Method, device and equipment for determining safe driving area of automatic driving vehicle and medium

By establishing a constrained potential field model and utilizing autonomous driving perception fusion information and vehicle motion information, a safe driving area is determined, which solves the problem of insufficient safety of traditional autonomous driving solutions in complex environments and improves the safety performance of autonomous vehicles.

CN118991824APending Publication Date: 2024-11-22CHINA FAW CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411228372.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Traditional autonomous driving solutions cannot effectively determine safe driving areas in complex driving environments, resulting in insufficient safety during the autonomous driving process.

Method used

By acquiring autonomous driving perception fusion information and vehicle motion information, a constrained potential field model is established, and safe driving areas are determined by using target modeling objects such as lane center lines, lane boundary lines, and driving obstacles.

Benefits of technology

It improves the safety performance of autonomous vehicles in complex environments, ensuring that vehicles can adjust their driving path and speed in real time within a safe driving area.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118991824A_ABST
    Figure CN118991824A_ABST
Patent Text Reader

Abstract

The invention discloses a method, a device, equipment and a medium for determining a safe driving area of an automatic driving vehicle, and the method comprises the steps: obtaining automatic driving perception fusion information and vehicle motion information corresponding to a target vehicle, and determining a target modeling object according to the automatic driving perception fusion information, establishing a constraint potential field model corresponding to the target modeling object based on the automatic driving perception fusion information and the vehicle motion information; and determining a target constraint potential field model corresponding to the target vehicle based on the constraint potential field model, and determining a safe driving area according to the target constraint potential field model. Based on the technical scheme, the constraint potential field model in the automatic driving process is established by integrating the automatic driving perception fusion information and the vehicle motion information, and then the safe driving area is determined according to the constraint potential field model, so that the safety performance of the vehicle in the automatic driving process is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a method, device, equipment and medium for determining a safe driving area for an autonomous driving vehicle. Background Art

[0002] With the continuous development of automobile technology, in order to ensure the safety of vehicles during driving, various sensors are often installed on vehicles to collect vehicle parameters, and the vehicle is controlled to drive automatically according to the collected sensor parameters.

[0003] However, when faced with a more complex driving environment, traditional autonomous driving solutions cannot determine a safe vehicle driving area based solely on the collected sensor information, and thus cannot guarantee safety during the autonomous driving process. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for determining a safe driving area of ​​an autonomous driving vehicle, so as to improve the safety performance of the autonomous driving vehicle in a complex driving environment, and to solve the technical problem that the autonomous driving vehicle in the existing solution lacks a modeling method for the complex and changing driving environment around the vehicle.

[0005] According to one aspect of the present invention, a method for determining a safe driving area of ​​an autonomous driving vehicle is provided, comprising:

[0006] Acquire autonomous driving perception fusion information and vehicle motion information corresponding to the target vehicle, and determine a target modeling object according to the autonomous driving perception fusion information, wherein the target modeling object includes at least one of a lane centerline, a lane boundary line, and a driving obstacle;

[0007] Establishing a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information;

[0008] A target constraint potential field model corresponding to the target vehicle is determined based on the constraint potential field model, and a safe driving area is determined according to the target constraint potential field model.

[0009] According to another aspect of the present invention, a device for determining a safe driving area of ​​an autonomous driving vehicle is provided, comprising:

[0010] an object determination module, configured to obtain autonomous driving perception fusion information and vehicle motion information corresponding to a target vehicle, and determine a target modeling object according to the autonomous driving perception fusion information, wherein the target modeling object includes at least one of a lane centerline, a lane boundary line, and a driving obstacle;

[0011] A local model determination module, used to establish a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information;

[0012] The safety area determination module is used to determine a target constraint potential field model corresponding to a target vehicle based on the constraint potential field model, and determine a safe driving area according to the target constraint potential field model.

[0013] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining the safe driving area of ​​an autonomous driving vehicle described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a safe driving area for an autonomous driving vehicle described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains the autonomous driving perception fusion information and vehicle motion information corresponding to the target vehicle, and determines the target modeling object based on the autonomous driving perception fusion information, and then establishes a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information, and finally determines the target constraint potential field model corresponding to the target vehicle based on the constraint potential field model, and determines the safe driving area based on the target constraint potential field model. Based on the above technical solution, the constraint potential field model in the autonomous driving process is established by integrating the autonomous driving perception fusion information and the vehicle motion information, and then the safe driving area is determined based on the constraint potential field model, thereby improving the safety performance of the vehicle in the autonomous driving process.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of a method for determining a safe driving area for an autonomous driving vehicle provided by an embodiment of the present invention;

[0022] Figure 2 This is a rendering of a target constraint potential field model in a lane-changing scenario of two lanes in the same direction provided by an embodiment of the present invention;

[0023] Figure 3 is a flow chart of a method for determining a safe driving area for an autonomous driving vehicle provided by an embodiment of the present invention;

[0024] Figure 4 is a structural block diagram of a device for determining a safe driving area for an autonomous driving vehicle provided by an embodiment of the present invention;

[0025] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1 This is a flow chart of a method for determining a safe driving area for an autonomous driving vehicle provided by an embodiment of the present invention. This embodiment can be applied to establishing constraints corresponding to a target vehicle according to autonomous driving perception fusion information and vehicle motion information during autonomous driving.

