, then... Figure 5 As shown, the speed change strategy is determined to be constant speed driving or deceleration based on the second acceleration. That is, when the distance between the vehicle and the target vehicle is far, the vehicle drives at a constant speed or decelerates slightly based on the second acceleration to avoid collision with the target vehicle.

[0062] If the collision time is less than the first preset time and greater than or equal to the second preset time, then the speed change strategy is determined to be deceleration based on the third acceleration. Figure 6 As shown, when the distance between the vehicle and the target vehicle is close, the vehicle decelerates significantly according to the third acceleration to avoid a collision.

[0063] If, based on relative position information, it is determined that the target vehicle is in front of the vehicle and the collision time is less than a second preset time, then the transmission strategy is determined to be emergency braking. Figure 7 As shown, when the distance between the vehicle and the target vehicle is close (e.g., a collision is imminent), the vehicle stops urgently to avoid a collision.

[0064] In this embodiment, the heading angle of the adjacent vehicle (target vehicle) is monitored continuously for multiple frames and compared with the angle between the target vehicle and the virtual reference line of the vehicle itself. If the angle is continuously greater than a set threshold, it is determined that the adjacent vehicle intends to change lanes and intrude into the turning path of the vehicle. This focuses on the dynamic changes in vehicle heading in the intersection turning scenario, and uses continuous multi-frame verification to avoid misjudgments caused by brief changes in vehicle attitude. Compared with the straight road reuse solution, this application fully considers the special characteristics of intersections without lane lines and large changes in vehicle turning trajectories. By continuously monitoring the heading angle for multiple frames, it accurately identifies lane-changing intrusion intentions and reduces the misjudgment rate. Furthermore, by verifying whether the angle between the adjacent vehicle's heading angle and the vehicle's virtual reference line continuously exceeds the limit through multi-frame data verification, interference from non-intrusion scenarios such as brief vehicle deviations and temporary heading fluctuations during intersection turns is effectively filtered out. This makes the judgment of lane-changing intrusion intentions more consistent with the actual characteristics of the intersection scenario, reducing the risk of misjudgment from the root of the judgment logic.

[0065] In this embodiment, after confirming that the adjacent vehicle intends to change lanes and intrude, the longitudinal relative positional relationship and speed information of the two vehicles are analyzed based on the Frenet (SL) coordinate system to calculate the collision time. Based on the longitudinal relative position and different TTC intervals, the decision is divided into multiple levels, adopting different driving strategies such as constant speed / small acceleration, small deceleration, large deceleration, and emergency braking. Compared with the master-slave scheme and the distance-based direct avoidance scheme, this application clarifies the relative positional relationship of the two vehicles through the Frenet coordinate system, quantifies the time dimension of collision risk by combining TTC, and considers right-of-way (e.g., the vehicle has right-of-way when the other vehicle is behind it), making the decision dynamic, interactive, and accurate. This avoids the decision-making defects of the master-slave scheme and solves the problems of inappropriate timing and unclear right-of-way when based solely on distance. Through the "right-of-way judgment + risk classification" design, it realizes the interactive logic of "mutual consideration and dynamic adjustment" with actual driving.

[0066] Meanwhile, this application constructs an integrated logical architecture of "lane change intrusion intent recognition - hierarchical decision-making based on Frenet and TTC", which directly uses the result of intent recognition as the input condition for hierarchical decision-making, forming a complete closed loop from perception judgment to action decision-making. The architecture has a clear process and close connection between each link, which can quickly respond to changes in vehicle interaction in intersection turning scenarios, ensuring consistency from detecting the intrusion intent of the adjacent vehicle to taking corresponding decision actions, improving the timeliness and rationality of autonomous vehicles' decision-making when turning at intersections, and ensuring driving safety and smoothness.

[0067] Compared to distance-based direct avoidance solutions that rely solely on distance for decision-making, this application constructs a multi-dimensional decision-making system encompassing "intent recognition, relative position, right-of-way determination, and risk quantification." Intent recognition filters out targets that pose a genuine risk. Then, based on the SL coordinate system, right-of-way is clearly defined (e.g., if the other vehicle is behind, the vehicle has the right-of-way). Finally, TTC (Traffic Troubleshooting) is used to quantify collision risk, achieving a tiered decision-making process of "uniform acceleration, slight deceleration, significant deceleration, and emergency braking." This avoids the decision-making lag of "avoiding only when the distance is too close" and prevents the efficiency loss of "blindly decelerating without clearly defining right-of-way." While ensuring the safety of the autonomous driving system, it also considers the fairness of right-of-way and the smoothness of traffic flow.

