WO2023284859A1 - 路径检测方法、装置、汽车及存储介质 - Google Patents

路径检测方法、装置、汽车及存储介质 Download PDF

Info

Publication number
WO2023284859A1
WO2023284859A1 PCT/CN2022/105985 CN2022105985W WO2023284859A1 WO 2023284859 A1 WO2023284859 A1 WO 2023284859A1 CN 2022105985 W CN2022105985 W CN 2022105985W WO 2023284859 A1 WO2023284859 A1 WO 2023284859A1
Authority
WO
WIPO (PCT)
Prior art keywords
path
planned path
planned
curve
detection
Prior art date
Application number
PCT/CN2022/105985
Other languages
English (en)
French (fr)
Inventor
张超昱
赵季楠
赵永正
陈集辉
李弼超
Original Assignee
广州小鹏自动驾驶科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广州小鹏自动驾驶科技有限公司 filed Critical 广州小鹏自动驾驶科技有限公司
Publication of WO2023284859A1 publication Critical patent/WO2023284859A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/53—Road markings, e.g. lane marker or crosswalk

Definitions

  • the present application relates to the technical field of automatic driving, in particular to a path detection method, device, vehicle and storage medium.
  • automatic driving includes automatic lane change function.
  • the automatic lane change function it is necessary to detect whether the planned transition path is within the range allowed by the lane line, and it is required not to cross the centerline of the target lane too far, that is to say, it is necessary to detect whether the transition path has a convex hull.
  • the path detection methods in the related art all need to sample on the planned path, and then analyze the relative relationship between the sampling point and the path limit.
  • the method of the related technology has a large amount of calculation and a slow detection speed, which cannot meet the real-time requirements of automatic driving.
  • this application provides a path detection method, device, vehicle and storage medium, which can realize fast detection and screening of planned paths and meet the real-time requirements of automatic driving.
  • the first aspect of the present application provides a path detection method, including:
  • the method also includes:
  • the boundary condition of the planned path satisfying the detection trigger threshold, and the extremum points of the curve of the planned path satisfying the path convex hull constraint condition it is determined that the planned path does not exceed the path limit.
  • the method also includes:
  • the boundary condition of the planned path satisfying the detection trigger threshold, and the extremum points of the curve of the planned path do not satisfy the path convex hull constraint condition it is determined that the planned path exceeds the path limit.
  • the acquiring the planned path and the boundary conditions of the planned path includes:
  • boundary conditions of the planned path are obtained, where the boundary conditions include heading and curvature of a starting point.
  • the boundary condition of the planned path does not meet the detection trigger threshold, including:
  • the boundary conditions of the planned path satisfy the detection trigger threshold including:
  • the extremum points of the curve of the planned path satisfy the path convex hull restriction conditions, including:
  • the ymax is greater than D0
  • the ymin is less than -D1
  • the extremum points of the curve of the planned path do not meet the path convex hull restriction conditions, including:
  • the extreme value of the extreme point is determined in the following manner:
  • the second aspect of the present application provides a path detection device, including:
  • a path acquisition module configured to acquire a planned path and boundary conditions of the planned path, wherein the planned path uses the target reference lane centerline as a reference line;
  • a path detection module configured to compare the boundary conditions of the planned path with a detection trigger threshold, and determine that the planned path does not exceed the detection trigger threshold according to that the boundary conditions of the planned path obtained by the path acquisition module do not meet the detection trigger threshold limit.
  • the path detection module includes:
  • a first judging submodule configured to compare the boundary conditions of the planned path with a detection trigger threshold, and judge whether the boundary conditions of the planned path meet the detection trigger threshold;
  • the second judging submodule is used to judge whether the extremum point extremum of the curve of the planned path satisfies the restriction condition of the path convex hull;
  • the first detection submodule is configured to determine that the planned path does not exceed the path limit according to that the boundary condition of the planned path does not meet the detection trigger threshold;
  • the second detection submodule determines that the planned path does not exceed the path limit according to that the boundary condition of the planned path satisfies the detection trigger threshold, and the extremum points of the curve of the planned path meet the path convex hull restriction condition .
  • the path detection module further includes:
  • the third detection submodule is configured to determine the plan according to that the boundary condition of the planned path satisfies the detection trigger threshold, and the extremum points of the curve of the planned path do not satisfy the restriction condition of the convex hull of the path. Path exceeds path limit.
  • the first detection submodule acquires the heading and curvature of the starting point of the planned path, if the absolute value of the heading and the absolute value of the curvature are less than a set threshold, it determines that the boundary condition of the planned path does not satisfy the detection trigger threshold.
  • the second detection submodule acquires the heading and curvature of the starting point of the planned path, if the absolute value of the heading and the absolute value of the curvature are greater than or equal to a set threshold, then it is determined that the boundary condition of the planned path satisfies Detection trigger threshold.
  • a third aspect of the present application provides an automobile, which includes the path detection device described in any one of the above embodiments.
  • the fourth aspect of the present application provides a non-transitory machine-readable storage medium, on which executable code is stored, and when the executable code is executed by a processor of an electronic device, the processor executes the above-mentioned method.
  • the path detection method provided in this application after obtaining the planned path and the boundary conditions of the planned path, compares the boundary conditions of the planned path with the detection trigger threshold, and according to the fact that the boundary conditions of the planned path do not satisfy the A trigger threshold is detected to determine that the planned path does not exceed the path limit.
  • FIG. 1 is a schematic flow diagram of a path detection method shown in an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a path detection method shown in another embodiment of the present application.
  • Fig. 3 is a schematic flow chart of judging whether the extremum point extremum of the curve of the planned path meets the path convex hull restriction condition in Fig. 2;
  • Fig. 4 is a schematic diagram of a planned path shown in an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a path detection device shown in an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
  • first information may also be called second information, and similarly, second information may also be called first information.
  • second information may also be called first information.
  • a feature defined as “first” and “second” may explicitly or implicitly include one or more of these features.
  • “plurality” means two or more, unless otherwise specifically defined.
  • the path detection methods in related technologies all need to sample on the planned path, and then analyze the relative relationship between the sampling point and the path limit, which requires a large amount of calculation and slow detection speed, which cannot meet the real-time requirements of automatic driving.
  • the present application provides a path detection method, which can realize rapid detection and screening of planned paths and meet the real-time requirements of automatic driving.
  • the path detection method of the embodiment of the present application includes:
  • Step S110 obtaining the planned path and the boundary conditions of the planned path, wherein the planned path uses the centerline of the target reference lane as a reference line.
  • the automatic driving process of the car is the process in which the car automatically drives from the preset starting point of the road to the preset end point. Between the preset start point and the preset end point, multiple passing paths can be formed.