[0030] In the case of a vehicle that is not in a safe driving area, the method may be performed by a device for determining a safe driving area for an autonomous driving vehicle, which may be implemented in the form of hardware and / or software, and may be configured in an electronic device, which may be a vehicle-mounted central controller, etc. Figure 1 As shown, the method includes:

[0031] S110. Obtain autonomous driving perception fusion information and vehicle motion information corresponding to the target vehicle, and determine a target modeling object based on the autonomous driving perception fusion information.

[0032] Among them, the target vehicle may be a vehicle that is starting the autonomous driving function. Autonomous driving perception fusion information may be understood as information collected by a driving assistance system installed in the vehicle for controlling the assisted autonomous driving function, such as sensor information collected by cameras, millimeter wave radars, lidars, etc. installed in the vehicle, and a pre-established high-precision map. Vehicle motion information may be driving data generated by the target vehicle during driving, such as driving speed, driving direction, heading angle, and other information. The target modeling object may be understood as a reference object in the process of building a model, and the target modeling object includes at least one of a lane centerline, a lane boundary line, and a driving obstacle.

[0033] Specifically, the autonomous driving perception fusion information and vehicle motion information corresponding to the target vehicle are obtained, and the target modeling object is determined based on the autonomous driving perception fusion information. For example, sensor information corresponding to the target vehicle may be collected to obtain environmental data around the vehicle, and the real-time position, speed, acceleration, heading and other motion information of the vehicle may be obtained based on the on-board sensors. Then, the modeling object may be determined based on the collected information, such as any one of the lane center line, lane boundary line and driving obstacle.

[0034] S120. Establishing a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information.

[0035] The constraint potential field model may be an artificial potential field model corresponding to the target vehicle and established according to preset constraint conditions.

[0036] Specifically, in the spatial model of the autonomous driving system, a potential field is defined for each target modeling object, and then the impact of the modeling object on the vehicle's driving space is represented according to the potential field. Areas with high potential field values ​​represent areas that need to be avoided, and areas with low potential field values ​​represent drivable or safe areas. For example, for the center line of the lane, a gravitational potential field is defined to guide the vehicle to drive along the center line. For the lane boundary line and driving obstacles, a repulsive potential field is defined to prevent the vehicle from approaching or entering these areas. It should be noted that the strength and range of the potential field can be adjusted according to factors such as the size, speed, and distance of the object.

[0037] On the basis of the above technical solution, the constraint potential field model corresponding to the target modeling object is established based on the autonomous driving perception fusion information and the vehicle motion information, including: when the target modeling object is the lane centerline, determining the lane width corresponding to the lane centerline, and determining the potential field convergence coefficient of the lane centerline according to the lane width; determining the constraint potential field model corresponding to the lane centerline based on the potential field convergence coefficient of the lane centerline, the autonomous driving perception fusion information, the vehicle motion information and the lane centerline constraint potential field function.

[0038] The lane width can be understood as the width information of the road the vehicle is currently traveling on, and can be, for example, the width value of a lane. The potential field convergence coefficient can be used to describe the speed or trend of the potential field value changing with the spatial position.

[0039] Specifically, when the target modeling object is the lane centerline, determine the lane width corresponding to the lane centerline, and determine the corresponding potential field convergence coefficient based on the lane width, and then bring the potential field convergence coefficient and the autonomous driving perception fusion information into the lane centerline constraint potential field function to determine the constraint potential field model corresponding to the lane centerline. For example, taking the lane centerline potential field model as an example, assuming that a Gaussian-like function is used for modeling, the potential field convergence coefficient σcen is proportional to the lane width. Given a lane width, such as Wl=3.75m and other parameters, such as Acen=-15), the distribution characteristics of the potential field value within the lane can be changed by adjusting the potential field convergence coefficient. The lane centerline constraint potential field function is: Among them, the U cen is the potential field value of the lane centerline constraint; cen is the minimum value of the lane centerline constraint potential field; cen,i is the lateral coordinate value of the centerline of the i-th lane; i is the number of lane centerlines; σ cen is the potential field convergence coefficient of the lane centerline; boun,iis the lateral position of the i-th lane boundary line. It should be noted that according to conventional driving habits and considerations of driving safety, vehicles usually drive along the center line of the lane to ensure a safe distance from other vehicles, and the potential field value at the center line of the lane is the smallest. In this lane, as the distance from the center line increases, the potential field value gradually increases.

