Vehicle travelable boundary generation method and device, electronic equipment and storage medium

Abstract

The invention provides a vehicle travelable boundary generation method and device, electronic equipment and a storage medium, the method comprises the steps that obstacle information of a vehicle under a vehicle-mounted camera coordinate system is acquired through a vehicle-mounted camera of the vehicle, the vehicle has at least three obstacles, and the obstacle information at least comprises transverse and longitudinal distances of the obstacles; coordinate system conversion is carried out on the obstacle information of the vehicle under the vehicle-mounted camera coordinate system, an obstacle information coordinate system conversion result of the vehicle is obtained, and the obstacle information coordinate system conversion result at least comprises the obstacle information of the vehicle under the own vehicle coordinate system; according to the obstacle information coordinate system conversion result, the travelable boundary of the vehicle is generated without depending on map data, the travelable boundary can be generated according to actual sensing data, and the problem that an existing technical scheme for generating the travelable boundary by using a high-precision map is very dependent on map data and cannot be used for generating the travelable boundary is solved. And the problem that the driving safety is influenced because the automatic driving system cannot accurately identify the road condition is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a method, device, electronic device and storage medium for generating a vehicle drivable boundary. Background Art

[0002] The drivable boundary usually refers to the range within which a vehicle can safely drive in road traffic, that is, the maximum boundary range allowed when the vehicle is driving on the road.

[0003] At present, the technical solution for generating vehicle drivable boundaries in the field of autonomous driving is mainly generated by using high-precision map data, such as roads, radar signs and other information, to help vehicles plan paths.

[0004] The inventors have discovered that the technical solution of using high-precision maps to generate drivable boundaries is highly dependent on map data. If there is a lag in map information, especially in the case of road reconstruction or new road construction, the autonomous driving system may be unable to accurately identify road conditions, thereby affecting driving safety. Summary of the Invention

[0005] In this regard, the present application provides a method, device, electronic device and storage medium for generating a vehicle's drivable boundary to solve the problem that the existing technical solution for generating a drivable boundary using high-precision maps is highly dependent on map data. If there is a lag in map information, especially in the case of road reconstruction or new road construction, it is easy for the autonomous driving system to be unable to accurately identify the road conditions, thereby affecting driving safety.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] The first aspect of the present application discloses a method for generating a vehicle drivable boundary, comprising:

[0008] Obtaining obstacle information of the vehicle in a coordinate system of the vehicle-mounted camera through the vehicle-mounted camera, wherein there are at least three obstacles in front of the vehicle, and the obstacle information includes at least the horizontal and vertical distances of the obstacles;

[0009] performing a coordinate system conversion on the obstacle information of the vehicle in the onboard camera coordinate system to obtain a coordinate system conversion result of the obstacle information of the vehicle, wherein the obstacle information coordinate system conversion result includes at least the obstacle information of the vehicle in the ego-vehicle coordinate system and the obstacle information of the vehicle in the kinematically predicted trajectory coordinate system;

[0010] The drivable boundary of the vehicle is generated according to the obstacle information coordinate system conversion result.

[0011] Optionally, in the above-mentioned method for generating a vehicle drivable boundary, performing coordinate system transformation on the obstacle information of the vehicle in the on-board camera coordinate system to obtain the coordinate transformation result of the obstacle information of the vehicle includes:

[0012] Performing a self-vehicle coordinate system conversion on the obstacle information of the vehicle in the vehicle-mounted camera coordinate system to obtain the obstacle information of the vehicle in the self-vehicle coordinate system;

[0013] Determining whether the vehicle meets the lane line prediction trajectory coordinate system conversion requirements;

[0014] If the vehicle meets the lane line prediction trajectory coordinate system conversion requirements, then the obstacle information of the vehicle in the ego vehicle coordinate system is respectively converted into the lane line prediction trajectory coordinate system and the kinematic prediction trajectory coordinate system to obtain the obstacle information of the vehicle in the lane line prediction trajectory coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system, and the obstacle information of the vehicle in the ego vehicle coordinate system, the obstacle information of the vehicle in the lane line prediction trajectory coordinate system, and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system are used as the obstacle information coordinate conversion result of the vehicle;

[0015] If the vehicle does not meet the lane line prediction trajectory coordinate system conversion requirements, the obstacle information of the vehicle in the ego vehicle coordinate system is converted into the kinematic prediction trajectory coordinate system to obtain the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system, and the obstacle information of the vehicle in the ego vehicle coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system are used as the obstacle information coordinate conversion result of the vehicle.

[0016] Optionally, in the above-mentioned method for generating a drivable boundary of a vehicle, the vehicle meets the lane line prediction trajectory coordinate system conversion requirements, including:

[0017] The road line mass of the vehicle is greater than a preset road line mass.

[0018] Optionally, in the above-mentioned method for generating a drivable boundary of a vehicle, the process of generating a lane line prediction trajectory coordinate system includes:

[0019] Determine lane line information of the vehicle in the vehicle coordinate system, wherein the lane line information includes at least: lane line lateral distance, lane line slope, lane line curvature, and lane line curvature change rate;

[0020] Fitting the lane line information of the vehicle in the vehicle coordinate system to obtain a lane line prediction trajectory curve of the vehicle, and obtaining a lane line prediction trajectory coordinate system of the vehicle based on the lane line prediction trajectory curve of the vehicle;

[0021] The process of generating the kinematic prediction trajectory coordinate system includes:

[0022] Acquiring kinematic information of the vehicle, the kinematic information including at least: vehicle angular velocity, steering wheel angle, and steering gear ratio;

[0023] Obtaining a turning radius of the vehicle according to the kinematic information;

[0024] Fitting is performed according to the vehicle's own turning radius to obtain a kinematic prediction trajectory curve of the vehicle, and based on the vehicle's kinematic prediction trajectory curve, a kinematic prediction trajectory coordinate system of the vehicle is obtained.

[0025] Optionally, in the above-mentioned method for generating a drivable boundary of a vehicle, generating the drivable boundary of the vehicle according to the obstacle information coordinate system conversion result includes:

[0026] Determining whether the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal;

[0027] If it is determined that the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is unequal, generating a drivable boundary of the vehicle based on the obstacle seed points in the coordinate system having the largest number of obstacle seed points in the obstacle information coordinate system conversion result;

[0028] If it is determined that the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal, generating the drivable boundary of the vehicle based on the obstacle seed points in the coordinate system with the highest priority in the obstacle information coordinate system conversion result in accordance with the coordinate system priority order;

[0029] The priority order of the coordinate systems is: lane line prediction trajectory coordinate system > kinematics prediction trajectory coordinate system > vehicle coordinate system.