  • Obtaining the planned path in this step may be to obtain the planned path according to the current reference lane centerline and the target reference lane centerline, wherein the planned path uses the target reference lane centerline as the reference line; according to the planned path, the boundary conditions of the planned path are obtained, the boundary conditions Include the heading and curvature of the origin.
  • Step S120 comparing the boundary condition of the planned path with the detection trigger threshold, and determining that the planned path does not exceed the path limit according to that the boundary condition of the planned path does not meet the detection trigger threshold.
  • this step after obtaining the heading and the curvature of the starting point of the planned path, if the absolute value of the heading and the absolute value of the curvature are smaller than a set threshold, it is determined that the boundary condition of the planned path does not meet the detection trigger threshold. Then, according to the boundary condition of the planned path not meeting the detection trigger threshold, it is determined that the planned path does not exceed the path limit.
  • the planned path does not exceed the path limit according to that the boundary condition of the planned path satisfies the detection trigger threshold, and the extremum points of the curve of the planned path satisfy the path convex hull constraint condition.
  • the absolute value of the heading and the absolute value of the curvature are greater than or equal to a set threshold, then it is determined that the boundary condition of the planned path satisfies the detection trigger threshold.
  • the boundary conditions of the planned path are compared with the detection trigger threshold, and the planned path is determined according to the fact that the boundary conditions of the planned path do not meet the detection trigger threshold Path limit not exceeded.
  • the path detection method of the embodiment of the present application including:
  • Step S210 acquiring the planned path and the boundary conditions of the planned path, wherein the planned path uses the centerline of the target reference lane as a reference line.
  • This step may be to obtain the planned path according to the centerline of the current reference lane and the centerline of the target reference lane, and obtain boundary conditions of the planned path according to the planned path.
  • the boundary conditions of the planned path may include the heading and curvature of the starting point of the planned path.
  • the transition path C planned according to the current reference lane centerline A and the target reference lane centerline B, that is, the planned path, is acquired, wherein the planned path uses the target reference lane centerline B as a reference line.
  • the curve planned by the planned path is a polynomial curve of degree n, for example, a polynomial curve of degree 5, and the course and curvature of the end point of the curve are both 0, that is, the first derivative (direction) of the end point of the curve and the second order derivative (curvature) of the end point of the curve are both is 0.
  • the schematic diagram of the planned path is as shown in Figure 4 shown.
  • the planned coordinate system is the SL coordinate system established based on the centerline of the target reference lane, that is, the SL coordinate system uses the centerline of the target reference lane as the reference line, wherein S represents the longitudinal distance (that is, along the The distance in the direction of the centerline of the target reference lane), and L represents the lateral distance (that is, the distance away from the centerline of the target reference lane, that is, the reference line).
  • Step S220 judge whether the boundary condition of the planned path meets the detection trigger threshold, if it meets the detection trigger threshold, go to step S230, if not, go to step S260.
  • the boundary condition of the planned path does not meet the detection trigger threshold, including: after obtaining the course and curvature of the starting point of the planned path, if the absolute value of the course and the absolute value of the curvature are less than the set threshold, it is determined that the boundary condition of the planned path is not The detection trigger threshold is met.
  • the boundary condition of the planned path satisfies the detection trigger threshold, including: after obtaining the course and curvature of the starting point of the planned path, if the absolute value of the course and the absolute value of the curvature are greater than or equal to the set threshold, then determine the boundary condition of the planned path The detection trigger threshold is met.
  • the heading and curvature of the starting point of the planned path are obtained. If the absolute value of the heading and the absolute value of the curvature are both less than the set threshold (for example, 1e-4, that is, 1x0.0001), it means the extreme value of the planned path.
  • the detection trigger threshold is not met, go to step S260 and return the result that the planned path does not exceed the limit; otherwise, the planned path needs to perform convex hull detection and meet the detection trigger threshold, enter Step S230 continues processing.
  • Step S230 determining the extremum point extremum of the curve of the planned path.
  • the calculation method of the position of the extreme point of the curve of the planned path and the size of the extreme point of the extreme point can adopt the following methods:
  • S is the distance between the end point of the curve of the planned path and the starting point in the S direction
  • A (120 ⁇ dy0 ⁇ y0-120 ⁇ dy0 ⁇ y1+64 ⁇ S ⁇ dy0 ⁇ dy0+S3 ⁇ ddy0 ⁇ ddy0+14 ⁇ S2 ⁇ ddy0 ⁇ dy0) ⁇ S3,
  • Step S240 judging whether the extremum points of the curve of the planned path satisfy the path convex hull constraint condition, if the path convex hull constraint condition is met, go to step S260, if not, go to step S250.
  • step S240 it is mainly judged whether the extremum point extremum of the curve of the planned path satisfies the path convex hull restriction condition, the process can be as follows: judge whether the positions xc and xd of the extremum point are within the length range from the starting point to the end point of the curve If it is not within the range, then set its corresponding extremum y c or y d to 0; select the larger one of y c and y d as y max , and the smaller one as y min ; assume a dichotomous One of the target reference lane width is D 0 , and the allowable threshold for the vehicle to cross the center line of the target reference lane is D 1 , then the following judgment is made: if the y0 of the initial position of the extreme point is greater than 0, continue to judge whether y max is greater than D 0 , and judging whether y min is less than -D 1 , if one of the two judging conditions is not satisfied, it is determined
  • Step S250 determining that the planned route exceeds the route limit.
  • This step finally returns the result that the planned path exceeds the path limit.
  • Step S260 determining that the planned route does not exceed the route limit.
  • This step finally returns the result that the planned path does not exceed the path limit.
  • FIG. 3 it is a schematic flow chart of step S240 in FIG. 2 judging whether the extremum points of the curve of the planned path satisfy the restriction condition of the convex hull of the path.
  • the process in Figure 3 includes:
  • Step S310 obtain the ordinate y0 of the initial position of the extreme point of the curve, half of the target reference lane width D0, the limit threshold D1 of the vehicle crossing the centerline of the target reference lane, the extreme value ymax of the first extreme point of the curve, The extreme value ymin of the second extreme point of the curve, where ymax is greater than ymin;
  • Step S320 judging whether y0 is greater than 0, if y0 is greater than 0, proceed to step S330, otherwise, proceed to step S360;
  • Step S330 judge whether ymax is greater than D0, if ymax is greater than D0, enter step S340, otherwise, enter step S380;
  • Step S340 judging whether ymin is less than -D1, if ymin is less than -D1, go to step S350, otherwise, go to step S380;
  • Step S350 determining that the extremum point extremum of the curve of the planned path satisfies the restriction condition of the convex hull of the path;
  • Step S360 judging whether ymin is less than -D0, if ymin is less than -D0, go to step S370, otherwise, go to step S380;
  • Step S370 judging whether ymax is greater than D1, if ymax is greater than D1, return to step S350, otherwise, enter step S380;
  • step S380 it is determined that the extremum point extremum of the curve of the planned path does not satisfy the restriction condition of the convex hull of the path.
  • the path detection method of the embodiment of the present application no longer needs to sample on the planned path and then analyze the relative relationship between the sampling point and the path limit, but to determine the shape of the path, and perform the process according to the comparison between the boundary conditions of the path and the detection trigger threshold. Judgment, and judgment based on the extremum points of the curve of the planned path and the restriction conditions of the convex hull of the path, the calculation is simpler, the result is more accurate, and the detection and screening of the planned path can be quickly realized to meet the real-time requirements of automatic driving.