[0040] On the basis of the above technical solution, the constraint potential field model corresponding to the target modeling object is established based on the autonomous driving perception fusion information and the vehicle motion information, including: when the target modeling object is a lane boundary line, determining the potential field convergence coefficient of the lane boundary line; determining the constraint potential field model corresponding to the lane boundary line based on the potential field convergence coefficient of the lane boundary line, the autonomous driving perception fusion information, the vehicle motion information and the lane boundary line constraint potential field function.

[0041] Specifically, in structured roads, boundary lines are used to limit the range of motion of vehicles. For driving safety reasons, boundary lines cannot be crossed. Therefore, in the area close to the boundary line, the potential field value should increase significantly and reach the maximum value at the lane boundary line. Then, the potential field convergence coefficient of the lane boundary line, the autonomous driving perception fusion information, and the vehicle motion information can be substituted into the lane boundary line constraint potential field function to determine the constraint potential field model corresponding to the lane boundary line. It should be noted that the lane boundary line constraint potential field function is Among them, the U boun is the potential field value of the lane boundary line constraint potential field; boun is the maximum value of the potential field constrained by the lane boundary line; boun,i is the lateral position of the i-th lane boundary line; the σ boun is the potential field convergence coefficient of the lane boundary line.

[0042] On the basis of the above technical solution, the constraint potential field model corresponding to the target modeling object is established based on the autonomous driving perception fusion information and the vehicle motion information, including: when the target modeling object is a moving obstacle, obtaining vehicle information corresponding to the target vehicle, and determining the obstacle information of the moving obstacle, and determining the potential field convergence coefficient of the moving obstacle according to the vehicle information and the obstacle information; determining the constraint potential field model corresponding to the moving obstacle based on the potential field convergence coefficient of the moving obstacle, the autonomous driving perception fusion information, the vehicle motion information and the moving obstacle constraint potential field function.

[0043] The vehicle information may be vehicle data of the vehicle, such as width information of the vehicle, length information of the vehicle, and various preset parameters corresponding to the target vehicle.

[0044] Specifically, in the driving environment, in addition to the static constraints of lane lines on driving behavior, obstacles in the surrounding environment of the vehicle will also affect and interfere with the normal driving of the vehicle. In addition, whether it is lane keeping or lane changing, the lateral and longitudinal speed differences of the vehicle are very large, and the longitudinal driving risk is higher. The safety distance should be much larger than the lateral one. Therefore, the technical solution provided by the embodiment of the present invention will model the lateral and longitudinal dynamic interference potential fields of obstacles in the surrounding environment of the vehicle. Furthermore, the driving obstacle constraint potential field function is Among them, U obs,i is the potential field value of the ith obstacle, A obs is the maximum value of the potential field of the obstacle i, (x i ,y i ) represents the position coordinates of the ith obstacle, (x, y) represents the position coordinates of any point in the area, is the lateral potential field convergence coefficient of the i-th obstacle; is the longitudinal potential field convergence coefficient of the ith obstacle, and n is the potential field shape coefficient of the surrounding vehicles. It should be noted that for the shape parameter n, when its value is 2, then statistically 2σ obs,i It can represent more than 99% of the spatial information of the environment vehicles, therefore, in the technical solution provided in the embodiment of the present invention, n=2.

[0045] S130. Determine a target constraint potential field model corresponding to the target vehicle based on the constraint potential field model, and determine a safe driving area according to the target constraint potential field model.

[0046] The target constraint potential field model may be a comprehensive constraint potential field model obtained by superimposing the potential fields of various target modeling objects.

[0047] Specifically, after determining the constraint potential field model corresponding to each modeling object, the constraint potential field models corresponding to each modeling object can be superimposed to obtain a target constraint potential field model corresponding to the target vehicle, and then the safe driving area is determined according to the target constraint potential field model. For example, in the constraint potential field model, the low potential energy area usually represents the safe driving area. The automatic driving system needs to dynamically determine the safe driving area according to the current vehicle motion state and the constraint potential field model, and adjust the vehicle's driving path and speed in real time to ensure that the vehicle always stays within the safe driving area.