[0030] Optionally, in the above-mentioned method for generating a drivable boundary of a vehicle, generating the drivable boundary of the vehicle according to the obstacle seed points in the corresponding coordinate system includes:

[0031] Determining the inner point of the vehicle in the obstacle in the corresponding coordinate system according to the seed point of the obstacle in the corresponding coordinate system;

[0032] respectively determining whether the number of points within the obstacle of the vehicle in the corresponding coordinate system is greater than or equal to a preset number and whether the quadratic term coefficient of the corresponding cubic polynomial curve is less than a preset quadratic term coefficient;

[0033] If it is determined that the number of obstacle interior points of the vehicle in the corresponding coordinate system is greater than or equal to a preset number, and the quadratic term coefficient of the corresponding cubic polynomial curve is less than the preset quadratic term coefficient, the obstacle interior point of the vehicle in the corresponding coordinate system is used as the target obstacle interior point, and the drivable boundary of the vehicle is generated based on the target obstacle interior point.

[0034] Optionally, in the above-mentioned method for generating a drivable boundary of a vehicle, determining the obstacle interior point of the vehicle in the corresponding coordinate system according to the obstacle seed point in the corresponding coordinate system includes:

[0035] Generating a fitting curve of the obstacle seed points of the vehicle in the corresponding coordinate system according to the obstacle seed points in the corresponding coordinate system;

[0036] Determining the horizontal coordinate of the fitting curve of each obstacle seed point of the vehicle in the corresponding coordinate system according to the obstacle seed point fitting curve;

[0037] For each obstacle seed point of the vehicle in the corresponding coordinate system, obtain its lateral distance error according to its coordinate system abscissa and the fitting curve abscissa;

[0038] The obstacle seed point whose lateral distance error is less than the preset lateral distance error is used as the obstacle interior point of the vehicle in the corresponding coordinate system.

[0039] A second aspect of the present application discloses a vehicle drivable boundary generating device, comprising:

[0040] an acquisition unit, configured to acquire obstacle information of the vehicle in a vehicle-mounted camera coordinate system through a vehicle-mounted camera of the vehicle, wherein there are at least three obstacles in front of the vehicle, and the obstacle information includes at least the horizontal and vertical distances of the obstacles;

[0041] a conversion unit, configured to perform coordinate system conversion on the obstacle information of the vehicle in the onboard camera coordinate system to obtain a coordinate system conversion result of the obstacle information of the vehicle, wherein the obstacle information coordinate system conversion result includes at least the obstacle information of the vehicle in the ego-vehicle coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system;

[0042] A generating unit is used to generate a drivable boundary of the vehicle according to the obstacle information coordinate system conversion result.

[0043] A third aspect of the present application discloses an electronic device, comprising: a memory and a processor;

[0044] Wherein, the memory is used to store computer programs;

[0045] The processor is used to execute the computer program, specifically to implement the vehicle drivable boundary generation method as described in any one of the first aspects disclosed.

[0046] The fourth aspect of the present application discloses a computer storage medium for storing a computer program. When the computer program is executed, it is specifically used to implement the vehicle drivable boundary generation method as described in any one of the items disclosed in the first aspect.

[0047] The present invention provides a method for generating a drivable boundary of a vehicle, comprising: obtaining obstacle information of the vehicle in a coordinate system of the on-board camera through an on-board camera of the vehicle, wherein there are at least three obstacles in the vehicle, and the obstacle information includes at least the horizontal and vertical distances of the obstacles; performing coordinate system conversion on the obstacle information of the vehicle in the on-board camera coordinate system to obtain a coordinate system conversion result of the obstacle information of the vehicle, wherein the obstacle information coordinate system conversion result includes at least the obstacle information of the vehicle in the own-vehicle coordinate system; generating a drivable boundary of the vehicle according to the obstacle information coordinate system conversion result, without relying on map data, and the drivable boundary can be generated according to actual perception data, thereby solving the problem that the existing technical solution for generating a drivable boundary using a high-precision map is highly dependent on map data. If there is a lag in the map information, especially in the case of road reconstruction or new road construction, it is easy to cause the automatic driving system to be unable to accurately identify the road condition, thereby affecting driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0049] Figure 1 A flowchart of a method for generating a vehicle drivable boundary provided in this application;

[0050] Figure 2 A flowchart of a coordinate system conversion provided in an embodiment of the present application;

[0051] Figure 3 A flow chart for generating a kinematic prediction trajectory coordinate system for a vehicle provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of the structure of a vehicle lane line prediction trajectory coordinate system provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of a lane line prediction trajectory and a kinematic prediction trajectory provided in an embodiment of the present application;

[0054] Figure 6 An example diagram of generating a drivable boundary of a vehicle provided in an embodiment of the present application;

[0055] Figure 7 A schematic diagram of the structure of a vehicle drivable boundary generating device provided in an embodiment of the present application;

[0056] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0058] First of all, it should be noted that an obstacle in this application refers to any object that may potentially hinder the normal driving path of a vehicle.

[0059] The embodiments of the present application provide a method, device, electronic device and storage medium for generating a vehicle's drivable boundary to solve the problem that the existing technical solution for generating a drivable boundary using high-precision maps is highly dependent on map data. If there is a lag in map information, especially in the case of road reconstruction or new road construction, it is easy for the autonomous driving system to be unable to accurately identify the road conditions, thereby affecting driving safety.

[0060] See Figure 1 , the vehicle drivable boundary generation method mainly includes the following steps:

[0061] S101. Obtain obstacle information of the vehicle in the vehicle camera coordinate system through the vehicle camera; there are at least three obstacles in front of the vehicle, and the obstacle information includes at least the horizontal and vertical distances of the obstacles.

[0062] In practice, the vehicle's onboard forward-looking camera can be used to obtain obstacle information of the vehicle under the coordinates of the onboard camera; of course, it is not limited to this, and it can also be obtained through other cameras of the vehicle, all of which are within the scope of protection of this application.

[0063] Specifically, each vehicle is generally equipped with 1 to 3 on-board forward-looking cameras, which are generally installed on the inside of the vehicle's windshield, near the top or rearview mirror.

[0064] It should be noted that the vehicle's onboard camera can obtain obstacle information such as the vehicle's horizontal and vertical distance, horizontal and vertical speed, length, width, and heading angle. Since the obstacle information is obtained through the onboard camera, the obstacle information uses the onboard camera coordinate system as a reference point. Among them, the origin of the onboard camera coordinate system is the location where the onboard camera is installed. Axis and The axis direction can be customized by the onboard camera.