[0068] The integrated architecture of "intent recognition-hierarchical decision-making" in this application has a clear process: intent recognition continuously monitors heading angle data, and hierarchical decision-making relies on the relative position calculation of the SL coordinate system and the basic speed-distance calculation of TTC. Both are linear complexity operations, which do not require complex trajectory prediction models or a large amount of behavior sampling. This reduces the computing power requirements of the vehicle computing platform and can meet the real-time decision-making requirements of intersection turning scenarios. At the same time, the simple logic link reduces the difficulty of algorithm debugging and engineering deployment, making it more conducive to application in commercial mass-produced vehicles.

[0069] This embodiment provides a vehicle control method. When a vehicle is detected in an intersection area, it determines whether there are target vehicles on either side of the vehicle. If target vehicles are present, the angle between the vehicle and the target vehicles is determined based on the current image frame. If the angle is greater than a preset angle, the frame count value of the corresponding frame counter is updated. If the frame count value is greater than a pre-designed value, the relative position information and collision time between the vehicle and the target vehicles are obtained. Finally, based on the relative position information and the collision time, the vehicle's speed control strategy is determined and executed. The proposed speed-changing strategy determines that a vehicle intends to change lanes and intrude into the turning path of the vehicle if the angle between the vehicle and the adjacent target vehicle is greater than a preset angle in multiple consecutive image frames. Then, based on the relative position information and collision time, the system controls the vehicle to execute the corresponding speed-changing strategy. By focusing on the dynamic changes in vehicle heading in intersection turning scenarios and verifying with multiple consecutive image frames to avoid misjudgments caused by brief changes in vehicle posture, the system improves the accuracy of detecting the lane-changing intrusion intentions of other vehicles in intersection turning scenarios, reduces the false judgment rate of lane-changing intrusion in intersection turning scenarios, and improves the safety and efficiency of vehicle driving in intersection turning scenarios.

[0070] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the vehicle control method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0071] This application provides a vehicle control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the vehicle control method in Embodiment 1 above.

[0072] The following is for reference. Figure 8 The diagram illustrates a structural schematic suitable for implementing vehicle control devices according to embodiments of this application. Vehicle control devices in embodiments of this application may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8The vehicle control device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0073] like Figure 8 As shown, the vehicle control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the vehicle control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the vehicle control unit to communicate wirelessly or wiredly with other devices to exchange data. Although the figures show vehicle control units with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0074] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0075] The vehicle control device provided in this application, employing the vehicle control method described in the above embodiments, can solve the technical problem of how to improve the detection accuracy of other vehicles' lane-changing and intrusion intentions in intersection turning scenarios. Compared with the prior art, the beneficial effects of the vehicle control device provided in this application are the same as those of the vehicle control method provided in the above embodiments, and other technical features in this vehicle control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0076] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0077] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0078] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the vehicle control method in the above embodiments.

[0079] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0080] The aforementioned computer-readable storage medium may be included in the vehicle control device; or it may exist independently and not be assembled into the vehicle control device.

[0081] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a vehicle control device, the vehicle control device: when it detects that the vehicle is in an intersection area, determines whether there are target vehicles on either side of the vehicle; if there are target vehicles on either side of the vehicle, it determines the angle between the vehicle and the target vehicle based on the current image frame of the vehicle; if the angle is greater than a preset angle, it updates the frame count value of the frame counter corresponding to the image frame; if the frame count value of the frame counter is greater than a preset value, it acquires the relative position information and collision time between the vehicle and the target vehicle; and determines the vehicle's speed-changing strategy based on the relative position information and the collision time, and executes the speed-changing strategy.

[0082] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0083] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0084] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0085] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described vehicle control method, which can solve the technical problem of how to improve the detection accuracy of other vehicles' lane-changing intrusion intentions in intersection turning scenarios. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the vehicle control method provided in the above embodiments, and will not be repeated here.