[0048] Exemplarily, the total potential field of the driving environment is a potential field of the combined effect of the dynamic interference potential field and the static constraint potential field. Where n is the number of vehicles in the environment, U pThe value directly reflects the drivability of the location. The larger the total potential field value, the lower the drivability safety of the location. The smaller the total potential field value, the higher the drivability safety of the location. Figure 2 As shown in the figure, taking the lane-changing scene of the same-direction two-lane as an example, assuming that the vehicle position (x o y o )=(0 0), the positions of the environment vehicles are (x Fc y Fc )=(40 0),(x Ft y Ft )=(70 3.75),x Rt y Rt )=(-30 3.75), the speeds of the vehicle and surrounding vehicles are v o =25m / s,v Fc =15m / s,v Ft =30m / s,v Rt =30m / s, lane width is W l =3.75m, the lane centerline and lane boundary line positions are y cen,1 =0,y cen,2 =3.75m, y boun,1 =-1.875m, y boun,2 =5.625m, the potential field coefficients are A cen =-15, A boun =50, A obj =40. Based on Figure 2 The changing law of the total potential field of the surrounding environment when the vehicle is driving can be obtained: (1) In terms of potential field value: the potential field value near the boundary line and the surrounding vehicles is very large, indicating that the driving risk in these areas is very high and the vehicle must stay away from them; on the contrary, the potential field value is small at locations far away from the boundary line and the surrounding vehicles, and reaches a minimum value near the center line of the lane, indicating that the driving risk in these areas is very low and is a relatively safe driving area; (2) In terms of the trend of potential field value changes: the potential field value near the boundary line and the surrounding vehicles increases rapidly when approaching; in addition, the risk impact range of the surrounding vehicles is related to the relative speed of the two vehicles. The greater the relative speed, the greater the longitudinal risk impact range of the surrounding vehicles, while the lateral potential field range does not change significantly, reflecting the reasonable description of the lateral and longitudinal dynamic interference potential fields by the improved artificial potential field method.

[0049] On the basis of the above technical solution, the target constraint potential field model corresponding to the target vehicle is determined based on the constraint potential field model, including: determining the constraint potential field values ​​of each coordinate position in the detection area corresponding to the target vehicle based on the constraint potential field model; determining the target constraint potential field model corresponding to the target vehicle based on the constraint potential field values ​​of each coordinate position in the detection area.

[0050] The detection area can be understood as a preset maximum perception area corresponding to the target vehicle. The coordinate position can be the coordinates of each point in the detection area determined according to the vehicle coordinate system corresponding to the target vehicle established by the autonomous driving system.

[0051] Specifically, for each coordinate point, according to the established constraint potential field model, including the constraint potential field models such as lane boundary lines, lane center lines and driving obstacles, the potential field values ​​of the constraint potential field models corresponding to the current coordinate point are superimposed to obtain the target constraint potential field model corresponding to the target vehicle. The proportional value corresponding to each constraint potential field model can also be determined, and the potential field values ​​of each constraint potential field model are weighted and summed according to the proportional value to obtain the final target constraint potential field model.

[0052] Based on the above technical solution, determining the safe driving area according to the target constraint potential field model includes: obtaining a constraint potential field threshold corresponding to the target vehicle, and determining the safe driving area from the target constraint potential field model according to the constraint potential field threshold.

[0053] The constraint potential field threshold may be understood as a pre-set potential field value corresponding to the target vehicle.

[0054] Specifically, it can be to obtain the automatic driving mode corresponding to the target vehicle, determine the constraint potential field threshold of the target vehicle according to the automatic driving mode selected by the user, and determine the safe driving area from the target constraint potential field model according to the constraint potential field threshold. For example, it can be to traverse each coordinate point in the target constraint potential field model, obtain its corresponding constraint potential field value, and compare the constraint potential field value of each coordinate point with the preset constraint potential field threshold. If the constraint potential field value is lower than the threshold, it is considered that the coordinate point belongs to the safe driving area; otherwise, it is considered that there is potential danger, and then according to the comparison result, the safe driving area is marked in the target constraint potential field model.

[0055] The technical solution of the embodiment of the present invention obtains the autonomous driving perception fusion information and vehicle motion information corresponding to the target vehicle, and determines the target modeling object based on the autonomous driving perception fusion information, and then establishes a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information, and finally determines the target constraint potential field model corresponding to the target vehicle based on the constraint potential field model, and determines the safe driving area based on the target constraint potential field model. Based on the above technical solution, the constraint potential field model in the autonomous driving process is established by integrating the autonomous driving perception fusion information and the vehicle motion information, and then the safe driving area is determined based on the constraint potential field model, thereby improving the safety performance of the vehicle in the autonomous driving process.

[0056] Embodiment 2

[0057] Figure 3 This is a flowchart of a method for determining a safe driving area for an autonomous driving vehicle provided in an embodiment of the present invention. Based on the above embodiment, this embodiment further refines the technical solution of determining the potential field convergence coefficient of the driving obstacle based on the vehicle information and obstacle information. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiment are not repeated here. Figure 3 As shown, the method includes:

[0058] S210: Acquire the vehicle width and vehicle length of the target vehicle, and determine the lateral safety distance and longitudinal safety distance corresponding to the target vehicle.