[0065] To address multiple stationary vehicle scenarios, after obtaining obstacle information about the vehicles in their camera coordinate systems through their onboard cameras, the obstacle information can be filtered and used to subsequently generate the vehicle's drivable boundary. The filtering conditions can include the requirement that the obstacle's lateral and longitudinal distances are less than a preset lateral and longitudinal distance and that the obstacle is stationary. Thus, obstacles with a lateral and longitudinal distance less than the preset lateral and longitudinal distances and that are stationary are used to subsequently generate the vehicle's drivable boundary. Of course, the filtering conditions are not limited to these and can be determined based on the application environment and user needs, all of which are within the scope of protection of this application.

[0066] In practice, the specific values ​​of the preset horizontal and vertical distances can be determined based on the detection range of the vehicle-mounted camera. For example, the longer the detection range of the vehicle-mounted camera, the larger the preset horizontal and vertical distances. When the horizontal and vertical speeds of an obstacle are both 0, the obstacle is considered to be stationary.

[0067] S102 : performing coordinate system conversion on the obstacle information of the vehicle in the vehicle-mounted camera coordinate system to obtain a coordinate system conversion result of the obstacle information of the vehicle, wherein the obstacle information coordinate system conversion result at least includes the obstacle information of the vehicle in the vehicle coordinate system.

[0068] In some embodiments, the specific process of performing coordinate system conversion on the obstacle information of the vehicle in the vehicle-mounted camera coordinate system in step S102 to obtain the coordinate system conversion result of the obstacle information of the vehicle can be as follows: Figure 2 As shown, it mainly includes steps S201 to S204:

[0069] S201 : performing a conversion of the obstacle information of the vehicle in the vehicle-mounted camera coordinate system into the vehicle coordinate system to obtain the obstacle information of the vehicle in the vehicle coordinate system.

[0070] In this application, the vehicle coordinate system is a coordinate system established with the vehicle itself as the reference point, and the origin is usually set at the center of the vehicle's rear axle or center of mass. The axis points to the front of the vehicle, Axis pointing to the left, The axis is vertically upward.

[0071] Since the obstacle information obtained by the vehicle's onboard camera is based on the vehicle's onboard camera coordinate system, it is necessary to align the obstacle information to the vehicle's own vehicle coordinate system.

[0072] In specific applications, the horizontal and vertical distances of the vehicle's obstacles can be converted from the vehicle's camera coordinates to the vehicle's own coordinate system.

[0073] S202: Determine whether the vehicle meets the lane line prediction trajectory coordinate system conversion requirements.

[0074] The vehicle meets the lane prediction trajectory coordinate system conversion requirements when the vehicle's lane quality is greater than the preset lane quality. The lane quality generally includes the lane quality on the left and right sides of the vehicle.

[0075] If the left-side road line quality and / or the right-side road line quality of the vehicle are both greater than the preset road line quality, that is, the left-side road line quality and / or the right-side road line quality of the vehicle are both high, the vehicle is deemed to meet the lane line prediction trajectory coordinate system conversion requirements; if the left-side road line quality and the right-side road line quality of the vehicle are both not greater than the preset road line quality, that is, the left-side road line quality and the right-side road line quality of the vehicle are both low, the vehicle is deemed to not meet the lane line prediction trajectory coordinate system conversion requirements.

[0076] It should be noted that the road quality of the vehicle can be determined by parameters such as road length and road confidence; the specific value of the preset road quality can be determined according to the application environment and user needs. This application does not make any specific limitations and is within the scope of protection of this application.

[0077] If the vehicle meets the lane line prediction trajectory coordinate system conversion requirements, step S202 is executed; if the vehicle does not meet the lane line prediction trajectory coordinate system conversion requirements, step S203 is executed.

[0078] S203. Perform lane line prediction trajectory coordinate system conversion and kinematic prediction trajectory coordinate system conversion on the obstacle information of the vehicle in the ego-vehicle coordinate system, obtain the obstacle information of the vehicle in the lane line prediction trajectory coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system, and use the obstacle information of the vehicle in the ego-vehicle coordinate system, the obstacle information of the vehicle in the lane line prediction trajectory coordinate system, and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system as the vehicle's obstacle information coordinate conversion result.

[0079] In practice, if the vehicle meets the requirements for lane line prediction trajectory coordinate system conversion, the obstacle information of the vehicle in the ego-vehicle coordinate system is converted into the lane line prediction trajectory coordinate system and the kinematic prediction trajectory coordinate system.

[0080] In specific applications, the lateral and longitudinal distances of the vehicle's obstacles can be converted from the vehicle coordinate system to the lane line prediction trajectory coordinate system and the kinematic prediction trajectory coordinate system respectively.

[0081] S204. Perform a kinematic prediction trajectory coordinate system conversion on the obstacle information of the vehicle in the ego-vehicle coordinate system to obtain the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system. The obstacle information of the vehicle in the ego-vehicle coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system are used as the vehicle's obstacle information coordinate conversion result.

[0082] In practice, if the vehicle does not meet the lane line prediction trajectory coordinate system conversion requirements, only the obstacle information of the vehicle in the vehicle coordinate system is converted into the kinematic prediction trajectory coordinate system.

[0083] In this application, the kinematic prediction trajectory coordinate system is a coordinate system used to describe the vehicle's motion state, including the changes in parameters such as position, velocity, acceleration, etc. over time. In some embodiments, the generation process of the vehicle's kinematic prediction trajectory coordinate system is as follows: Figure 3 As shown, it mainly includes steps S301 to S303:

[0084] S301. Acquire kinematic information of the vehicle, where the kinematic information includes at least vehicle angular velocity, steering wheel angle, and steering gear ratio.

[0085] In practice, the vehicle's kinematic information can be obtained through the vehicle's onboard system.

[0086] S302: Obtain the vehicle's turning radius based on the kinematic information.

[0087] The turning radius of the vehicle, also known as the turning radius of the vehicle, is calculated based on the angular velocity of the vehicle, the steering wheel angle, and the steering gear ratio.

[0088] Specifically, the vehicle's turning radius can be express.

[0089] S303 . Perform fitting based on the vehicle's own turning radius to obtain a kinematic prediction trajectory curve of the vehicle, and obtain a kinematic prediction trajectory coordinate system of the vehicle based on the kinematic prediction trajectory curve of the vehicle.