  • the embodiments of the present application also provide a path detection device, a vehicle, a non-transitory machine-readable storage medium, and corresponding embodiments.
  • FIG. 5 it is a schematic structural diagram of a path detection device shown in an embodiment of the present application.
  • the path detection device 50 provided in the embodiment of the present application includes: a path acquisition module 510 and a path detection module 520 .
  • the path acquisition module 510 is configured to acquire the planned path and the boundary conditions of the planned path, wherein the planned path uses the centerline of the target reference lane as a reference line.
  • the acquisition of the planned path by the path acquisition module 510 may be to obtain the planned path according to the current reference lane centerline and the target reference lane centerline, wherein the planned path uses the target reference lane centerline as the reference line; according to the planned path, the boundary conditions of the planned path are obtained, the Boundary conditions include the heading and curvature of the origin.
  • the path detection module 520 is configured to compare the boundary condition of the planned path with the detection trigger threshold, and determine that the planned path does not exceed the path limit according to that the boundary condition of the planned path does not meet the detection trigger threshold.
  • the path detection module 520 may include: a first judgment submodule 5201 , a second judgment submodule 5202 , a first detection submodule 5203 , a second detection submodule 5204 , and a third detection submodule 5205 .
  • the first judging sub-module 5201 is used to compare the boundary condition of the planned path with the detection trigger threshold, and judge whether the boundary condition of the planned path satisfies the detection trigger threshold;
  • the second judging sub-module 5202 is used to judge whether the extremum point extremum of the curve of the planned path satisfies the restriction condition of the path convex hull;
  • the first detection sub-module 5203 is configured to determine that the planned path does not exceed the path limit according to the fact that the boundary condition of the planned path does not meet the detection trigger threshold;
  • the second detection sub-module 5204 determines that the planned path does not exceed the path limit according to the boundary condition of the planned path meeting the detection trigger threshold, and the extremum points of the curve of the planned path satisfying the path convex hull constraint condition;
  • the third detection sub-module 5205 is configured to determine that the planned path exceeds the path limit according to that the boundary condition of the planned path satisfies the detection trigger threshold, and the extremum points of the curve of the planned path do not meet the constraint condition of the convex hull of the path.
  • the first detection submodule 5203 can determine that the boundary condition of the planned path does not meet the detection trigger threshold if the absolute value of the heading and the absolute value of the curvature are less than the set threshold after acquiring the heading and curvature of the starting point of the planned path.
  • the second detection submodule 5204 may determine that the boundary condition of the planned path satisfies the detection trigger threshold if the absolute value of the heading and the absolute value of the curvature are greater than or equal to the set threshold after acquiring the heading and curvature of the starting point of the planned path.
  • the process for the second detection sub-module 5204 to determine that the extremum points of the curve of the planned path satisfy the path convex hull constraint condition may include:
  • the process that the third detection sub-module 5205 determines that the extremum point extremum of the curve of the planned path does not satisfy the path convex hull constraint condition may include:
  • the extreme value of the above extreme point can be determined in the following manner: according to the parametric equation of the curve of the planned path, the parametric equation of the first-order derivative of the curve is obtained; the parametric equation of the first-order derivative of the curve is solved to obtain the extreme point extremum.
  • the path detection device in the embodiment of the present application after obtaining the planned path, determines that the planned path does not exceed the path limit according to the fact that the boundary condition of the planned path does not meet the detection trigger threshold.
  • the calculation is simpler and the result is more accurate. Accurate, can quickly realize the detection and screening of the planned path, and meet the real-time requirements of automatic driving.
  • An embodiment of the present application further provides a car, and the car in the embodiment of the present application may include the path detection device in any of the foregoing embodiments.
  • the function and structure of the path detection device can refer to the description in FIG. 5 , and will not be repeated here.
  • the present application also provides an electronic device 600 , and the electronic device 600 includes a memory 610 and a processor 620 .
  • Executable codes are stored in the memory 610 , and when the executable codes are executed by the processor 620 , the processor 620 is made to execute the path detection method described in any of the foregoing embodiments.
  • the processor 620 can be a central processing unit (Central Processing Unit, CPU), and can also be other general purpose processors 620, digital signal processors 620 (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC) ), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • the general purpose processor 620 may be a microprocessor 620 or the processor 620 may be any conventional processor 620 or the like.
  • Memory 610 may include various types of storage units, such as system memory, read only memory 610 (ROM), and persistent storage systems.
  • the ROM may store static data or instructions required by the processor 620 or other modules of the computer.
  • the persistent storage system may be a readable and writable storage system.
  • a persistent storage system may be a non-volatile storage device that does not lose stored instructions and data even if the computer is powered off.
  • the permanent storage system adopts a mass storage system (eg, magnetic or optical disk, flash memory) as the permanent storage system.
  • the permanent storage system may be a removable storage device (such as a floppy disk, an optical drive).
  • the system memory can be a readable and writable storage device or a volatile readable and writable storage device, such as dynamic random access memory.
  • System memory may store some or all of the instructions and data that processor 620 needs at runtime.
  • memory 610 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory 610), and magnetic and/or optical disks may also be used.
  • memory 610 may include a readable and/or writable removable storage device, such as a compact disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual-layer DVD-ROM), Blu-ray Disc, Super Density Disc, Flash memory card (such as SD card, min SD card, Micro-SD card, etc.), magnetic floppy disk, etc.
  • a readable and/or writable removable storage device such as a compact disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual-layer DVD-ROM), Blu-ray Disc, Super Density Disc, Flash memory card (such as SD card, min SD card, Micro-SD card, etc.), magnetic floppy disk, etc.
  • Computer-readable storage media do not contain carrier waves and transient electronic signals transmitted by wireless or wire.
  • Executable codes are stored in the memory 610 , and when the executable codes are processed by the processor 620 , the processor 620 may execute part or all of the methods mentioned above.
  • the method according to the present application can also be implemented as a computer program or computer program product, which includes computer program code instructions for executing some or all of the steps in the above-mentioned method of the present application.
  • the present application may also be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium), on which executable code (or computer program, or computer instruction code) is stored. ), when the executable code (or computer program, or computer instruction code) is executed by the processor of the electronic device (or electronic device, server, etc.), causing the processor to perform part or all of the steps of the above-mentioned method according to the present application .