[0059] The vehicle width can be understood as the body width value of the target vehicle, and the corresponding vehicle length can be the body length value corresponding to the target vehicle. The lateral safety distance can be understood as the minimum horizontal distance that should be maintained between the target vehicle and its adjacent lanes or obstacles, and the corresponding longitudinal safety distance can be understood as the minimum longitudinal distance that should be maintained between the target vehicle and the vehicle in front or behind it.

[0060] Specifically, the vehicle width and length corresponding to the target vehicle are determined by reading the data manual pre-stored in the vehicle storage device, and then the lateral safety distance corresponding to the target vehicle is determined according to the vehicle width. For example, the lateral safety distance should be at least half of the width of the target vehicle, and the longitudinal safety distance is closely related to the vehicle speed and the braking performance of the vehicle. Generally speaking, the faster the vehicle speed, the greater the required longitudinal safety distance. The longitudinal safety distance can be determined by obtaining the driving speed of the target vehicle and matching it in the database according to the driving speed.

[0061] S220. Determine the obstacle width and obstacle length corresponding to each driving obstacle according to the autonomous driving perception fusion information.

[0062] The obstacle width may be understood as the width value of the obstacle, and correspondingly, the obstacle length may be the length value corresponding to the current obstacle.

[0063] Specifically, the obstacle width and obstacle length corresponding to the current driving obstacle can be determined by using a laser radar installed on the vehicle, for example, by obtaining the three-dimensional point cloud data generated by the laser radar emitting a laser beam and receiving a reflected signal, and then the shape and size of the current driving obstacle can be accurately determined based on the three-dimensional point cloud data. Alternatively, a camera with depth perception function installed on the target vehicle can be used to collect an obstacle image corresponding to the current driving obstacle, and the obstacle width and obstacle length can be determined based on the obstacle image.

[0064] S230: Determine a lateral potential field convergence coefficient of the traveling obstacle based on the vehicle width, the obstacle width, and the lateral safety distance.

[0065] Among them, the lateral potential field convergence coefficient can be an indicator used to represent the degree of lateral space tension between the vehicle and the obstacle.

[0066] Based on the above technical solution, the method of determining the lateral potential field convergence coefficient of the moving obstacle based on the vehicle width, the obstacle width and the lateral safety distance includes: determining the lateral influence distance based on the vehicle width, the obstacle width and the lateral safety distance; determining the lateral potential field convergence coefficient of the moving obstacle based on the lateral influence distance.

[0067] The lateral impact distance may be a safe distance between the vehicle and obstacles or other vehicles on its side.

[0068] Specifically, for the potential field coefficient that affects the lateral risk range The main focus is on the impact of the width of the vehicle and surrounding vehicles. Since the lateral speed during lane change is small, it is not considered. The width of the vehicle is considered to expand the surrounding vehicles according to the size of the vehicle; at the same time, in order to ensure sufficient safety distance, the lateral safety distance is introduced here, and the lateral impact distance Among them, W o is the vehicle width, W obs,i is the width of the obstacle i in the surrounding environment, W safe is the lateral safety distance, and the lateral potential field convergence coefficient can be determined according to the lateral influence distance

[0069] S240: Determine a longitudinal potential field convergence coefficient of a traveling obstacle based on the vehicle length, the obstacle length, the longitudinal safety distance, and the vehicle motion information.

[0070] The longitudinal potential field convergence coefficient may be an indicator for indicating the degree of longitudinal space tension between the vehicle and the obstacle.

[0071] On the basis of the above technical solution, the determining of the longitudinal potential field convergence coefficient of the traveling obstacle based on the vehicle length, the obstacle length, the longitudinal safety distance and the vehicle motion information includes: determining the speed difference between the target vehicle and the traveling obstacle based on the vehicle motion information, and determining the calculation delay time; determining the longitudinal influence distance according to the speed difference, the calculation delay time, the longitudinal safety distance, the vehicle length and the obstacle length; and determining the longitudinal potential field convergence coefficient of the traveling obstacle according to the longitudinal influence distance.

[0072] The calculation delay time may be understood as a preset calculation delay. The longitudinal impact distance may be a safe distance between the target vehicle and other vehicles or obstacles in the longitudinal direction.

[0073] Specifically, for the potential field coefficient that affects the longitudinal risk range Since the longitudinal speed of the vehicle is relatively high, its impact on the risk range must be taken into consideration. The longitudinal impact distance L of the technical solution provided in the embodiment of the present invention is imp , Where: L o is the length of the vehicle, L obs,Fc is the length of the preceding vehicle Fc, L safe is the longitudinal safety distance, v o and v Fc are the longitudinal speeds of the vehicle and the preceding vehicle respectively, and ΔT is the delay time. Then, the longitudinal potential field convergence coefficient can be determined according to the longitudinal influence distance.