[0086] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle control method described above.

[0087] The computer program product provided in this application solves the technical problem of how to improve the detection accuracy of lane-changing intrusion intentions of other vehicles in intersection turning scenarios. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the vehicle control method provided in the above embodiments, and will not be repeated here.

[0088] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A vehicle control method, characterized in that, The vehicle control method includes: When the vehicle is detected to be in the intersection area, determine whether there are target vehicles on either side of the vehicle; If there are target vehicles on both sides of the vehicle, the angle between the vehicle and the target vehicle is determined based on the current image frame of the vehicle. If the included angle is greater than the preset angle, then update the frame count value of the frame counter corresponding to the image frame; If the frame count value of the frame counter is greater than the preset value, then the relative position information between the vehicle and the target vehicle and the collision time are obtained. The vehicle's speed change strategy is determined based on the relative position information and the collision time, and the speed change strategy is executed.

2. The vehicle control method as described in claim 1, characterized in that, The step of determining the vehicle's shifting strategy based on the relative position information and the collision time includes: If the target vehicle is determined to be behind the vehicle based on the relative position information, then the speed change strategy is determined to be constant speed driving or acceleration based on the first acceleration.

3. The vehicle control method as described in claim 2, characterized in that, The step of determining the vehicle's shifting strategy based on the relative position information and the collision time further includes: If, based on the relative position information, it is determined that the target vehicle is in front of the vehicle, and the collision time is greater than or equal to the first preset time, then the speed change strategy is determined to be constant speed driving or deceleration based on the second acceleration. If, based on the relative position information, it is determined that the target vehicle is in front of the vehicle, and the collision time is less than a first preset time and greater than or equal to a second preset time, then the speed change strategy is determined to be deceleration based on a third acceleration; or... If the target vehicle is determined to be in front of the vehicle based on the relative position information, and the collision time is less than the second preset time, then the speed change strategy is determined to be an emergency stop. Wherein, the first preset time is greater than the second preset time, and the third acceleration is greater than the second acceleration.

4. The vehicle control method as described in claim 1, characterized in that, The step of obtaining the relative position information between the vehicle and the target vehicle and the collision time if the frame count value is greater than the preset value includes: If the frame count value is greater than the preset value, then the first speed of the vehicle is obtained; The relative position information and the second speed of the target vehicle are determined based on the image frame; The collision time is determined based on the first velocity, the second velocity, and the relative position information.

5. The vehicle control method as described in claim 1, characterized in that, After the step of determining the angle between the vehicle and the target vehicle based on the current image frame of the vehicle, the vehicle control method further includes: If the included angle is less than or equal to a preset angle, then the frame counter is reset.

6. The vehicle control method according to any one of claims 1 to 5, characterized in that, After the step of updating the frame count value of the frame counter corresponding to the image frame, the vehicle control method further includes: If the frame count value of the frame counter is less than or equal to the pre-designed value, then the next image frame corresponding to the current image frame of the vehicle is taken as the current image frame of the vehicle, and the process returns to the step of determining the angle between the vehicle and the target vehicle based on the current image frame of the vehicle.

7. The vehicle control method according to any one of claims 1 to 5, characterized in that, When the vehicle is detected to be in the intersection area, the step of determining whether there are target vehicles on both sides of the vehicle includes: When a vehicle is detected to be in an intersection area, a virtual reference line is constructed within the intersection area based on the road information of the intersection area; Based on the current image frame of the vehicle, the virtual reference lines on both sides of the vehicle are dynamically detected to determine whether the target vehicle exists on both sides of the vehicle.

8. The vehicle control method as described in claim 7, characterized in that, The included angle includes the virtual reference line angle. The step of determining the included angle between the vehicle and the target vehicle based on the current image frame of the vehicle if there are target vehicles on both sides of the vehicle includes: If there are target vehicles on both sides of the vehicle, the heading vector corresponding to the target vehicle and the direction vector of the virtual reference line where the vehicle is located are obtained based on the image frame. Based on the heading vector and the direction vector, the virtual reference line angle between the vehicle and the target vehicle is determined.

9. A vehicle control device, characterized in that, The vehicle control device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle control method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the vehicle control method as described in any one of claims 1 to 8.

Images