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

一种路径检测方法、装置、汽车及存储介质，该路径检测方法包括：获取规划路径和规划路径的边界条件，其中规划路径使用目标参考车道中心线作为参考线；将规划路径的边界条件与检测触发阈值进行比较，根据规划路径的边界条件不满足检测触发阈值，确定规划路径未超出路径限制。

Description

路径检测方法、装置、汽车及存储介质
本申请要求于2021年07月15日提交国家知识产权局、申请号为202110802322.8、申请名称为“路径检测方法、装置及汽车”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及自动驾驶技术领域，具体涉及一种路径检测方法、装置、汽车及存储介质。
背景技术
目前，汽车自动驾驶技术在不断发展。其中，自动驾驶包括自动变道功能。对于自动变道功能，需要检测规划的过渡路径是否在车道线允许的范围内，而且要求不能越过目标车道中心线太远距离，也就是说，需检测过渡路径是否存在凸包。
相关技术中的路径检测方法，都需要在规划路径上进行采样，然后分析采样点和路径限制的相对关系。然而，相关技术的方法，计算量较大，检测速度慢，满足不了自动驾驶的实时性需求。
发明内容
为解决或部分解决相关技术中存在的问题，本申请提供一种路径检测方法、装置、汽车及存储介质，能够实现对规划路径的快速检测和筛选，满足自动驾驶的实时性需求。
本申请第一方面提供一种路径检测方法，包括：
获取规划路径和所述规划路径的边界条件，其中所述规划路径使用目标参考车道中心线作为参考线；
将所述规划路径的边界条件与检测触发阈值进行比较，根据所述规划路径的边界条件不满足所述检测触发阈值，确定所述规划路径未超出路径限制。
在一实施例中，所述方法还包括：
根据所述规划路径的边界条件满足所述检测触发阈值，且所述规划路径的曲线的极值点极值满足路径凸包限制条件，确定所述规划路径未超出路径限制。
在一实施例中，所述方法还包括：
根据所述规划路径的边界条件满足所述检测触发阈值，且所述规划路径的曲线的极值点极值不满足路径凸包限制条件，确定所述规划路径超出路径限制。
在一实施例中，所述获取规划路径和所述规划路径的边界条件，包括：
根据当前参考车道中心线和目标参考车道中心线得到所述规划路径；
根据所述规划路径，获取所述规划路径的边界条件，所述边界条件包括起点的航向和曲率。
在一实施例中，所述规划路径的边界条件不满足所述检测触发阈值，包括：
在获取所述规划路径的起点的航向和曲率后，如果所述航向的绝对值和所述曲率的绝对值小于设定阈值，则确定所述规划路径的边界条件不满足所述检测触发阈值；或，
所述规划路径的边界条件满足所述检测触发阈值，包括：
在获取所述规划路径的起点的航向和曲率后，如果所述航向的绝对值和所述曲率的绝对值大于或等于设定阈值，则确定所述规划路径的边界条件满足检测所述触发阈值。
在一实施例中，所述规划路径的曲线的极值点极值满足路径凸包限制条件，包括：
当获取所述曲线的极值点的初始位置纵坐标y0、二分之一目标参考车道宽度值D0、车辆越过目标参考车道中心线的极限阈值D1、所述曲线的第一极值点极值ymax、所述曲线的第二极值点极值ymin之后；
在所述y0大于0、ymax大于D0且ymin小于-D1时，确定所述规划路径的曲线的极值点极值满足路径凸包限制条件；或，
在所述y0小于或等于0、ymin小于-D0且ymax大于D1时，确定所述规划路径的曲线的极值点极值满足路径凸包限制条件；
其中所述ymax大于所述ymin。
在一实施例中，所述所述规划路径的曲线的极值点极值不满足路径凸包限制条件，包括：
当获取所述曲线的极值点的初始位置纵坐标y0、二分之一目标参考车道宽度值D0、车辆越过目标参考车道中心线的极限阈值D1、所述曲线的第一极值点极值ymax、所述曲线的第二极值点极值ymin，之后；
在所述y0小于或等于0且ymin大于或等于-D0时，确定所述规划路径的曲线的极值点极值不满足路径凸包限制条件；或，
在所述y0大于0且ymax小于或等于D0时，确定所述规划路径的曲线的极值点极值不满足路径凸包限制条件；或，
在所述y0大于0、ymax大于D0且ymin大于或等于-D1时，确定所述规划路径的曲线的极值点极值不满足路径凸包限制条件；或，
在所述y0小于或等于0、ymin小于-D0且ymax小于或等于D1时，确定所述规划路径的曲线的极值点极值不满足路径凸包限制条件；
其中所述ymax大于所述ymin。
在一实施例中，所述极值点极值按以下方式确定：
根据所述规划路径的曲线的参数方程，得到所述曲线的一阶导数的参数方程；
对所述曲线的一阶导数的参数方程进行求解运算，得到所述极值点极值。
本申请第二方面提供一种路径检测装置，包括：
路径获取模块，用于获取规划路径和所述规划路径的边界条件，其中所述规划路径使用目标参考车道中心线作为参考线；
路径检测模块，用于将所述规划路径的边界条件与检测触发阈值进行比较，根据所述路径获取模块获取的规划路径的边界条件不满足所述检测触发阈值，确定所述规划路径未超出路径限制。
在一实施例中，所述路径检测模块包括：
第一判断子模块，用于将所述规划路径的边界条件与检测触发阈值进行比较，判断所述规划路径的边界条件是否满足所述检测触发阈值；
第二判断子模块，用于判断所述规划路径的曲线的极值点极值是否满足路径凸包限制条件；
第一检测子模块，用于根据所述规划路径的边界条件不满足所述检测触发阈值，确定所述规划路径未超出路径限制；
第二检测子模块，根据所述规划路径的边界条件满足所述检测触发阈值，且所述规划路径的曲线的极值点极值满足路径凸包限制条件，确定所述规划路径未超出路径限制。
在一实施例中，所述路径检测模块还包括：
第三检测子模块，用于根据所述规划路径的边界条件满足所述检测触发阈值，且所述规划路径的曲线的极值点极值不满足所述路径凸包限制条件，确定所述规划路径超出路径限制。
在一实施例中，所述第一检测子模块在获取规划路径的起点的航向和曲率后，如果航向的绝对值和曲率的绝对值小于设定阈值，则确定规划路径的边界条件不满足检测触发阈值。
在一实施例中，所述第二检测子模块在获取规划路径的起点的航向和曲率后，如果航向的绝对值和曲率的绝对值大于或等于设定阈值，则确定规划路径的边界条件满足检测触发阈值。
本申请第三方面提供一种汽车，其包括上述任一实施例所述的路径检测装置。
本申请第四方面提供一种非暂时性机器可读存储介质，其上存储有可执行代码，当所述可执行代码被电子设备的处理器执行时，使所述处理器执行如上所述的方法。
本申请提供的技术方案可以包括以下有益效果：
本申请提供的路径检测方法，在获取规划路径和所述规划路径的边界条件后，是将所述规划路径的边界条件与检测触发阈值进行比较，根据所述规划路径的边界条件不满足所述检测触发阈值，确定所述规划路径未超出路径限制。这样的设计，不再需要在规划路径上采样然后分析采样点和路径限制的相对关系，而是确定路径的形状，根据路径的边界条件与检测触发阈值的比较进行判断，计算更简单，结果更精确，可以快速实现对规划路径的检测和筛选，满足自动驾驶实时性需求。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本申请。
附图说明
通过结合附图对本申请示例性实施方式进行更详细的描述，本申请的上述以及其它目的、特征和优势将变得更加明显，其中，在本申请示例性实施方式中，相同的参考标号通常代表相同部件。
图1是本申请实施例示出的路径检测方法的流程示意图；
图2是本申请另一实施例示出的路径检测方法的流程示意图；
图3是图2中判断规划路径的曲线的极值点极值是否满足路径凸包限制条件的流程示意图；
图4是本申请一实施例示出的规划路径的示意图；
图5是本申请实施例示出的路径检测装置的结构示意图；
图6是本申请实施例示出的电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本申请的实施方式。虽然附图中显示了本申请的实施方式，然而应该理解，可以以各种形式实现本申请而不应被这里阐述的实施方式所限制。相反，提供这些实施方式是为了使本申请更加透彻和完整，并且能够将本申请的范围完整地传达给本领域的技术人员。