[0074] The technical solution of the embodiment of the present invention obtains the vehicle width and vehicle length of the target vehicle, and determines the lateral safety distance and longitudinal safety distance corresponding to the target vehicle, and then determines the obstacle width and obstacle length corresponding to each driving obstacle according to the autonomous driving perception fusion information, and determines the lateral potential field convergence coefficient of the driving obstacle based on the vehicle width, the obstacle width and the lateral safety distance, and finally determines the longitudinal potential field convergence coefficient of the driving obstacle based on the vehicle length, the obstacle length, the longitudinal safety distance and the vehicle motion information. Based on the above technical solution, the potential field convergence coefficients corresponding to different driving obstacles are determined, and then the constraint potential fields corresponding to different obstacles are determined according to the potential field convergence coefficients, which ensures the accuracy of the potential field modeling process and improves the safety performance of autonomous driving.

[0075] Embodiment 3

[0076] Figure 4 This is a structural block diagram of a device for determining a safe driving area for an autonomous driving vehicle provided by an embodiment of the present invention. Figure 4 As shown, the device includes: an object determination module 410 , a local model determination module 420 and a safety area determination module 430 .

[0077] The object determination module 410 is used to obtain the autonomous driving perception fusion information and the vehicle motion information corresponding to the target vehicle, and determine the target modeling object according to the autonomous driving perception fusion information, wherein the target modeling object includes at least one of a lane centerline, a lane boundary line, and a driving obstacle;

[0078] A local model determination module 420, configured to establish a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information;

[0079] The safety area determination module 430 is used to determine a target constraint potential field model corresponding to the target vehicle based on the constraint potential field model, and determine a safe driving area according to the target constraint potential field model.

[0080] Based on the above technical solution, the local model determination module includes: a lane centerline potential field establishment unit, which is used to determine the lane width corresponding to the lane centerline when the target modeling object is the lane centerline, and determine the potential field convergence coefficient of the lane centerline according to the lane width; determine the constraint potential field model corresponding to the lane centerline based on the potential field convergence coefficient of the lane centerline, the autonomous driving perception fusion information, the vehicle motion information and the lane centerline constraint potential field function.

[0081] On the basis of the above technical solution, the local model determination module includes: a lane boundary line potential field establishment unit, the lane boundary line potential field establishment unit is used to determine the potential field convergence coefficient of the lane boundary line when the target modeling object is a lane boundary line;

[0082] A constraint potential field model corresponding to the lane boundary line is determined based on the potential field convergence coefficient of the lane boundary line, the autonomous driving perception fusion information, the vehicle motion information and the lane boundary line constraint potential field function.

[0083] On the basis of the above technical solution, the local model determination module includes: a driving obstacle potential field establishment unit, which is used to obtain vehicle information corresponding to the target vehicle and determine the obstacle information of the driving obstacle when the target modeling object is a driving obstacle, and determine the potential field convergence coefficient of the driving obstacle according to the vehicle information and the obstacle information; determine the constraint potential field model corresponding to the driving obstacle based on the potential field convergence coefficient of the driving obstacle, the automatic driving perception fusion information, the vehicle motion information and the driving obstacle constraint potential field function.

[0084] On the basis of the above technical solution, the driving obstacle potential field establishing unit is used to obtain the vehicle width and vehicle length of the target vehicle, and determine the lateral safety distance and longitudinal safety distance corresponding to the target vehicle; determine the obstacle width and obstacle length corresponding to each driving obstacle according to the automatic driving perception fusion information; determine the lateral potential field convergence coefficient of the driving obstacle based on the vehicle width, the obstacle width and the lateral safety distance; determine the longitudinal potential field convergence coefficient of the driving obstacle based on the vehicle length, the obstacle length, the longitudinal safety distance and the vehicle motion information.

[0085] Based on the above technical solution, the driving obstacle potential field establishing unit is used to determine the lateral impact distance based on the vehicle width, the obstacle width and the lateral safety distance; and determine the lateral potential field convergence coefficient of the driving obstacle based on the lateral impact distance.

[0086] On the basis of the above technical solution, the traveling obstacle potential field establishing unit is used to determine the speed difference between the target vehicle and the traveling obstacle based on the vehicle motion information, and determine the calculation delay time; determine the longitudinal influence distance according to the speed difference, the calculation delay time, the longitudinal safety distance, the vehicle length and the obstacle length; determine the longitudinal potential field convergence coefficient of the traveling obstacle according to the longitudinal influence distance.