[0090] In this application, the lane line prediction trajectory coordinate system specifically refers to the coordinate system related to the vehicle and the lane line, which is used to accurately describe the position relationship of the vehicle relative to the lane line.

[0091] In some embodiments, the generation process of the lane line prediction trajectory coordinate system is as follows: Figure 4 As shown, it mainly includes steps S401 and S402:

[0092] S401. Determine lane line information of the vehicle in the vehicle coordinate system, where the lane line information includes at least: lane line lateral distance, lane line slope, lane line curvature, and lane line curvature change rate.

[0093] Among them, in the vehicle coordinate system, the road line lateral distance represents the distance between the road line and the vehicle camera installation position in the vehicle coordinate system. The absolute distance in the direction, the slope of the road line represents the distance of the road line relative to the vehicle in the vehicle coordinate system. The slope of the direction, the road curvature indicates the degree of curvature of the road at a certain point, and the road curvature change rate indicates the change of curvature of the road at different positions.

[0094] In practice, the vehicle's onboard camera can be used to obtain the vehicle's lane line information in the onboard camera coordinate system, and then the lane line information in the onboard camera coordinate system can be converted into a coordinate system to obtain the vehicle's lane line information in the vehicle coordinate system.

[0095] Specifically, the horizontal distance of the road line can be Indicates that the slope of the line can be used Indicates that the road curvature can be used Indicates that the rate of change of road curvature can be used express.

[0096] S402 . Perform fitting based on the lane line information of the vehicle to obtain a lane line prediction trajectory curve of the vehicle, and obtain a lane line prediction trajectory coordinate system of the vehicle based on the lane line prediction trajectory curve of the vehicle.

[0097] In practical applications, the vehicle lane line prediction trajectory curve is generally a cubic polynomial curve, which is used to represent the lateral distance With longitudinal distance Changes:

[0098] ;

[0099] The coefficients in this curve 、 、 、 The initial setting is 0, corresponding to the above 、 、 、 .

[0100] When the quality of the left and right lane lines detected by the on-board camera is very low, it is considered that the lane line in the current frame does not meet the requirements, that is, the vehicle does not meet the lane line prediction trajectory coordinate system conversion requirements, and the four coefficients in the curve are not assigned, that is, the vehicle has no lane line trajectory.

[0101] When the left lane and right lane quality detected by the vehicle camera are both high, 、 、 、 Assigned as the average value of the corresponding coefficients of the road lines on both sides, the corresponding coefficients of the road lines are provided by the vehicle-mounted camera. For example, Left lane marking , Right lane line , .

[0102] If the left lane detected by the onboard camera is of high quality and the right lane is of low quality, 、 、 、 Assign the corresponding coefficient to the left lane; if the onboard camera detects that the right lane has high quality and the left lane has low quality, 、 、 、 Assign the corresponding coefficient to the right lane.

[0103] In summary, the coordinate system conversion relationship in this application is as follows: In the vehicle coordinate system, the vertical coordinate of the obstacle can be expressed as , the horizontal axis is represented by In the lane line prediction trajectory coordinate system, the obstacle ordinate can be expressed as , the horizontal axis is represented by . 、 and 、 The conversion relationship is:

[0104] ;

[0105] .

[0106] In the kinematic prediction trajectory coordinate system, the obstacle ordinate can be expressed as , the horizontal axis is represented by , the turning radius of the vehicle is expressed as . 、 and 、 The conversion relationship is:

[0107] ;

[0108] ;

[0109] .

[0110] It is worth noting that, combined with Figure 5 ,When the vehicle is in a driving state, there are generally two predicted trajectory curves, namely the kinematic prediction trajectory curve (the blue dotted line in the figure) and the lane line prediction trajectory curve (the red dotted line in the figure).

[0111] S103: Generate a drivable boundary of the vehicle based on the obstacle information coordinate system conversion result.

[0112] In practical applications, since the obstacle information coordinate system conversion result includes obstacle information in at least one coordinate system, determining which coordinate system's obstacle information is used as the basis for generating the vehicle's drivable boundary is a key step. Specifically, the obstacle information coordinate system conversion result can be combined with the RANSAC (Random Sample Consensus) algorithm to generate the vehicle's drivable boundary. The detailed process is as follows:

[0113] S501: Determine whether the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal.

[0114] In practice, the RANSAC algorithm can be used to determine the obstacle seed points of each coordinate system in the obstacle information coordinate system transformation result; the seed points represent the observation data that can be used for the RANSAC algorithm, that is, the horizontal and vertical coordinates of the obstacle.

[0115] Taking a multi-vehicle stationary scene as an example, if there is a stationary target only on the left side of the vehicle, the stationary target on the left side of the vehicle is used as the seed point, that is, the obstacle on the left side of the coordinate system is used as the obstacle seed point of the coordinate system; if there is a stationary target only on the right side of the vehicle, the stationary targets on both sides of the vehicle are used as seed points, that is, the obstacle on the right side of the coordinate system is used as the obstacle seed point of the coordinate system; if there are stationary targets on both sides of the vehicle, the stationary targets on the side with more stationary targets are used as seed points, that is, the obstacles on the side with more obstacles in the coordinate system are used as obstacle seed points of the coordinate system.

[0116] It should be noted that after determining the obstacle seed points of each coordinate system in the obstacle information coordinate system conversion result, it can be judged whether the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal based on the quantitative relationship of the obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result.

[0117] If it is determined that the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is unequal, step S502 may be executed; if it is determined that the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal, step S503 may be executed.

[0118] S502 : Generate a drivable boundary of the vehicle according to the obstacle seed points in the coordinate system with the largest number of obstacle seed points in the obstacle information coordinate system conversion result.

[0119] In practical applications, if it is determined that the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is unequal, the vehicle's drivable boundary can be generated based on the obstacle seed points in the coordinate system with the largest number of obstacle seed points in the obstacle information coordinate system conversion result.

[0120] S503 : Generate a drivable boundary of the vehicle according to the coordinate system priority order and the obstacle seed point in the coordinate system with the highest priority in the obstacle information coordinate system conversion result.

[0121] Among them, the priority order of the coordinate systems is: lane line prediction trajectory coordinate system > kinematics prediction trajectory coordinate system > vehicle coordinate system.

[0122] In practical applications, if the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is determined to be equal, the vehicle's drivable boundary can be generated based on the obstacle seed points in the coordinate system with the highest priority in the obstacle information coordinate system conversion result, in the order of lane line prediction trajectory coordinate system > kinematic prediction trajectory coordinate system > vehicle coordinate system.

[0123] Exemplary:

[0124] ① Assume that the obstacle information coordinate system conversion result includes: obstacle information in the ego-vehicle coordinate system, obstacle information in the vehicle's lane line prediction trajectory coordinate system, and obstacle information in the vehicle's kinematic prediction trajectory coordinate system, and the number of obstacle seed points in each coordinate system is equal. According to the coordinate system priority order of lane line prediction trajectory coordinate system > kinematic prediction trajectory coordinate system > ego-vehicle coordinate system, the coordinate system with the highest priority is the lane line prediction trajectory coordinate system. The vehicle's drivable boundary can be generated based on the obstacle seed points in the lane line prediction trajectory coordinate system.

[0125] ② Assuming that the obstacle information coordinate system conversion result includes: obstacle information in the ego-vehicle coordinate system and obstacle information in the vehicle's lane line prediction trajectory coordinate system, and the number of obstacle seed points in each coordinate system is equal, according to the coordinate system priority order of lane line prediction trajectory coordinate system > kinematic prediction trajectory coordinate system > ego-vehicle coordinate system, the coordinate system with the highest priority is the lane line prediction trajectory coordinate system. The vehicle's drivable boundary can be generated based on the obstacle seed points in the lane line prediction trajectory coordinate system.

[0126] ③ Assuming that the obstacle information coordinate system conversion result includes: obstacle information in the ego-vehicle coordinate system and obstacle information in the vehicle's kinematically predicted trajectory coordinate system, and the number of obstacle seed points in each coordinate system is equal, according to the coordinate system priority order of lane line prediction trajectory coordinate system > kinematic prediction trajectory coordinate system > ego-vehicle coordinate system, the coordinate system with the highest priority is the kinematic prediction trajectory coordinate system. The vehicle's drivable boundary can be generated based on the obstacle seed points in the kinematic prediction trajectory coordinate system.

[0127] In some embodiments, the specific process of generating the vehicle's drivable boundary based on the obstacle seed points in the corresponding coordinate system is as follows, mainly including steps S601 to S603:

[0128] In practice, the corresponding coordinate system is the coordinate system used to generate the vehicle's drivable boundary. When the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is unequal, the corresponding coordinate system is the coordinate system with the largest number of obstacle seed points in the obstacle information coordinate system conversion result. When the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal, the corresponding coordinate system is the coordinate system with the highest priority in the obstacle information coordinate system conversion result.

[0129] S601: Determine the inner point of the vehicle in the obstacle in the corresponding coordinate system according to the seed point of the obstacle in the corresponding coordinate system.

[0130] In this application, the obstacle interior points can be used as RANSAC algorithm interior points.

[0131] In some embodiments, the specific execution process of step S601, determining the point inside the obstacle in the corresponding coordinate system based on the obstacle seed point in the corresponding coordinate system, is as follows, mainly including steps S701 to S704:

[0132] S701: Generate a fitting curve of the obstacle seed points of the vehicle in the corresponding coordinate system according to the obstacle seed points in the corresponding coordinate system.

[0133] In practice, the obstacle species points in the corresponding coordinate system can be fitted to generate a fitting curve of the obstacle species points of the vehicle in the corresponding coordinate system.

[0134] Specific fitting methods can be found in the prior art, such as fitting using the least squares method, which are all within the scope of protection of this application.

[0135] S702: Determine the horizontal coordinate of the fitting curve of each obstacle seed point of the vehicle in the corresponding coordinate system according to the obstacle seed point fitting curve.

[0136] In practice, the ordinate of each obstacle species point in the corresponding coordinate system can be input into the obstacle species point fitting curve to obtain the abscissa of the fitting curve of the obstacle species point.

[0137] S703 : For each obstacle seed point of the vehicle in the corresponding coordinate system, obtain its lateral distance error according to its coordinate system abscissa and the fitting curve abscissa.

[0138] The coordinate system abscissa of the obstacle seed point refers to the abscissa corresponding to the obstacle seed point in the corresponding coordinate system.

[0139] In practice, the horizontal distance error of each obstacle seed point can be obtained by subtracting the horizontal coordinate of the coordinate system from the horizontal coordinate of the fitting curve.

[0140] S704: Taking the obstacle seed point whose lateral distance error is less than the preset lateral distance error as the obstacle interior point of the vehicle in the corresponding coordinate system.

[0141] In practice, after determining the lateral distance errors of each obstacle seed point under the corresponding coordinate system, the obstacle seed point with a lateral distance error less than the preset lateral distance error can be used as the obstacle interior point of the vehicle in the corresponding coordinate system.

[0142] Among them, the specific value of the preset lateral distance error can be determined based on the actual problem scenario and big data screening and comprehensiveness, and is within the scope of protection of this application.

[0143] S602: Determine whether the number of points within the obstacle of the vehicle in the corresponding coordinate system is greater than or equal to a preset number and whether the quadratic term coefficient of the corresponding cubic polynomial curve is less than a preset quadratic term coefficient.

[0144] If it is determined that the number of points inside the obstacle of the vehicle in the corresponding coordinate system is greater than or equal to the preset number, and the quadratic term coefficient of the corresponding cubic polynomial curve is less than the preset quadratic term coefficient, step S603 can be executed. Otherwise, the RANSAC algorithm is continued to be used for iterative calculation until the number of points inside the obstacle of the vehicle in the corresponding coordinate system is greater than or equal to the preset number and the quadratic term coefficient of the corresponding cubic polynomial curve is less than the preset quadratic term coefficient.

[0145] Among them, the specific value of the preset number can be determined according to the application environment and user needs. For example, it can be any positive integer, which is within the protection scope of this application; and the specific value of the preset quadratic term coefficient can be determined based on the actual scenario and big data screening.

[0146] In practice, a corresponding cubic polynomial curve can be fitted based on the vehicle's obstacle interior points in the corresponding coordinate system, and then a determination can be made as to whether the quadratic term coefficient of the fitted cubic polynomial curve is less than a preset quadratic term coefficient. If so, a determination can be made as to whether the number of the vehicle's obstacle interior points in the corresponding coordinate system is greater than or equal to a preset number. If so, the obstacle interior point of the vehicle in the corresponding coordinate system is determined as the target obstacle interior point. Of course, a determination can be made as to whether the number of the vehicle's obstacle interior points in the corresponding coordinate system is greater than or equal to a preset number. If so, a determination can be made as to whether the quadratic term coefficient of the fitted cubic polynomial curve is less than the preset quadratic term coefficient.

[0147] S603: Taking the obstacle interior point of the vehicle in the corresponding coordinate system as the target obstacle interior point, and generating the vehicle's drivable boundary based on the target obstacle interior point.

[0148] In practice, when the number of the vehicle's obstacle interior points in the corresponding coordinate system is greater than or equal to a preset number and the quadratic term coefficient of the corresponding cubic polynomial curve is less than the preset quadratic term coefficient, the vehicle's obstacle interior points in the corresponding coordinate system can be used as target obstacle interior points, and the vehicle's drivable boundary is generated based on the target obstacle interior points.

[0149] Specifically, the vehicle's drivable boundary can be generated based on the horizontal and vertical coordinates of the target obstacle's points. Alternatively, the vehicle's drivable boundary can be generated based on the ID of the target obstacle's points. The ID is used to distinguish different objects. In a multi-vehicle stationary scene, the ID of a target remains unchanged from the moment it appears to the moment it moves.

[0150] For example, Figure 6 As shown in the figure, if the target obstacle interior point is the red dot in the figure, the red dotted line is the drivable boundary of the vehicle.

[0151] Based on the above principles, the method for generating a vehicle's drivable boundary provided in this embodiment includes: obtaining obstacle information of the vehicle in the vehicle-mounted camera coordinate system through the vehicle's on-board camera, where the vehicle has at least three obstacles, and the obstacle information includes at least the horizontal and vertical distances of the obstacles; performing a coordinate system conversion on the vehicle's obstacle information in the vehicle-mounted camera coordinate system to obtain a coordinate system conversion result of the vehicle's obstacle information, where the obstacle information coordinate system conversion result includes at least the obstacle information of the vehicle in the vehicle's own coordinate system; generating the vehicle's drivable boundary based on the obstacle information coordinate system conversion result, without relying on map data, and the drivable boundary can be generated based on actual perception data. This solves the problem that existing technical solutions for generating drivable boundaries using high-precision maps are highly dependent on map data. If there is a lag in map information, especially in the case of road reconstruction or new road construction, it is easy for the autonomous driving system to be unable to accurately identify road conditions, thereby affecting driving safety.

[0152] It is worth noting that the inventors have discovered through research that there is still a method of using sensors to collect environmental information, such as cameras, radars, and lidars, and collecting data through neural network model training to generate drivable boundaries or areas, thereby helping the vehicle to perceive road conditions in real time; however, the solution of using sensor data and generating drivable boundaries through neural network model training has high requirements on the system computing power, and a large amount of data is needed for model training to achieve more accurate results. The present application uses the on-board camera to perceive the output obstacle information and the processing of the RANSAC algorithm, which can effectively reduce the amount of calculation for generating drivable boundaries and improve the response speed and processing efficiency of the autonomous driving system.

[0153] It should be noted that since the lateral distance difference between the target obstacle point and the vehicle's drivable boundary is small, the obstacle corresponding to the target obstacle point can be processed accordingly, such as not selecting it as the nearest vehicle on the path. This can effectively solve problems such as misselection of the target causing erroneous braking of the vehicle. The obstacles corresponding to the remaining obstacle points can be left unfiltered for subsequent processing such as target selection. In other words, this application can also improve the vehicle's perception of obstacles in multi-vehicle stationary scenarios, avoiding misselection of obstacles with no collision risk as the nearest vehicle on the path, which can lead to erroneous braking of the vehicle, thereby improving driving safety.

[0154] Optionally, another embodiment of the present application further provides a vehicle drivable boundary generating device, see Figure 7 , the device comprises:

[0155] An acquisition unit 101 is configured to acquire obstacle information of the vehicle in a vehicle-mounted camera coordinate system using the vehicle-mounted camera. The vehicle is located near at least three obstacles, and the obstacle information includes at least the horizontal and vertical distances of the obstacles.

[0156] The conversion unit 102 is configured to perform coordinate system conversion on the vehicle's obstacle information in the vehicle-mounted camera coordinate system to obtain a vehicle obstacle information coordinate system conversion result, wherein the obstacle information coordinate system conversion result includes at least the vehicle's obstacle information in the vehicle coordinate system and the vehicle's obstacle information in the kinematically predicted trajectory coordinate system;

[0157] The generating unit 103 is configured to generate a drivable boundary of the vehicle according to the obstacle information coordinate system conversion result.

[0158] In some embodiments, the conversion unit 102 is used to perform coordinate system conversion on the obstacle information of the vehicle in the vehicle-mounted camera coordinate system to obtain the vehicle obstacle information coordinate system conversion result, specifically for:

[0159] The obstacle information of the vehicle in the onboard camera coordinate system is converted into the vehicle coordinate system to obtain the obstacle information of the vehicle in the vehicle coordinate system;

[0160] Determine whether the vehicle meets the lane line prediction trajectory coordinate system conversion requirements;

[0161] If the vehicle meets the lane line prediction trajectory coordinate system conversion requirements, then the obstacle information of the vehicle in the ego vehicle coordinate system is converted into the lane line prediction trajectory coordinate system and the kinematic prediction trajectory coordinate system, respectively, to obtain the obstacle information of the vehicle in the lane line prediction trajectory coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system, and the obstacle information of the vehicle in the ego vehicle coordinate system, the obstacle information of the vehicle in the lane line prediction trajectory coordinate system, and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system are used as the vehicle's obstacle information coordinate conversion result;

[0162] If the vehicle does not meet the lane line prediction trajectory coordinate system conversion requirements, the obstacle information of the vehicle in the ego vehicle coordinate system is converted into the kinematic prediction trajectory coordinate system to obtain the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system, and the obstacle information of the vehicle in the ego vehicle coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system are used as the vehicle's obstacle information coordinate conversion results.

[0163] In some embodiments, the vehicle meets the lane line prediction trajectory coordinate system conversion requirements, including:

[0164] The vehicle's lane mass is greater than the preset lane mass.

[0165] In some embodiments, the vehicle drivable boundary generating device further includes:

[0166] A lane line information determination unit is used to determine the lane line information of the vehicle in the vehicle coordinate system, where the lane line information includes at least: lane line lateral distance, lane line slope, lane line curvature, and lane line curvature change rate;

[0167] A lane line prediction trajectory coordinate system generating unit is used to fit the lane line information of the vehicle in the vehicle coordinate system to obtain the vehicle's lane line prediction trajectory curve, and obtain the vehicle's lane line prediction trajectory coordinate system based on the vehicle's lane line prediction trajectory curve;

[0168] an acquisition unit, configured to acquire kinematic information of the vehicle, the kinematic information including at least: vehicle angular velocity, steering wheel angle, and steering gear ratio;

[0169] a turning radius determination unit, configured to obtain the vehicle's own turning radius based on kinematic information;

[0170] The kinematic prediction trajectory coordinate system generating unit is used to perform fitting according to the vehicle's own vehicle turning radius to obtain the vehicle's kinematic prediction trajectory curve, and obtain the vehicle's kinematic prediction trajectory coordinate system based on the vehicle's kinematic prediction trajectory curve.

[0171] In some embodiments, when the generating unit 103 is used to generate the drivable boundary of the vehicle according to the obstacle information coordinate system conversion result, it is specifically used to:

[0172] Determine whether the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal;

[0173] If it is determined that the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is unequal, the vehicle's drivable boundary is generated based on the obstacle seed points in the coordinate system with the largest number of obstacle seed points in the obstacle information coordinate system conversion result;

[0174] If it is determined that the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal, then the vehicle's drivable boundary is generated based on the obstacle seed points in the coordinate system with the highest priority in the obstacle information coordinate system conversion result according to the coordinate system priority order;

[0175] Among them, the priority order of the coordinate systems is: lane line prediction trajectory coordinate system > kinematics prediction trajectory coordinate system > vehicle coordinate system.

[0176] In some embodiments, generating a drivable boundary of a vehicle based on obstacle seed points in a corresponding coordinate system includes:

[0177] According to the seed points of the obstacle in the corresponding coordinate system, determine the point inside the obstacle of the vehicle in the corresponding coordinate system;

[0178] Determining whether the number of points within the obstacle of the vehicle in the corresponding coordinate system is greater than or equal to a preset number and whether the quadratic term coefficient of the corresponding cubic polynomial curve is less than a preset quadratic term coefficient;

[0179] If it is determined that the number of the vehicle's obstacle interior points in the corresponding coordinate system is greater than or equal to a preset number, and the quadratic term coefficient of the corresponding cubic polynomial curve is less than the preset quadratic term coefficient, the vehicle's obstacle interior point in the corresponding coordinate system is used as the target obstacle interior point, and the vehicle's drivable boundary is generated based on the target obstacle interior point.

[0180] In some embodiments, determining the point inside the obstacle of the vehicle in the corresponding coordinate system based on the obstacle seed point in the corresponding coordinate system includes:

[0181] Generate a fitting curve of the obstacle seed points of the vehicle in the corresponding coordinate system according to the obstacle seed points in the corresponding coordinate system;

[0182] According to the obstacle seed point fitting curve, determine the horizontal coordinate of the fitting curve of each obstacle seed point of the vehicle in the corresponding coordinate system;

[0183] For each obstacle seed point of the vehicle in the corresponding coordinate system, its lateral distance error is obtained according to its coordinate system abscissa and the fitting curve abscissa.

[0184] The obstacle seed point with a lateral distance error less than the preset lateral distance error is regarded as the obstacle interior point of the vehicle in the corresponding coordinate system.

[0185] In the vehicle drivable boundary generation device provided in this embodiment, an acquisition unit 101 is used to obtain obstacle information of the vehicle in the vehicle-mounted camera coordinate system through the vehicle's on-board camera. The vehicle has at least three obstacles, and the obstacle information includes at least the horizontal and vertical distances of the obstacles. A conversion unit 102 is used to perform coordinate system conversion on the obstacle information of the vehicle in the vehicle-mounted camera coordinate system to obtain a coordinate system conversion result of the vehicle's obstacle information. The obstacle information coordinate system conversion result includes at least obstacle information of the vehicle in the vehicle coordinate system and obstacle information of the vehicle in the kinematic prediction trajectory coordinate system. A generation unit 103 is used to generate the vehicle's drivable boundary based on the obstacle information coordinate system conversion result. The drivable boundary can be generated based on actual perception data without relying on map data. This solves the problem that existing technical solutions for generating drivable boundaries using high-precision maps are highly dependent on map data. If there is a lag in map information, especially in the case of road reconstruction or new road construction, it is easy for the automatic driving system to be unable to accurately identify road conditions, thereby affecting driving safety.

[0186] It should be noted that, for the relevant description of each unit in the vehicle drivable boundary generating device, please refer to the corresponding method embodiment mentioned above, and no further details will be given here.

[0187] Optionally, another embodiment of the present application further provides a computer storage medium for storing a computer program. When the computer program is executed, it is specifically used to implement the vehicle drivable boundary generation method provided in any embodiment of the present application.

[0188] It should be noted that, for the relevant description of the method for generating the vehicle drivable boundary, please refer to the above embodiment and will not be repeated here.

[0189] Optionally, another embodiment of the present application further provides an electronic device, such as Figure 7 As shown, the electronic device includes a memory 601 and a processor 602 .

[0190] The memory 601 is used to store computer programs;

[0191] The processor 602 is used to execute a computer program, specifically to implement the vehicle drivable boundary generation method provided in any embodiment of the present application.

[0192] It should be noted that, for the relevant description of the method for generating the vehicle drivable boundary, reference can also be made to the above embodiment, which will not be repeated here.

[0193] The features described in the various embodiments of this specification may be interchanged or combined. Similar or identical parts between the various embodiments may be referenced to each other. Each embodiment focuses on the differences from other embodiments. In particular, since system or system embodiments are generally similar to method embodiments, their descriptions are relatively simplified. For relevant details, reference may be made to the description of the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network elements. Some or all of these modules may be selected based on actual needs to achieve the objectives of the present embodiments. Persons of ordinary skill in the art will be able to understand and implement these embodiments without inventive effort. Professionals will further appreciate that the units and algorithmic steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered as exceeding the scope of the present invention.

[0194] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0195] It should also be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

Claims

1. A method for generating a vehicle drivable boundary, characterized in that: include: Obtaining obstacle information of the vehicle in a coordinate system of the vehicle-mounted camera through the vehicle-mounted camera, wherein there are at least three obstacles in front of the vehicle, and the obstacle information includes at least the horizontal and vertical distances of the obstacles; performing a coordinate system conversion on the obstacle information of the vehicle in the onboard camera coordinate system to obtain a coordinate system conversion result of the obstacle information of the vehicle, wherein the obstacle information coordinate system conversion result includes at least the obstacle information of the vehicle in the ego-vehicle coordinate system and the obstacle information of the vehicle in the kinematically predicted trajectory coordinate system; The drivable boundary of the vehicle is generated according to the obstacle information coordinate system conversion result.

2. The method for generating a vehicle drivable boundary according to claim 1, characterized in that: Performing coordinate system conversion on the obstacle information of the vehicle in the onboard camera coordinate system to obtain a coordinate conversion result of the obstacle information of the vehicle, including: Performing a self-vehicle coordinate system conversion on the obstacle information of the vehicle in the vehicle-mounted camera coordinate system to obtain the obstacle information of the vehicle in the self-vehicle coordinate system; Determining whether the vehicle meets the lane line prediction trajectory coordinate system conversion requirements; If the vehicle meets the lane line prediction trajectory coordinate system conversion requirements, then the obstacle information of the vehicle in the ego vehicle coordinate system is respectively converted into the lane line prediction trajectory coordinate system and the kinematic prediction trajectory coordinate system to obtain the obstacle information of the vehicle in the lane line prediction trajectory coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system, and the obstacle information of the vehicle in the ego vehicle coordinate system, the obstacle information of the vehicle in the lane line prediction trajectory coordinate system, and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system are used as the obstacle information coordinate conversion result of the vehicle; If the vehicle does not meet the lane line prediction trajectory coordinate system conversion requirements, the obstacle information of the vehicle in the ego vehicle coordinate system is converted into the kinematic prediction trajectory coordinate system to obtain the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system, and the obstacle information of the vehicle in the ego vehicle coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system are used as the obstacle information coordinate conversion result of the vehicle.

3. The method for generating a vehicle drivable boundary according to claim 2, wherein: The vehicle meets the lane line prediction trajectory coordinate system conversion requirements, including: The road line mass of the vehicle is greater than a preset road line mass.

4. The method for generating a vehicle drivable boundary according to claim 2, wherein: The process of generating the lane line prediction trajectory coordinate system includes: Determine lane line information of the vehicle in the vehicle coordinate system, wherein the lane line information includes at least: lane line lateral distance, lane line slope, lane line curvature, and lane line curvature change rate; Fitting the lane line information of the vehicle in the vehicle coordinate system to obtain a lane line prediction trajectory curve of the vehicle, and obtaining a lane line prediction trajectory coordinate system of the vehicle based on the lane line prediction trajectory curve of the vehicle; The process of generating the kinematic prediction trajectory coordinate system includes: Acquiring kinematic information of the vehicle, the kinematic information including at least: vehicle angular velocity, steering wheel angle, and steering gear ratio; Obtaining a turning radius of the vehicle according to the kinematic information; Fitting is performed according to the vehicle's own turning radius to obtain a kinematic prediction trajectory curve of the vehicle, and based on the vehicle's kinematic prediction trajectory curve, a kinematic prediction trajectory coordinate system of the vehicle is obtained.

5. The method for generating a vehicle drivable boundary according to claim 1, characterized in that: Generating a drivable boundary of the vehicle according to the obstacle information coordinate system conversion result, including: Determining whether the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal; If it is determined that the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is unequal, generating a drivable boundary of the vehicle based on the obstacle seed points in the coordinate system having the largest number of obstacle seed points in the obstacle information coordinate system conversion result; If it is determined that the number of obstacle seed points in each coordinate system in the obstacle information coordinate system conversion result is equal, generating the drivable boundary of the vehicle based on the obstacle seed points in the coordinate system with the highest priority in the obstacle information coordinate system conversion result in accordance with the coordinate system priority order; The priority order of the coordinate systems is: lane line prediction trajectory coordinate system > kinematics prediction trajectory coordinate system > vehicle coordinate system.

6. The method for generating a vehicle drivable boundary according to claim 5, characterized in that: Generating a drivable boundary of the vehicle according to the obstacle seed points in the corresponding coordinate system includes: Determining the inner point of the vehicle in the obstacle in the corresponding coordinate system according to the seed point of the obstacle in the corresponding coordinate system; respectively determining whether the number of points within the obstacle of the vehicle in the corresponding coordinate system is greater than or equal to a preset number and whether the quadratic term coefficient of the corresponding cubic polynomial curve is less than a preset quadratic term coefficient; If it is determined that the number of obstacle interior points of the vehicle in the corresponding coordinate system is greater than or equal to a preset number, and the quadratic term coefficient of the corresponding cubic polynomial curve is less than the preset quadratic term coefficient, the obstacle interior point of the vehicle in the corresponding coordinate system is used as the target obstacle interior point, and the drivable boundary of the vehicle is generated based on the target obstacle interior point.

7. The method for generating a vehicle drivable boundary according to claim 6, wherein: Determining the inner point of the vehicle in the obstacle in the corresponding coordinate system according to the obstacle seed point in the corresponding coordinate system includes: Generating a fitting curve of the obstacle seed points of the vehicle in the corresponding coordinate system according to the obstacle seed points in the corresponding coordinate system; Determining the horizontal coordinate of the fitting curve of each obstacle seed point of the vehicle in the corresponding coordinate system according to the obstacle seed point fitting curve; For each obstacle seed point of the vehicle in the corresponding coordinate system, obtain its lateral distance error according to its coordinate system abscissa and the fitting curve abscissa; The obstacle seed point whose lateral distance error is less than the preset lateral distance error is used as the obstacle interior point of the vehicle in the corresponding coordinate system.

8. A vehicle drivable boundary generating device, characterized in that: include: an acquisition unit, configured to acquire obstacle information of the vehicle in a vehicle-mounted camera coordinate system through a vehicle-mounted camera of the vehicle, wherein there are at least three obstacles in front of the vehicle, and the obstacle information includes at least the horizontal and vertical distances of the obstacles; a conversion unit, configured to perform coordinate system conversion on the obstacle information of the vehicle in the onboard camera coordinate system to obtain a coordinate system conversion result of the obstacle information of the vehicle, wherein the obstacle information coordinate system conversion result includes at least the obstacle information of the vehicle in the ego-vehicle coordinate system and the obstacle information of the vehicle in the kinematic prediction trajectory coordinate system; A generating unit is used to generate a drivable boundary of the vehicle according to the obstacle information coordinate system conversion result.

9. An electronic device, characterized in that: include: memory and processor; Wherein, the memory is used to store computer programs; The processor is used to execute the computer program, specifically to implement the vehicle drivable boundary generation method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that Used to store a computer program, which, when executed, is specifically used to implement the vehicle drivable boundary generation method as described in any one of claims 1 to 7.

Images