在本申请使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本申请。在本申请和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。应当理解，尽管在本申请可能采用术语“第一”、“第二”、“第三”等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本申请范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本申请的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。
相关技术中的路径检测方法，都需要在规划路径上进行采样，然后分 析采样点和路径限制的相对关系，计算量较大，检测速度慢，满足不了自动驾驶的实时性需求。
针对上述问题，本申请提供一种路径检测方法，能够实现对规划路径的快速检测和筛选，满足自动驾驶的实时性需求。
以下结合附图详细描述本申请实施例的技术方案。
参见图1，本申请实施例的路径检测方法，包括：
步骤S110，获取规划路径和规划路径的边界条件，其中规划路径使用目标参考车道中心线作为参考线。
汽车的自动驾驶过程，是汽车从道路的预设起点自动行驶到达预设终点的过程。在预设起点和预设终点之间，可以形成多条通行路径。
该步骤获取规划路径可以是根据当前参考车道中心线和目标参考车道中心线得到规划路径，其中规划路径使用目标参考车道中心线作为参考线；根据规划路径，获取规划路径的边界条件，该边界条件包括起点的航向和曲率。
步骤S120，将所述规划路径的边界条件与检测触发阈值进行比较，根据规划路径的边界条件不满足检测触发阈值，确定规划路径未超出路径限制。
该步骤可以在获取规划路径的起点的航向和曲率后，如果航向的绝对值和曲率的绝对值小于设定阈值，则确定规划路径的边界条件不满足检测触发阈值。然后，根据规划路径的边界条件不满足检测触发阈值，确定规划路径未超出路径限制。
另外，还可以根据规划路径的边界条件满足检测触发阈值，且规划路径的曲线的极值点极值满足路径凸包限制条件，确定规划路径未超出路径限制。其中，可以是在获取规划路径的起点的航向和曲率后，如果航向的绝对值和曲率的绝对值大于或等于设定阈值，则确定规划路径的边界条件满足检测触发阈值。
本申请实施例的路径检测方法，在获取规划路径和规划路径的边界条件后，是将规划路径的边界条件与检测触发阈值进行比较，根据规划路径的边界条件不满足检测触发阈值，确定规划路径未超出路径限制。这样的设计，不再需要在规划路径上采样然后分析采样点和路径限制的相对关系， 而是确定路径的形状，根据路径的边界条件与检测触发阈值的比较进行判断，计算更简单，结果更精确，可以快速实现对规划路径的检测和筛选，满足自动驾驶实时性需求。
为了进一步理解本申请的方法，参见图2，本申请实施例的路径检测方法，包括：
步骤S210，获取规划路径和规划路径的边界条件，其中规划路径使用目标参考车道中心线作为参考线。
该步骤可以是根据当前参考车道中心线和目标参考车道中心线得到规划路径，根据规划路径，获取规划路径的边界条件。规划路径的边界条件可以包括规划路径的起点的航向和曲率。
其中，获取根据当前参考车道中心线A和目标参考车道中心线B规划的过渡路径C也即规划路径，其中，规划路径使用目标参考车道中心线B作为参考线。规划路径所规划的曲线为n次多项式曲线例如为5次多项式曲线，且曲线终点的航向和曲率均为0，即曲线终点的一阶导数(航向)和曲线终点的二阶导数(曲率)均为0。
规划路径的曲线的参数方程为y＝f(x)，y和x即为规划路径的曲线在以目标参考车道中心线B为基准建立的SL坐标系下的坐标，规划路径的示意图如图4所示。
本申请实施例的方案，所规划的坐标系是以目标参考车道中心线为基准建立的SL坐标系，也即SL坐标系使用目标参考车道中心线作为参考线，其中S表示纵向距离(即沿着目标参考车道中心线方向的距离)，L表示横向距离(即偏离目标参考车道中心线即参考线的距离)。
步骤S220，判断规划路径的边界条件是否满足检测触发阈值，如果满足检测触发阈值，进入步骤S230，如果不满足检测触发阈值，进入步骤S260。
其中，规划路径的边界条件不满足检测触发阈值，包括：在获取规划路径的起点的航向和曲率后，如果航向的绝对值和曲率的绝对值小于设定阈值，则确定规划路径的边界条件不满足检测触发阈值。
其中，规划路径的边界条件满足检测触发阈值，包括：在获取规划路径的起点的航向和曲率后，如果航向的绝对值和曲率的绝对值大于或等于 设定阈值，则确定规划路径的边界条件满足检测触发阈值。
也就是说，获取规划路径的起点的航向和曲率，如果航向的绝对值和曲率的绝对值都是小于设定阈值(例如1e-4，即1x0.0001)，则表示该规划路径的极值点接近路径起点，因此该规划路径无需做凸包检测，不满足检测触发阈值，进入步骤S260返回规划路径未超限的结果；否则，该规划路径需要进行凸包检测，满足检测触发阈值，进入步骤S230继续处理。
步骤S230，确定规划路径的曲线的极值点极值。
规划路径的曲线的极值点位置和极值点极值大小的计算方法可以采用以下方式：
(1)根据规划路径的曲线的参数方程y＝f(x)，运算得曲线的一阶导数的参数方程
Figure PCTCN2022105985-appb-000001
(2)求解g(x)＝0，得到y＝f(x)的极值点，由于y＝f(x)是5次多项式，因此其极值点有四个，记为x a,x b,x c,x d，其中它们分别为：
x a＝x b＝S
x c＝(0.2·S 3·a0-0.2·A+0.4·S 2·v0)·B
x d＝(A+S 3·ddy0+2·S 2·dy0)·0.2·B
其中：
[y0,dy0,ddy0]为y＝f(x)的初始条件，[y1,dy1,ddy1]为y＝f(x)的终止条件，S是规划路径的曲线终点相对起点的S方向的距离，
A＝(120·dy0·y0-120·dy0·y1+64·S·dy0·dy0+S 3·ddy0·ddy0+14·S 2·ddy0·dy0)·S 3，
B＝1/(ddy0·S 2+6·dy0·S+12·y0-12·y1)。
(3)前两个极值点x a和x b都位于曲线终点，因此排除在外，只需要考虑x c和x d。通过x c和x d，可以求得其对应的极值点极值的大小分别为：
y c＝f(x c)
y d＝f(x d)
步骤S240，判断规划路径的曲线的极值点极值是否满足路径凸包限制条件，如果满足路径凸包限制条件，进入步骤S260，如果不满足路径凸包限制条件，进入步骤S250。
在步骤S240中，主要判断规划路径的曲线的极值点极值是否满足路径凸包限制条件，过程可以如下：判断极值点的位置x c和x d是否在曲线的起点到终点的长度范围内，若不在范围内，则将其对应的极值y c或y d置为0；选择y c和y d中的较大者设为y max，较小者设为y min；假设二分之一目标参考车道宽度为D 0，车辆越过目标参考车道中心线的允许阈值为D 1，则进行如下判断：若极值点初始位置的纵坐标y0大于0，则继续判断y max是否大于D 0，以及判断y min是否小于-D 1，如果二个判断条件中之一不满足，则确定不满足路径凸包限制条件，最终将返回路径超限的结果，否则确定满足路径凸包限制条件，最终将返回路径未超限的结果；若极值点初始位置的纵坐标y0小于或等于0(即不大于0)，则继续判断y min是否小于-D 0，以及判断y max是否大于D 1，如果二个判断条件中之一不满足，则确定不满足路径凸包限制条件，最终将返回规划路径超限的结果，否则确定满足路径凸包限制条件，最终将返回路径未超限的结果。
步骤S250，确定规划路径超出路径限制。
该步骤最终返回规划路径超出路径限制的结果。
步骤S260，确定规划路径未超出路径限制。
该步骤最终返回规划路径未超出路径限制的结果。
进一步参见图3，是图2中步骤S240判断规划路径的曲线的极值点极值是否满足路径凸包限制条件的流程示意图。图3中的流程包括：
步骤S310，获取曲线的极值点的初始位置纵坐标y0、二分之一目标参考车道宽度值D0、车辆越过目标参考车道中心线的极限阈值D1、曲线的第一极值点极值ymax、曲线的第二极值点极值ymin，其中ymax大于ymin；
步骤S320，判断y0是否大于0，如果y0是大于0，进入步骤S330，否则，进入步骤S360；