[0087] Based on the above technical solution, the safety area determination module is used to determine the constraint potential field value of each coordinate position in the detection area corresponding to the target vehicle based on the constraint potential field model; and determine the target constraint potential field model corresponding to the target vehicle based on the constraint potential field value of each coordinate position in the detection area.

[0088] On the basis of the above technical solution, the safety area determination module is used to obtain a constraint potential field threshold corresponding to the target vehicle, and determine the safe driving area from the target constraint potential field model according to the constraint potential field threshold.

[0089] Based on the above technical solution, the lane centerline constraint potential field function is: Among them, the U cen is the potential field value of the lane centerline constraint; cen is the minimum value of the lane centerline constraint potential field; cen,i is the lateral coordinate value of the centerline of the i-th lane; i is the number of lane centerlines; σ cen is the potential field convergence coefficient of the lane centerline; boun,i is the lateral position of the i-th lane boundary line.

[0090] Based on the above technical solution, the lane boundary line constraint potential field function is: Among them, the U boun is the potential field value of the lane boundary line constraint potential field; boun is the maximum value of the potential field constrained by the lane boundary line; boun,i is the lateral position of the i-th lane boundary line; the σ boun is the potential field convergence coefficient.

[0091] Based on the above technical solution, the driving obstacle constraint potential field function is: Among them, U obs,i is the potential field value of the ith obstacle, A obs is the maximum value of the potential field of the obstacle i, (x i ,y i ) represents the position coordinates of the ith obstacle, (x, y) represents the position coordinates of any point in the area, σ obsx,i is the lateral potential field convergence coefficient of the ith obstacle; σ obsy,i is the longitudinal potential field convergence coefficient of the ith obstacle, and n is the potential field shape coefficient of the surrounding vehicles.

[0092] The technical solution of the embodiment of the present invention obtains the autonomous driving perception fusion information and vehicle motion information corresponding to the target vehicle, and determines the target modeling object based on the autonomous driving perception fusion information, and then establishes a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information, and finally determines the target constraint potential field model corresponding to the target vehicle based on the constraint potential field model, and determines the safe driving area based on the target constraint potential field model. Based on the above technical solution, the constraint potential field model in the autonomous driving process is established by integrating the autonomous driving perception fusion information and the vehicle motion information, and then the safe driving area is determined based on the constraint potential field model, thereby improving the safety performance of the vehicle in the autonomous driving process.

[0093] The device for determining the safe driving area of ​​an autonomous driving vehicle provided in an embodiment of the present invention can execute the method for determining the safe driving area of ​​an autonomous driving vehicle provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0094] Embodiment 4

[0095] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0096] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0097] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0098] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining a safe driving area for an autonomous driving vehicle.

[0099] In some embodiments, the method for determining a safe driving area for an autonomous driving vehicle may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining a safe driving area for an autonomous driving vehicle described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for determining a safe driving area for an autonomous driving vehicle in any other appropriate manner (e.g., by means of firmware).

[0100] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0101] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0102] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0103] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0104] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0105] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0106] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0107] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a safe driving area for an autonomous driving vehicle, characterized in that: include: Acquire autonomous driving perception fusion information and vehicle motion information corresponding to the target vehicle, and determine a target modeling object according to the autonomous driving perception fusion information, wherein the target modeling object includes at least one of a lane centerline, a lane boundary line, and a driving obstacle; Establishing a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information; A target constraint potential field model corresponding to the target vehicle is determined based on the constraint potential field model, and a safe driving area is determined according to the target constraint potential field model.

2. The method according to claim 1, characterized in that The step of establishing a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information includes: In a case where the target modeling object is a lane centerline, determining a lane width corresponding to the lane centerline, and determining a potential field convergence coefficient of the lane centerline according to the lane width; A constraint potential field model corresponding to the lane centerline is determined based on the potential field convergence coefficient of the lane centerline, the autonomous driving perception fusion information, the vehicle motion information and the lane centerline constraint potential field function.

3. The method according to claim 1, characterized in that The step of establishing a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information includes: When the target modeling object is a lane boundary line, determining a potential field convergence coefficient of the lane boundary line; A constraint potential field model corresponding to the lane boundary line is determined based on the potential field convergence coefficient of the lane boundary line, the autonomous driving perception fusion information, the vehicle motion information and the lane boundary line constraint potential field function.

4. The method according to claim 1, characterized in that: The step of establishing a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information includes: In the case where the target modeling object is a traveling obstacle, vehicle information corresponding to the target vehicle is acquired, obstacle information of the traveling obstacle is determined, and a potential field convergence coefficient of the traveling obstacle is determined according to the vehicle information and the obstacle information; A constraint potential field model corresponding to the driving obstacle is determined based on the potential field convergence coefficient of the driving obstacle, the automatic driving perception fusion information, the vehicle motion information and the driving obstacle constraint potential field function.