步骤S330，判断ymax是否大于D0，如果ymax是大于D0，进入步骤 S340，否则，进入步骤S380；
步骤S340，判断ymin是否小于-D1，如果ymin是小于-D1，进入步骤S350，否则，进入步骤S380；
步骤S350，确定规划路径的曲线的极值点极值满足路径凸包限制条件；
步骤S360，判断ymin是否小于-D0，如果ymin是小于-D0，进入步骤S370，否则，进入步骤S380；
步骤S370，判断ymax是否大于D1，如果ymax是大于D1，返回步骤S350，否则，进入步骤S380；
步骤S380，确定规划路径的曲线的极值点极值不满足路径凸包限制条件。
综上，本申请实施例的路径检测方法，不再需要在规划路径上采样然后分析采样点和路径限制的相对关系，而是确定路径的形状，根据路径的边界条件与检测触发阈值的比较进行判断，及根据规划路径的曲线的极值点极值与路径凸包限制条件进行判断，计算更简单，结果更精确，可以快速实现对规划路径的检测和筛选，满足自动驾驶实时性需求。
与前述应用功能实现方法实施例相对应，本申请实施例还提供了一种路径检测装置、汽车、非暂时性机器可读存储介质及相应的实施例。
参见图5，是本申请实施例示出的路径检测装置的结构示意图。
本申请实施例提供的路径检测装置50，其包括：路径获取模块510、路径检测模块520。
路径获取模块510，用于获取规划路径和规划路径的边界条件，其中规划路径使用目标参考车道中心线作为参考线。路径获取模块510获取规划路径可以是根据当前参考车道中心线和目标参考车道中心线得到规划路径，其中规划路径使用目标参考车道中心线作为参考线；根据规划路径，获取规划路径的边界条件，该边界条件包括起点的航向和曲率。
路径检测模块520，用于将规划路径的边界条件与检测触发阈值进行比较，根据规划路径的边界条件不满足检测触发阈值，确定规划路径未超出路径限制。
在一实施例中，路径检测模块520可以包括：第一判断子模块5201、第二判断子模块5202、第一检测子模块5203、第二检测子模块5204、第 三检测子模块5205。
第一判断子模块5201，用于将规划路径的边界条件与检测触发阈值进行比较，判断规划路径的边界条件是否满足检测触发阈值；
第二判断子模块5202，用于判断规划路径的曲线的极值点极值是否满足路径凸包限制条件；
第一检测子模块5203，用于根据规划路径的边界条件不满足检测触发阈值，确定规划路径未超出路径限制；
第二检测子模块5204，根据规划路径的边界条件满足检测触发阈值，且规划路径的曲线的极值点极值满足路径凸包限制条件，确定规划路径未超出路径限制；
第三检测子模块5205，用于根据规划路径的边界条件满足检测触发阈值，且规划路径的曲线的极值点极值不满足路径凸包限制条件，确定规划路径超出路径限制。
其中，第一检测子模块5203可以在获取规划路径的起点的航向和曲率后，如果航向的绝对值和曲率的绝对值小于设定阈值，则确定规划路径的边界条件不满足检测触发阈值。
第二检测子模块5204可以是在获取规划路径的起点的航向和曲率后，如果航向的绝对值和曲率的绝对值大于或等于设定阈值，则确定规划路径的边界条件满足检测触发阈值。
第二检测子模块5204确定规划路径的曲线的极值点极值满足路径凸包限制条件的过程可以包括：
当获取曲线的极值点的初始位置纵坐标y0、二分之一目标参考车道宽度值D0、车辆越过目标参考车道中心线的极限阈值D1、曲线的第一极值点极值ymax、曲线的第二极值点极值ymin之后；
在y0大于0、ymax大于D0且ymin小于-D1时，确定规划路径的曲线的极值点极值满足路径凸包限制条件；或，
在y0小于或等于0、ymin小于-D0且ymax大于D1时，确定规划路径的曲线的极值点极值满足路径凸包限制条件；
其中ymax大于ymin。
第三检测子模块5205确定规划路径的曲线的极值点极值不满足路径 凸包限制条件的过程可以包括：
当获取曲线的极值点的初始位置纵坐标y0、二分之一目标参考车道宽度值D0、车辆越过目标参考车道中心线的极限阈值D1、曲线的第一极值点极值ymax、曲线的第二极值点极值ymin之后；
在y0小于或等于0且ymin大于或等于-D0时，确定规划路径的曲线的极值点极值不满足路径凸包限制条件；或，
在y0大于0且ymax小于或等于D0时，确定规划路径的曲线的极值点极值不满足路径凸包限制条件；或，
在y0大于0、ymax大于D0且ymin大于或等于-D1时，确定规划路径的曲线的极值点极值不满足路径凸包限制条件；或，
在y0小于或等于0、ymin小于-D0且ymax小于或等于D1时，确定规划路径的曲线的极值点极值不满足路径凸包限制条件；
其中ymax大于ymin。
其中，上述极值点极值可以按以下方式确定：根据规划路径的曲线的参数方程，得到曲线的一阶导数的参数方程；对曲线的一阶导数的参数方程进行求解运算，得到极值点极值。
综上，本申请实施例的路径检测装置，在获取规划路径后，是根据规划路径的边界条件不满足检测触发阈值，确定规划路径未超出路径限制。这样的设计，不再需要在规划路径上采样然后分析采样点和路径限制的相对关系，而是确定路径的形状，根据路径的边界条件与检测触发阈值的比较进行判断，计算更简单，结果更精确，可以快速实现对规划路径的检测和筛选，满足自动驾驶实时性需求。
本申请实施例还提供一种汽车，本申请实施例的汽车可以包括上述任一实施例的路径检测装置。该路径检测装置的功能和结构可以参见图5中的描述，此处不再赘述。
参见图6，本申请还提供一种电子设备600，电子设备600包括存储器610和处理器620。存储器610上存储有可执行代码，当所述可执行代码被所述处理器620执行时，使所述处理器620执行上述任一实施例中所述的路径检测方法。
其中，处理器620可以是中央处理单元(Central Processing Unit，CPU)， 还可以是其他通用处理器620、数字信号处理器620(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器620可以是微处理器620或者该处理器620也可以是任何常规的处理器620等。
存储器610可以包括各种类型的存储单元，例如系统内存、只读存储器610(ROM)，和永久存储系统。其中，ROM可以存储处理器620或者计算机的其他模块需要的静态数据或者指令。永久存储系统可以是可读写的存储系统。永久存储系统可以是即使计算机断电后也不会失去存储的指令和数据的非易失性存储设备。在一些实施方式中，永久性存储系统采用大容量存储系统(例如磁或光盘、闪存)作为永久存储系统。另外一些实施方式中，永久性存储系统可以是可移除的存储设备(例如软盘、光驱)。系统内存可以是可读写存储设备或者易失性可读写存储设备，例如动态随机访问内存。系统内存可以存储一些或者所有处理器620在运行时需要的指令和数据。此外，存储器610可以包括任意计算机可读存储媒介的组合，包括各种类型的半导体存储芯片(DRAM，SRAM，SDRAM，闪存，可编程只读存储器610)，磁盘和/或光盘也可以采用。在一些实施方式中，存储器610可以包括可读和/或写的可移除的存储设备，例如激光唱片(CD)、只读数字多功能光盘(例如DVD-ROM，双层DVD-ROM)、只读蓝光光盘、超密度光盘、闪存卡(例如SD卡、min SD卡、Micro-SD卡等等)、磁性软盘等等。计算机可读存储媒介不包含载波和通过无线或有线传输的瞬间电子信号。
存储器610上存储有可执行代码，当可执行代码被处理器620处理时，可以使处理器620执行上文述及的方法中的部分或全部。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不再做详细阐述说明。
此外，根据本申请的方法还可以实现为一种计算机程序或计算机程序产品，该计算机程序或计算机程序产品包括用于执行本申请的上述方法中部分或全部步骤的计算机程序代码指令。
或者，本申请还可以实施为一种非暂时性机器可读存储介质(或计算机可读存储介质、或机器可读存储介质)，其上存储有可执行代码(或计算机程序、或计算机指令代码)，当可执行代码(或计算机程序、或计算机指令代码)被电子设备(或电子设备、服务器等)的处理器执行时，使处理器执行根据本申请的上述方法的各个步骤的部分或全部。
以上已经描述了本申请的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (15)