5. The method according to claim 4, characterized in that The determining of the potential field convergence coefficient of the traveling obstacle according to the vehicle information and the obstacle information includes: Obtaining the vehicle width and vehicle length of the target vehicle, and determining the lateral safety distance and longitudinal safety distance corresponding to the target vehicle; Determining the obstacle width and obstacle length corresponding to each driving obstacle according to the autonomous driving perception fusion information; Determining a lateral potential field convergence coefficient of the traveling obstacle based on the vehicle width, the obstacle width and the lateral safety distance; A longitudinal potential field convergence coefficient of the traveling obstacle is determined based on the vehicle length, the obstacle length, the longitudinal safety distance and the vehicle motion information.

6. The method according to claim 5, characterized in that The determining of the lateral potential field convergence coefficient of the traveling obstacle based on the vehicle width, the obstacle width and the lateral safety distance includes: determining a lateral impact distance based on the vehicle width, the obstacle width and the lateral safety distance; A lateral potential field convergence coefficient of the traveling obstacle is determined based on the lateral influence distance.

7. The method according to claim 5, characterized in that The determining of the longitudinal potential field convergence coefficient of the traveling obstacle based on the vehicle length, the obstacle length, the longitudinal safety distance and the vehicle motion information comprises: Determine a speed difference between the target vehicle and the driving obstacle based on the vehicle motion information, and determine a calculation delay time; determining a longitudinal impact distance according to the speed difference, the calculation delay time, the longitudinal safety distance, the vehicle length and the obstacle length; A longitudinal potential field convergence coefficient of the obstacle is determined according to the longitudinal influence distance.

8. The method according to claim 1, characterized in that The step of determining a target constraint potential field model corresponding to the target vehicle based on the constraint potential field model comprises: Determining the constraint potential field value of each coordinate position in the detection area corresponding to the target vehicle based on the constraint potential field model; A target constraint potential field model corresponding to the target vehicle is determined based on the constraint potential field values ​​of each coordinate position in the detection area.

9. The method according to claim 1, characterized in that: Determining the safe driving area according to the target constraint potential field model includes: A constraint potential field threshold corresponding to the target vehicle is acquired, and the safe driving area is determined from the target constraint potential field model according to the constraint potential field threshold.

10. The method according to claim 2, characterized in that The lane centerline constraint potential field function is: Among them, the U cen is the potential field value of the lane centerline constraint; cen is the minimum value of the lane centerline constraint potential field; cen,i is the lateral coordinate value of the centerline of the i-th lane; i is the number of lane centerlines; σ cen is the potential field convergence coefficient of the lane centerline; boun,i is the lateral position of the i-th lane boundary line.

11. The method according to claim 3, characterized in that The lane boundary line constraint potential field function is: Among them, the U boun is the potential field value of the lane boundary line constraint potential field; boun is the maximum value of the potential field constrained by the lane boundary line; boun,i is the lateral position of the i-th lane boundary line; the σ boun is the potential field convergence coefficient.

12. The method according to claim 4, characterized in that The driving obstacle constraint potential field function is: Among them, U obs,i is the potential field value of the ith obstacle, A obs is the maximum value of the potential field of the obstacle i, (x i ,y i ) represents the position coordinates of the ith obstacle, (x, y) represents the position coordinates of any point in the area, is the lateral potential field convergence coefficient of the i-th obstacle; is the longitudinal potential field convergence coefficient of the ith obstacle, and n is the potential field shape coefficient of the surrounding vehicles.

13. A device for determining a safe driving area for an autonomous driving vehicle, characterized in that: include: an object determination module, configured to obtain autonomous driving perception fusion information and vehicle motion information corresponding to a target vehicle, and determine a target modeling object according to the autonomous driving perception fusion information, wherein the target modeling object includes at least one of a lane centerline, a lane boundary line, and a driving obstacle; A local model determination module, used to establish a constraint potential field model corresponding to the target modeling object based on the autonomous driving perception fusion information and the vehicle motion information; The safety area determination module is used to determine a target constraint potential field model corresponding to a target vehicle based on the constraint potential field model, and determine a safe driving area according to the target constraint potential field model.

14. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the control method of the intelligent driving vehicle described in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the control method of an intelligent driving vehicle according to any one of claims 1 to 12 when executed.

Citation Information

Patent Citations

  • Method and device for controlling autonomous vehicle

    CN114771570A

  • Path planning method and device for autonomous vehicle, equipment and medium

    CN115839722A

  • Highway collaborative decision-making safe driving method and system

    CN117116072A

  • Self-driving automobile compliance decision-making method and device and electronic equipment

    CN118419072A

  • Calculation method and device for drivable area of vehicle, vehicle and storage medium

    CN118457598A