  1. 一种路径检测方法，其特征在于，包括：
    获取规划路径和所述规划路径的边界条件，其中所述规划路径使用目标参考车道中心线作为参考线；
    将所述规划路径的边界条件与检测触发阈值进行比较，根据所述规划路径的边界条件不满足所述检测触发阈值，确定所述规划路径未超出路径限制。
  2. 根据权利要求1所述的路径检测方法，其特征在于，所述方法还包括：
    根据所述规划路径的边界条件满足所述检测触发阈值，且所述规划路径的曲线的极值点极值满足路径凸包限制条件，确定所述规划路径未超出路径限制。
  3. 根据权利要求1或2所述的路径检测方法，其特征在于，所述方法还包括：
    根据所述规划路径的边界条件满足所述检测触发阈值，且所述规划路径的曲线的极值点极值不满足路径凸包限制条件，确定所述规划路径超出路径限制。
  4. 根据权利要求1所述的路径检测方法，其特征在于，所述获取规划路径和所述规划路径的边界条件，包括：
    根据当前参考车道中心线和目标参考车道中心线得到所述规划路径；
    根据所述规划路径，获取所述规划路径的边界条件，所述边界条件包括起点的航向和曲率。
  5. 根据权利要求2所述的路径检测方法，其特征在于：
    所述规划路径的边界条件不满足所述检测触发阈值，包括：
    在获取所述规划路径的起点的航向和曲率后，如果所述航向的绝对值和所述曲率的绝对值小于设定阈值，则确定所述规划路径的边界条件不满足所述检测触发阈值；或，
    所述规划路径的边界条件满足所述检测触发阈值，包括：
    在获取所述规划路径的起点的航向和曲率后，如果所述航向的绝对值和所述曲率的绝对值大于或等于设定阈值，则确定所述规划路径的边界条 件满足所述检测触发阈值。
  6. 根据权利要求2所述的路径检测方法，其特征在于，所述规划路径的曲线的极值点极值满足路径凸包限制条件，包括：
    当获取所述曲线的极值点的初始位置纵坐标y0、二分之一目标参考车道宽度值D 0、车辆越过目标参考车道中心线的极限阈值D 1、所述曲线的第一极值点极值ymax、所述曲线的第二极值点极值ymin之后，
    在所述y0大于0、ymax大于D 0且ymin小于-D 1时，确定所述规划路径的曲线的极值点极值满足路径凸包限制条件；或，
    在所述y0小于或等于0、ymin小于-D 0且ymax大于D 1时，确定所述规划路径的曲线的极值点极值满足路径凸包限制条件；
    其中所述ymax大于所述ymin。
  7. 根据权利要求3所述的路径检测方法，其特征在于，所述所述规划路径的曲线的极值点极值不满足路径凸包限制条件，包括：
    当获取所述曲线的极值点的初始位置纵坐标y0、二分之一目标参考车道宽度值D 0、车辆越过目标参考车道中心线的极限阈值D 1、所述曲线的第一极值点极值ymax、所述曲线的第二极值点极值ymin之后，
    在所述y0小于或等于0且ymin大于或等于-D 0时，确定所述规划路径的曲线的极值点极值不满足路径凸包限制条件；或，
    在所述y0大于0且ymax小于或等于D 0时，确定所述规划路径的曲线的极值点极值不满足路径凸包限制条件；或，
    在所述y0大于0、ymax大于D 0且ymin大于或等于-D 1时，确定所述规划路径的曲线的极值点极值不满足路径凸包限制条件；或，
    在所述y0小于或等于0、ymin小于-D 0且ymax小于或等于D 1时，确定所述规划路径的曲线的极值点极值不满足路径凸包限制条件；
    其中所述ymax大于所述ymin。
  8. 根据权利要求2所述的路径检测方法，其特征在于，所述极值点极值按以下方式确定：
    根据所述规划路径的曲线的参数方程，得到所述曲线的一阶导数的参数方程；
    对所述曲线的一阶导数的参数方程进行求解运算，得到所述极值点极 值。
  9. 一种路径检测装置，其特征在于，包括：
    路径获取模块，用于获取规划路径和所述规划路径的边界条件，其中所述规划路径使用目标参考车道中心线作为参考线；
    路径检测模块，用于将所述规划路径的边界条件与检测触发阈值进行比较，根据所述路径检测模块获取的规划路径的边界条件不满足所述检测触发阈值，确定所述规划路径未超出路径限制。
  10. 根据权利要求9所述的路径检测装置，其特征在于，所述路径检测模块包括：
    第一判断子模块，用于将所述规划路径的边界条件与检测触发阈值进行比较，判断所述规划路径的边界条件是否满足所述检测触发阈值；
    第二判断子模块，用于判断所述规划路径的曲线的极值点极值是否满足路径凸包限制条件；
    第一检测子模块，用于根据所述第一判断子模块判断的规划路径的边界条件不满足所述检测触发阈值，确定所述规划路径未超出路径限制；
    第二检测子模块，根据所述第一判断子模块判断的规划路径的边界条件满足所述检测触发阈值，且所述第二判断子模块判断的规划路径的曲线的极值点极值满足路径凸包限制条件，确定所述规划路径未超出路径限制。
  11. 根据权利要求10所述的路径检测装置，其特征在于，所述路径检测模块还包括：
    第三检测子模块，用于根据所述第一判断子模块判断的规划路径的边界条件满足所述检测触发阈值，且所述第二判断子模块判断的规划路径的曲线的极值点极值不满足所述路径凸包限制条件，确定所述规划路径超出路径限制。
  12. 根据权利要求10所述的路径检测装置，其特征在于：
    所述第一检测子模块在获取规划路径的起点的航向和曲率后，如果航向的绝对值和曲率的绝对值小于设定阈值，则确定规划路径的边界条件不满足检测触发阈值。
  13. 根据权利要求10所述的路径检测装置，其特征在于：
    所述第二检测子模块在获取规划路径的起点的航向和曲率后，如果航 向的绝对值和曲率的绝对值大于或等于设定阈值，则确定规划路径的边界条件满足检测触发阈值。
  14. 一种汽车，其特征在于，根据权利要求9-13任一项所述的路径检测装置。
  15. 一种非暂时性机器可读存储介质，其上存储有可执行代码，当所述可执行代码被电子设备的处理器执行时，使所述处理器执行如权利要求1-8中任一项所述的方法。
PCT/CN2022/105985 2021-07-15 2022-07-15 路径检测方法、装置、汽车及存储介质 WO2023284859A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110802322.8 2021-07-15
CN202110802322.8A CN113320547B (zh) 2021-07-15 2021-07-15 路径检测方法、装置及汽车

Publications (1)

Publication Number Publication Date
WO2023284859A1 true WO2023284859A1 (zh) 2023-01-19

Family

ID=77426419

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/105985 WO2023284859A1 (zh) 2021-07-15 2022-07-15 路径检测方法、装置、汽车及存储介质

Country Status (2)

Country Link
CN (1) CN113320547B (zh)
WO (1) WO2023284859A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117553801A (zh) * 2024-01-08 2024-02-13 深圳市普渡科技有限公司 拓扑路径图生成方法、装置、机器人及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113320547B (zh) * 2021-07-15 2023-08-25 广州小鹏自动驾驶科技有限公司 路径检测方法、装置及汽车

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111361564A (zh) * 2020-04-29 2020-07-03 吉林大学 一种考虑效益最大化的车道变更系统及综合决策方法
CN111653113A (zh) * 2020-04-20 2020-09-11 浙江吉利汽车研究院有限公司 车辆的局部路径确定方法、装置、终端和存储介质
CN111721309A (zh) * 2019-03-19 2020-09-29 上海汽车集团股份有限公司 路径规划方法及装置
CN112146667A (zh) * 2020-09-29 2020-12-29 广州小鹏自动驾驶科技有限公司 一种车辆过渡轨迹的生成方法和装置
US20210114617A1 (en) * 2019-10-18 2021-04-22 Uatc, Llc Method for Using Lateral Motion to Optimize Trajectories for Autonomous Vehicles
CN113320547A (zh) * 2021-07-15 2021-08-31 广州小鹏自动驾驶科技有限公司 路径检测方法、装置及汽车

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103528585B (zh) * 2013-09-26 2016-05-25 中北大学 一种不等距分割可通行区域的路径规划方法
CN107121980B (zh) * 2017-03-17 2019-07-09 北京理工大学 一种基于虚拟约束的自动驾驶车辆路径规划方法
CN107817000B (zh) * 2017-10-25 2020-09-08 广州汽车集团股份有限公司 无人驾驶车辆的路径规划方法、装置及计算机设备
CN109540159B (zh) * 2018-10-11 2020-11-27 同济大学 一种快速完备的自动驾驶轨迹规划方法
CN112506176B (zh) * 2019-08-26 2024-05-28 上海汽车集团股份有限公司 路径规划方法及装置
CN112577503B (zh) * 2019-09-30 2024-04-09 北京百度网讯科技有限公司 车辆起点区域的路径规划方法、装置、设备
EP3861291B1 (en) * 2019-12-20 2023-01-25 Baidu.com Times Technology (Beijing) Co., Ltd. Spline curve and spiral curve based reference line smoothing method
CN111186443B (zh) * 2020-02-06 2021-09-03 北京百度网讯科技有限公司 变道路径规划方法、装置、电子设备和计算机可读介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111721309A (zh) * 2019-03-19 2020-09-29 上海汽车集团股份有限公司 路径规划方法及装置
US20210114617A1 (en) * 2019-10-18 2021-04-22 Uatc, Llc Method for Using Lateral Motion to Optimize Trajectories for Autonomous Vehicles
CN111653113A (zh) * 2020-04-20 2020-09-11 浙江吉利汽车研究院有限公司 车辆的局部路径确定方法、装置、终端和存储介质
CN111361564A (zh) * 2020-04-29 2020-07-03 吉林大学 一种考虑效益最大化的车道变更系统及综合决策方法
CN112146667A (zh) * 2020-09-29 2020-12-29 广州小鹏自动驾驶科技有限公司 一种车辆过渡轨迹的生成方法和装置
CN113320547A (zh) * 2021-07-15 2021-08-31 广州小鹏自动驾驶科技有限公司 路径检测方法、装置及汽车

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117553801A (zh) * 2024-01-08 2024-02-13 深圳市普渡科技有限公司 拓扑路径图生成方法、装置、机器人及存储介质

Also Published As

Publication number Publication date
CN113320547B (zh) 2023-08-25
CN113320547A (zh) 2021-08-31

Similar Documents

Publication Publication Date Title
WO2023284859A1 (zh) 路径检测方法、装置、汽车及存储介质
US20200074665A1 (en) Object detection method, device, apparatus and computer-readable storage medium
JP2020042773A (ja) シミュレーションデータの最適化方法、装置及び記憶媒体
CN111897364B (zh) 一种无人机区域轨迹规划方法、装置及可读存储介质
CN112731334A (zh) 一种激光定位车辆的方法及装置
JP2020038617A (ja) 車線処理方法及び装置
CN114705121B (zh) 车辆位姿测量方法、装置及电子设备、存储介质
CN111832665B (zh) 栅栏检测方法、装置、计算机设备和存储介质
JPWO2017130285A1 (ja) 車両判定装置、車両判定方法及び車両判定プログラム
CN114187579A (zh) 自动驾驶的目标检测方法、装置和计算机可读存储介质
CN116309628A (zh) 车道线识别方法和装置、电子设备和计算机可读存储介质
US20230022335A1 (en) Apparatus and method for monitoring surrounding environment of vehicle
US10388402B2 (en) Memory system and memory control method
US20220314980A1 (en) Obstacle tracking method, storage medium and unmanned driving device
CN113607159B (zh) 高精地图车道线的优化方法、装置及设备
CN115050007A (zh) 牵引车以及拖板车的识别方法、装置及电子设备、存储介质
CN114228741A (zh) 用于自动驾驶车辆的车道保持方法及装置
CN113902742A (zh) 一种基于tft-lcd检测缺陷真假判定方法和系统
US11391845B2 (en) Fog determination apparatus, fog determination method, and computer readable medium
CN113358894B (zh) 车速计算方法、运动目标运动状态检测方法、装置及设备
CN116468634A (zh) 高精地图车道线平滑处理方法、装置及电子设备
CN116839605A (zh) 高精地图异常车道线的处理方法、装置、设备及存储介质
CN116092039A (zh) 自动驾驶仿真系统的显示控制方法及装置
CN113277392B (zh) 一种基于高斯分布模型的电梯楼层高度标定方法、电子设备及存储介质
CN110118559B (zh) 一种基于变概率策略的导览机器人动态避障方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22841492

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE