WO2020216315A1 - 一种参考行驶线快速生成方法、***、终端和存储介质 - Google Patents

一种参考行驶线快速生成方法、***、终端和存储介质 Download PDF

Info

Publication number
WO2020216315A1
WO2020216315A1 PCT/CN2020/086577 CN2020086577W WO2020216315A1 WO 2020216315 A1 WO2020216315 A1 WO 2020216315A1 CN 2020086577 W CN2020086577 W CN 2020086577W WO 2020216315 A1 WO2020216315 A1 WO 2020216315A1
Authority
WO
WIPO (PCT)
Prior art keywords
difficulty
path
path planning
coordinate
map
Prior art date
Application number
PCT/CN2020/086577
Other languages
English (en)
French (fr)
Inventor
余恒
王凡
唐锐
Original Assignee
纵目科技（上海）股份有限公司
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 纵目科技（上海）股份有限公司 filed Critical 纵目科技（上海）股份有限公司
Priority to EP20794378.8A priority Critical patent/EP3951321A4/en
Priority to US17/606,559 priority patent/US11592305B2/en
Publication of WO2020216315A1 publication Critical patent/WO2020216315A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3461—Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types, segments such as motorways, toll roads, ferries
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3679—Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities
    • G01C21/3685—Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities the POI's being parking facilities
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3863—Structures of map data
    • G01C21/387—Organisation of map data, e.g. version management or database structures

Definitions

  • the present invention relates to the technical field of automotive electronics, in particular to a method, system, terminal and storage medium for quickly generating a reference driving line.
  • the reference driving line is a common module in the map path planning service. After obtaining the user's starting position and obtaining the user's input destination position, the map will generate a global path (global path).
  • the global road is sparse It is composed of road nodes along the route, and then a path planning line from the starting position to the ending direction of the destination position connects these road nodes along the route in series to form a global path.
  • Global path Because nodes and nodes are directly connected, and vehicles are in different road scenes and under the influence of the body dynamics parameters of different models, the actual driving path of the vehicle needs to be in line with the vehicle body dynamics. Control requirements, and need to meet the complex working conditions of real road scenes, can be used as a reference driving line for unmanned driving at L4 and even L5 levels. In the complex parking lot scene, the vehicle will update the reference driving line through the algorithm every time the local map is acquired. The calculation difficulty of the reference driving line of the road sections with different driving difficulty is different, and the same reference driving line generation algorithm is used for all road sections. It will increase the occupation of system resources and increase the time-consuming algorithm.
  • the present invention provides a method, system, terminal and storage medium for quickly generating a reference driving line, which divides the route planning points according to the driving difficulty for road sections of different difficulty, and divides the parts with low driving difficulty.
  • the driving reference driving line is obtained by geometric processing; the driving reference driving line is obtained by algorithmic processing of the parts with high driving difficulty combined with vehicle dynamics constraints, and then the driving reference driving line of each part is spliced to form a complete driving reference driving line.
  • This method has a low system resource occupancy rate and a short time-consuming algorithm.
  • a method for quickly generating a reference driving line including:
  • the part is divided into high-difficulty partial path parts, and the high-difficulty partial path division numbers are given, and the path planning points within the coverage of the high-difficulty partial path parts are extracted to form difficult partial path planning points set;
  • the part is divided into low-difficulty partial path parts, and the low-difficulty path division number is given, and the path planning points within the coverage of the low-difficulty partial path part are extracted to form a low-difficulty path planning point set;
  • the set of the high-difficulty local path part and the low-difficulty path part is equal to the global path planning part in the preloaded map;
  • S03 Extract the difficult path planning point set of the difficult local path division number one by one.
  • Each path planning point in the path planning point set contains the x coordinate information and y coordinate information of the path planning point.
  • S04 Use the algorithm to simulate the reference driving line of the difficult path points in each difficult local path area, and obtain the reference driving line from the path planning points in each low difficulty local path area in a geometric manner; Difficult local path planning is spliced according to the number to form a local map path planning.
  • step S04 if the execution of step S04 fails, the reference driving line of the difficult local route area is found by the search method; if the search method can find the reference driving line of the difficult local route area, the reference driving line and the The remaining part of the route area is spliced with reference to the driving line; if the search method fails to find the reference driving line of the difficult local route area, return to step S01 to find the route planning points and route directions existing in the preloaded map range.
  • step S011 judging whether the height information of the preloaded map and the height information of the previous local map that the vehicle has driven Consistent; if they are consistent, go to step S02; if they are not consistent, then end.
  • the algorithm used for simulating the reference driving line with the algorithm is: Hybrid A star algorithm generates the reference driving line.
  • the input layer of the Hybrid A star algorithm includes: the center line data of the two lanes that need to turn around, and each point data of the center line contains the position and orientation (x, y, theta).
  • the Hybrid A star algorithm is used for trajectory generation calculations, which can generate a trajectory with smooth position and curvature, so that the vehicle can complete a U-turn motion.
  • the output layer of the Hybrid A star algorithm includes a complete trajectory connecting two lanes. Each point in the trajectory contains position, orientation, and curvature data (x, y, theta, kappa).
  • Hybrid A star algorithm to find a drivable trajectory.
  • the path given by Hybrid A star is not drivable, but when we add the dynamic constraints of the car, we may be able to achieve the results required by the problem.
  • the Hybrid A star algorithm includes the following steps in the program:
  • the unreasonable areas include obstacles, areas outside the map, and areas with low efficiency;
  • S043 Record the continuous vehicle state and the discrete grid grid associated with the state
  • the visualization part uses python matplotlib.
  • Hybrid A star algorithm test problem The code part does not introduce test frameworks (gtest, boosttest, etc.), but uses scripts to cooperate with the lightweight solution of c++assert, because the development and testing process requires a lot of visual assistance and batch Test file reading, using C++ requires high code maintenance, and it cannot be visualized without coupling with the code.
  • Hybrid A star algorithm When Hybrid A star algorithm is used, it does not use the true grid map in the form of a three-dimensional array, but uses std::vector ⁇ std::map ⁇ Point,State>>. This form is a bit like the expression of sparse matrix, which greatly saves Space consumption also greatly reduces the work of coordinate system conversion.
  • the final trajectory has been fitted and resampled, in order to make the trajectory smooth, but also to calculate kappa
  • the calculation of kappa is obtained according to the formula:
  • the curve is determined by the parametric equation Given, the value of K can be obtained by using the parametric equation derivation method.
  • a semicircular curve can be generated as the reference line, and then qp is used for optimization.
  • This method may cause the calculated trajectory to not meet the physical characteristics of the car, for example, the curve at certain points is too large.
  • a rapid generation system for reference driving lines including:
  • the map module includes a city-level map of a certain city, a district-level map of a certain district, a township-level map of a certain township, a street-level map, or a map of an indoor scene;
  • a global path planning module includes the starting point, the ending point position of the vehicle, and the path points of the road passed from the starting point to the ending point;
  • Driving difficulty segmentation module the driving difficulty segmentation module is used to segment the path of the system preloaded with the local map, and pass the road driving difficulty analysis before segmentation.
  • the driving difficulty is determined to be higher than the rated value
  • the part is divided into a high difficulty local path Part, extract the path planning points in the part of the high-difficulty partial path coverage to form a high-difficulty partial path planning point set;
  • the driving difficulty is lower than the rated value, divide the part into the low-difficulty partial path part and extract the low-difficulty partial path Path planning points in part of the coverage area form a low-difficulty path planning point set;
  • a reference driving line generation module which generates a driving reference driving line in different ways from the high-difficulty local path planning points and the low-difficulty local path planning points according to the division results of the driving difficulty segmentation module, and then the driving reference The driving line is spliced into the completed driving reference driving line.
  • the driving difficulty segmentation module divides the high-difficulty local path planning point set, first obtains the high-difficulty local path area, and the acquisition method is:
  • each path planning point in the path planning point set contains the x coordinate information and y coordinate information of the path planning point, and traverse all the paths in the difficult path planning point set
  • the x coordinate information of the planning point find the maximum x coordinate and the minimum x coordinate
  • traverse the y coordinate information of all the path planning points in the difficult path planning point set and find the maximum y coordinate and the minimum y coordinate
  • a reference driving line rapid generation terminal such as a smart phone that can execute the above-mentioned reference driving line rapid generation method or a vehicle-mounted terminal control device that can execute the above-mentioned reference driving line rapid generation system.
  • a computer-readable storage medium having a computer program stored thereon is characterized in that the program is executed by a processor to execute the steps in a method for quickly generating a reference driving line.
  • the present invention has the following beneficial effects:
  • FIG. 1 shows a flowchart of the present invention.
  • Fig. 2 is a schematic diagram of a reference driving line for driving in an indoor parking lot at a certain time according to the present invention.
  • Fig. 3 shows a schematic diagram of a reference driving line for driving in an indoor parking lot at the next moment of the present invention.
  • Fig. 4 shows a schematic diagram of a reference driving line for driving in an indoor parking lot at the next moment of the present invention.
  • Fig. 5 is a schematic diagram of the preloaded partial map driving difficulty segmentation module of the present invention after segmentation.
  • Fig. 6 is a schematic diagram of a high-difficulty driving path after segmentation by the pre-loaded partial map driving difficulty segmentation module of the present invention.
  • FIG. 7 is a schematic diagram of a low-difficulty driving path after segmentation by the driving difficulty segmentation module of the preloaded partial map of the present invention.
  • FIG. 8 is a schematic diagram of another part of the low-difficulty driving path after segmentation by the driving difficulty segmentation module of the preloaded partial map of the present invention.
  • Fig. 9 shows a schematic diagram of the driving difficulty segmentation module in another preloaded local map after segmentation.
  • FIG. 10 is a schematic diagram of a certain high-difficulty path after segmentation by the driving difficulty segmentation module in another preloaded partial map.
  • a method for quickly generating a reference driving line including:
  • the part is divided into high-difficulty partial path parts, and the high-difficulty partial path division numbers are given, and the path planning points within the coverage of the high-difficulty partial path parts are extracted to form difficult partial path planning points set;
  • the part is divided into low-difficulty partial path parts, and the low-difficulty path division number is given, and the path planning points within the coverage of the low-difficulty partial path part are extracted to form a low-difficulty path planning point set;
  • the set of the high-difficulty local path part and the low-difficulty path part is equal to the global path planning part in the preloaded map;
  • S03 Extract the difficult path planning point set of the difficult local path division number one by one.
  • Each path planning point in the path planning point set contains the x coordinate information and y coordinate information of the path planning point.
  • S04 Use the algorithm to simulate the reference driving line of the difficult path points in each difficult local path area, and obtain the reference driving line from the path planning points in each low difficulty local path area in a geometric manner; Difficult local path planning is spliced according to the number to form a local map path planning.
  • step S04 if the execution of step S04 fails, the reference driving line of the difficult local route area is found by the search method; if the search method can find the reference driving line of the difficult local route area, the reference driving line and the The remaining part of the route area is spliced with reference to the driving line; if the search method fails to find the reference driving line of the difficult local route area, return to step S01 to find the route planning points and route directions existing in the preloaded map range.
  • step S011 judging whether the height information of the preloaded map and the height information of the previous local map that the vehicle has driven Consistent; if they are consistent, go to step S02; if they are not consistent, then end.
  • the algorithm used for simulating the reference driving line with the algorithm is: Hybrid A star algorithm generates the reference driving line.
  • the input layer of the Hybrid A star algorithm includes: the center line data of the two lanes that need to turn around, and each point data of the center line contains the position and orientation (x, y, theta).
  • the Hybrid A star algorithm is used for trajectory generation calculations, which can generate a trajectory with smooth position and curvature, so that the vehicle can complete a U-turn motion.
  • the output layer of the Hybrid A star algorithm includes a complete trajectory connecting two lanes. Each point in the trajectory contains position, orientation, and curvature data (x, y, theta, kappa).
  • Hybrid A star algorithm to find a drivable trajectory.
  • the path given by Hybrid A star is not drivable, but when we add the dynamic constraints of the car, we may be able to achieve the results required by the problem.
  • the Hybrid A star algorithm includes the following steps in the program:
  • the unreasonable areas include obstacles, areas outside the map, and areas with low efficiency;
  • S043 Record the continuous vehicle state and the discrete grid grid associated with the state
  • the visualization part uses python matplotlib.
  • Hybrid A star algorithm test problem The code part does not introduce test frameworks (gtest, boosttest, etc.), but uses scripts to cooperate with the lightweight solution of c++assert, because the development and testing process requires a lot of visual assistance and batch Test file reading, using C++ requires high code maintenance, and it cannot be visualized without coupling with the code.
  • Hybrid A star algorithm When Hybrid A star algorithm is used, it does not use the true grid map in the form of a three-dimensional array, but uses std::vector ⁇ std::map ⁇ Point,State>>. This form is a bit like the expression of sparse matrix, which greatly saves Space consumption also greatly reduces the work of coordinate system conversion.
  • the final trajectory has been fitted and resampled, in order to make the trajectory smooth, but also to calculate kappa
  • the calculation of kappa is obtained according to the formula:
  • the curve is determined by the parametric equation Given, the value of K can be obtained by using the parametric equation derivation method.
  • a semicircular curve can be generated as the reference line, and then qp is used for optimization.
  • This method may cause the calculated trajectory to not meet the physical characteristics of the car, for example, the curve at certain points is too large.
  • a rapid generation system for reference driving lines including:
  • the map module includes a city-level map of a certain city, a district-level map of a certain district, a township-level map of a certain township, a street-level map, or a map of an indoor scene;
  • a global path planning module includes the starting point, the ending point position of the vehicle, and the path points of the road passed from the starting point to the ending point;
  • Driving difficulty segmentation module the driving difficulty segmentation module is used to segment the path of the system preloaded with the local map, and pass the road driving difficulty analysis before segmentation.
  • the driving difficulty is determined to be higher than the rated value
  • the part is divided into a high difficulty local path Part, extract the path planning points in the part of the high-difficulty partial path coverage to form a high-difficulty partial path planning point set;
  • the driving difficulty is lower than the rated value, divide the part into the low-difficulty partial path part and extract the low-difficulty partial path Path planning points in part of the coverage area form a low-difficulty path planning point set;
  • a reference driving line generation module which generates a driving reference driving line in different ways from the high-difficulty local path planning points and the low-difficulty local path planning points according to the division results of the driving difficulty segmentation module, and then the driving reference The driving line is spliced into the completed driving reference driving line.
  • the driving difficulty segmentation module divides the high-difficulty local path planning point set, first obtains the high-difficulty local path area, and the acquisition method is:
  • each path planning point in the path planning point set contains the x coordinate information and y coordinate information of the path planning point, and traverse all the paths in the difficult path planning point set
  • the x coordinate information of the planning point find the maximum x coordinate and the minimum x coordinate
  • traverse the y coordinate information of all the path planning points in the difficult path planning point set and find the maximum y coordinate and the minimum y coordinate
  • a reference driving line rapid generation terminal such as a smart phone that can execute the above-mentioned reference driving line rapid generation method or a vehicle-mounted terminal control device that can execute the above-mentioned reference driving line rapid generation system.
  • a computer-readable storage medium having a computer program stored thereon is characterized in that the program is executed by a processor to execute the steps in a method for quickly generating a reference driving line.
  • this embodiment also provides a terminal device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack cloud, a blade cloud, a tower cloud, or a cabinet cloud (including Independent cloud, or cloud cluster composed of multiple clouds), etc.
  • the terminal device in this embodiment at least includes but is not limited to: a memory and a processor that can be communicatively connected to each other through a system bus. It should be pointed out that a terminal device with a component memory and a processor, but it should be understood that it is not required to implement all the components shown, and it can be replaced with more or less implementation of the reference driving line generation method in line with vehicle dynamics s component.
  • the memory (that is, the readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), only Readable memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc.
  • the memory may be an internal storage unit of the computer device, such as the hard disk or memory of the computer device.
  • the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), or a secure digital (SD) card equipped on the computer device.
  • the memory may also include both the internal storage unit of the computer device and its external storage device.
  • the memory is generally used to store the operating system and various application software installed in the computer device, such as the program code of the reference driving line generation method in accordance with the vehicle dynamics in the embodiment.
  • the memory can also be used to temporarily store various types of data that have been output or will be output.
  • This embodiment also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), only Readable memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, cloud, App application mall, etc., on which computer programs are stored, The corresponding function is realized when the program is executed by the processor.
  • the computer-readable storage medium of this embodiment is used to store a reference driving line generation method program that conforms to vehicle dynamics, and when executed by a processor, it realizes the vehicle dynamics-compliant reference driving line generation method program embodiment. Refer to the method of generating the driving line.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

一种参考行驶线快速生成方法、***、终端和存储介质，对不同难度的路段按照行驶难度分割路径规划点，将行驶难度低的部分以几何处理的方式获得行驶参考行驶线；将行驶难度高的部分结合车动力学约束以Hybrid A star算法处理方式获得行驶参考行驶线，再将各个部分的行驶参考行驶线拼接形成完整的行驶参考行驶线，***资源占用率低，算法耗时短。

Description

一种参考行驶线快速生成方法、***、终端和存储介质 技术领域
本发明涉及汽车电子技术领域，特别是涉及一种参考行驶线快速生成方法、***、终端和存储介质。
背景技术
参考行驶线是地图路径规划服务中的一种常用模块，在获取使用者起始位置，并获取使用者输入目的地位置后，地图会生成一个全局道路(global path)，全局道路是由稀疏的沿线道路节点组成的，再由自起始位置至目的地位置终止方向的路径规划线将这些沿线道路节点串联形成全局道路(global path)。
全局道路(global path)由于节点和节点之间是直接连线的，而车辆在不同的道路场景下、在不同车型的车身动力学参数影响下，车辆实际行驶路径都需要即符合车辆车身动力学控制要求，又需要符合真实道路场景复杂工况，才能作为L4乃至L5级别的无人驾驶参考行驶线使用。而车辆在复杂停车场场景中每获取一次局部地图均会通过算法更新一次参考行驶线，而不同行驶难度的路段参考行驶线的计算难度是不同的，对于所有路段使用同一种参考行驶线生成算法会提高***资源的占用，并且提高算法耗时。
发明内容
为了解决上述的以及其他潜在的技术问题，本发明提供了一种参考行驶线快速生成方法、***、终端和存储介质,对不同难度的路段按照行驶难度分割路径规划点，将行驶难度低的部分以几何处理的方式获得行驶参考行驶线；将行驶难度高的部分结合车动力学约束以算法处理方式获得行驶参考行驶线，再将各个部分的行驶参考行驶线拼接形成完整的行驶参考行驶线，该方法***资源占用率低，算法耗时短。
一种参考行驶线快速生成方法，包括：
S01：获取预加载地图和全局路径规划，找到存在于预加载地图范围内的路径规划点和路径方向；
S02：按照行驶难度分割路径规划点：
当行驶难度高于额定值时，将该部分划分为高难度局部路径部分，并给予高难度局部路径划分编号，提取高难度局部路径部分覆盖范围内的路径规划点，形成高难度局部路径规划点集；
当行驶难度低于额定值时，将该部分划分为低难度局部路径部分，并给予低难度路径划分编号，提取低难度局部路径部分覆盖范围内的路径规划点，形成低难度路径规划点集；
高难度局部路径部分和低难度路径部分的集合等于该预加载地图中全局路径规划部分；
S03：逐一提取高难度局部路径划分编号的高难度路径规划点集，路径规划点集中的每一个路径规划点均含有该路径规划点的x坐标信息、y坐标信息，
遍历高难度路径规划点集中所有路径规划点的x坐标信息，找出x坐标的最大值和x坐标的最小值；
遍历高难度路径规划点集中所有路径规划点的y坐标信息，找出y坐标的最大值和y坐标的最小值；
以x坐标最大值、x坐标最小值、y坐标最大值，y坐标最小值为边界形成高难度局部路径区域；
S04：将每一个高难度局部路径区域的高难度路径点以算法模拟参考行驶线，将每一个低难度局部路径区域中路径规划点以几何方式获取参考行驶线；将高难度局部路径规划和低难度局部路径规划按照编号拼接，形成局部地图的路径规划。
进一步地，若步骤S04执行失败，则以搜索方式找到该高难度局部路径区域的参考行驶线；若搜索方式可以找到高难度局部路径区域参考行驶线，则用该高难度路径区域参考行驶线与剩余部分路径区域参考行驶线拼接；若搜索方式寻找高难度局部路径区域参考行驶线失败，则返回到步骤S01重新寻找存在于预加载地图范围内的路径规划点和路径方向。
进一步地，还包括一下情形：
按照行驶难度分割路径规划点：当行驶难度无法识别时，给予预加载地图范围内路径规划点以统一的划分编号。
进一步地，在步骤S01获取预加载地图和预加载地图范围内的路径规划点和路径方向时，还包括步骤S011：判断预加载地图的高度信息与车辆行驶过的前一张局部地图高度信息是否一致；若一致，则进入步骤S02；若不一致，则结束。
进一步地，步骤S04中以算法模拟参考行驶线使用的算法是：Hybrid A star算法生成参考行驶线。Hybrid A star算法的输入层包括：需要完成掉头的两条车道的中心线数据，中心线的每个点数据包含位置与朝向(x,y,theta)。Hybrid A star算法用以轨迹生成类计算，能够生成一条位置、曲率平滑的轨迹，让车辆能够完成掉头运动。Hybrid A star算法的输出层包括连接两条车道的完整轨迹，轨迹中每个点包含位置、朝向与曲率数据(x,y,theta,kappa)。
使用Hybrid A star算法来寻找可行驶轨迹。在离散的情况下Hybrid A star给出的路径不是可行驶的，但是当我们加入汽车的动力学约束后，也许可以达到题目要求的结果。
Hybrid A star算法在程序中包括以下步骤：
S041：使用动力学约束来计算Hybrid A star算法的可扩展区域，即可扩展的栅格格子；约束动力学模型的同时，HeuristicCost也需要根据U-Turn的场景进行适当的优化；
S042：删除不合理的区域，所述不合理的区域包括障碍物、地图外区域、效率低的区域；
S043：记录连续的车辆状态以及状态关联的离散栅格格子；
S044：待得到搜索结果后取出路径相关联的连续状态点数据(x，y，theta)；
S045：检查曲率是否平滑。
Hybrid A star算法在程序实现中可视化问题：可视化部分使用python的matplotlib。
Hybrid A star算法测试问题：代码部分并没有引入测试框架(gtest，boosttest等)，而是用脚本配合c++assert的轻量化方案，因为开发和测试过程中需要很多肉眼观测的辅助和批量的测试文件读取，使用c++对代码维护要求较高，而且无法做到和代码不耦合的可视化。
Hybrid A star算法在使用时，没有使用三维数组形式的真栅各地图，而是使用std::vector<std::map<Point,State>>该形式有点像稀疏矩阵的表达方式，大大节约了空间消耗，也大大减轻的坐标系转换的工作。最终的轨迹经过了拟合以及重采样，为了让轨迹是平滑的，同时也是为了计算kappa kappa的计算根据该公式得出：
Figure PCTCN2020086577-appb-000001
其中，曲线是由参数方程
Figure PCTCN2020086577-appb-000002
给出，利用参数方程求导法可以得出K值。
进一步地，Hybrid A star算法的代替方案，可以生成半圆曲线作为reference line,然后使用qp进行优化。使用目标lane的入口作为end-configuration space，然后使用Jerk  minimize直接求解汽车可执行轨迹，然后检查轨迹是超过边界或存在碰撞。该方法可能导致计算出的trajectory不满足车子的物理特性，比如某些点的curve过大。
一种参考行驶线快速生成***，包括：
地图模块，所述地图模块包含某一城市的市级地图、某一区的区级地图、某一乡镇的乡镇级地图、街道级地图、或者某一室内场景的地图；
全局路径规划模块，所述全局路径规划模块包含车辆的起始点、终止点位置以及从起始点到终止点所经过的道路路径点；
行驶难度分割模块，所述行驶难度分割模块用于分割***预加载局部地图的路径，在分割前经过道路行驶难度分析，当认定行驶难度高于额定值时，将该部分划分为高难度局部路径部分，提取高难度局部路径部分覆盖范围内的路径规划点，形成高难度局部路径规划点集；当行驶难度低于额定值时，将该部分划分为低难度局部路径部分，提取低难度局部路径部分覆盖范围内的路径规划点，形成低难度路径规划点集；
参考行驶线生成模块，所述参考行驶线生成模块根据行驶难度分割模块分割结果，分别将高难度局部路径规划点和低难度局部路径规划点以不同的方式生成行驶参考行驶线，再将行驶参考行驶线拼接成完成的行驶参考行驶线。
进一步地，所述行驶难度分割模块分割高难度局部路径规划点集时，先获取高难度局部路径区域，获取方式为：
逐一提取高难度局部路径划分编号的高难度路径规划点集，路径规划点集中的每一个路径规划点均含有该路径规划点的x坐标信息、y坐标信息，遍历高难度路径规划点集中所有路径规划点的x坐标信息，找出x坐标的最大值和x坐标的最小值；遍历高难度路径规划点集中所有路径规划点的y坐标信息，找出y坐标的最大值和y坐标的最小值；以x坐标最大值、x坐标最小值、y坐标最大值，y坐标最小值为边界形成高难度局部路径区域。
一种参考行驶线快速生成终端，如可以执行上述参考行驶线快速生成方法的智能手机或可以执行上述参考行驶线快速生成***的车载终端控制设备。
一种计算机可读存储介质，其上存储有计算机程序，其特征在于：该程序被处理器执行参考行驶线快速生成方法中的步骤。
如上所述，本发明的具有以下有益效果：
对不同难度的路段按照行驶难度分割路径规划点，将行驶难度低的部分以几何处理的方式获得行驶参考行驶线；将行驶难度高的部分结合车动力学约束以算法处理方式获得行驶参考行驶线，再将各个部分的行驶参考行驶线拼接形成完整的行驶参考行驶线，该方法***资源占用率低，算法耗时短。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1显示为本发明的流程图。
图2显示为本发明某一时刻室内停车场中行驶参考行驶线的示意图。
图3显示为本发明下一时刻室内停车场中行驶参考行驶线的示意图。
图4显示为本发明下一时刻室内停车场中行驶参考行驶线的示意图。
图5显示为本发明预加载局部地图行驶难度分割模块分割后的示意图。
图6显示为本发明预加载局部地图行驶难度分割模块分割后高难度行驶路径的示意图。
图7显示为本发明预加载局部地图行驶难度分割模块分割后低难度行驶路径的示意图。
图8显示为本发明预加载局部地图行驶难度分割模块分割后另一部分低难度行驶路径的示意图。
图9显示为另一预加载局部地图中行驶难度分割模块分割后的示意图。
图10显示为另一预加载局部地图中行驶难度分割模块分割后某一高难度路径路径的示意图图。
100-第一低难度局部路径部分；200-第一高难度局部路径部分；300-第二低难度局部路径部分；400-第四低难度局部路径部分；500-第五高难度局部路径部分；101～106-第一低难度局部路径部分的路径点；201～211-第一高难度局部路径部分的路径点；301～305-第二低难度局部路径部分的路径点；501～521-第五高难度局部路径部分的路径点。
具体实施方式
以下通过特定的具体实例说明本发明的实施方式，本领域技术人员可由本说明书所揭露的内容轻易地了解本发明的其他优点与功效。本发明还可以通过另外不同的具体实施方式加 以实施或应用，本说明书中的各项细节也可以基于不同观点与应用，在没有背离本发明的精神下进行各种修饰或改变。需说明的是，在不冲突的情况下，以下实施例及实施例中的特征可以相互组合。
须知，本说明书所附图式所绘示的结构、比例、大小等，均仅用以配合说明书所揭示的内容，以供熟悉此技术的人士了解与阅读，并非用以限定本发明可实施的限定条件，故不具技术上的实质意义，任何结构的修饰、比例关系的改变或大小的调整，在不影响本发明所能产生的功效及所能达成的目的下，均应仍落在本发明所揭示的技术内容得能涵盖的范围内。同时，本说明书中所引用的如“上”、“下”、“左”、“右”、“中间”及“一”等的用语，亦仅为便于叙述的明了，而非用以限定本发明可实施的范围，其相对关系的改变或调整，在无实质变更技术内容下，当亦视为本发明可实施的范畴。
参见图1～图10，
一种参考行驶线快速生成方法，包括：
S01：获取预加载地图和全局路径规划，找到存在于预加载地图范围内的路径规划点和路径方向；
S02：按照行驶难度分割路径规划点：
当行驶难度高于额定值时，将该部分划分为高难度局部路径部分，并给予高难度局部路径划分编号，提取高难度局部路径部分覆盖范围内的路径规划点，形成高难度局部路径规划点集；
当行驶难度低于额定值时，将该部分划分为低难度局部路径部分，并给予低难度路径划分编号，提取低难度局部路径部分覆盖范围内的路径规划点，形成低难度路径规划点集；
高难度局部路径部分和低难度路径部分的集合等于该预加载地图中全局路径规划部分；
S03：逐一提取高难度局部路径划分编号的高难度路径规划点集，路径规划点集中的每一个路径规划点均含有该路径规划点的x坐标信息、y坐标信息，
遍历高难度路径规划点集中所有路径规划点的x坐标信息，找出x坐标的最大值和x坐标的最小值；
遍历高难度路径规划点集中所有路径规划点的y坐标信息，找出y坐标的最大值和y坐标的最小值；
以x坐标最大值、x坐标最小值、y坐标最大值，y坐标最小值为边界形成高难度局部路径区域；
S04：将每一个高难度局部路径区域的高难度路径点以算法模拟参考行驶线，将每一个低难度局部路径区域中路径规划点以几何方式获取参考行驶线；将高难度局部路径规划和低难度局部路径规划按照编号拼接，形成局部地图的路径规划。
进一步地，若步骤S04执行失败，则以搜索方式找到该高难度局部路径区域的参考行驶线；若搜索方式可以找到高难度局部路径区域参考行驶线，则用该高难度路径区域参考行驶线与剩余部分路径区域参考行驶线拼接；若搜索方式寻找高难度局部路径区域参考行驶线失败，则返回到步骤S01重新寻找存在于预加载地图范围内的路径规划点和路径方向。
进一步地，还包括一下情形：
按照行驶难度分割路径规划点：当行驶难度无法识别时，给予预加载地图范围内路径规划点以统一的划分编号。
进一步地，在步骤S01获取预加载地图和预加载地图范围内的路径规划点和路径方向时，还包括步骤S011：判断预加载地图的高度信息与车辆行驶过的前一张局部地图高度信息是否一致；若一致，则进入步骤S02；若不一致，则结束。
进一步地，步骤S04中以算法模拟参考行驶线使用的算法是：Hybrid A star算法生成参考行驶线。Hybrid A star算法的输入层包括：需要完成掉头的两条车道的中心线数据，中心线的每个点数据包含位置与朝向(x,y,theta)。Hybrid A star算法用以轨迹生成类计算，能够生成一条位置、曲率平滑的轨迹，让车辆能够完成掉头运动。Hybrid A star算法的输出层包括连接两条车道的完整轨迹，轨迹中每个点包含位置、朝向与曲率数据(x,y,theta,kappa)。
使用Hybrid A star算法来寻找可行驶轨迹。在离散的情况下Hybrid A star给出的路径不是可行驶的，但是当我们加入汽车的动力学约束后，也许可以达到题目要求的结果。
Hybrid A star算法在程序中包括以下步骤：
S041：使用动力学约束来计算Hybrid A star算法的可扩展区域，即可扩展的栅格格子；约束动力学模型的同时，HeuristicCost也需要根据U-Turn的场景进行适当的优化；
S042：删除不合理的区域，所述不合理的区域包括障碍物、地图外区域、效率低的区域；
S043：记录连续的车辆状态以及状态关联的离散栅格格子；
S044：待得到搜索结果后取出路径相关联的连续状态点数据(x，y，theta)；
S045：检查曲率是否平滑。
Hybrid A star算法在程序实现中可视化问题：可视化部分使用python的matplotlib。
Hybrid A star算法测试问题：代码部分并没有引入测试框架(gtest，boosttest等)，而是用脚本配合c++assert的轻量化方案，因为开发和测试过程中需要很多肉眼观测的辅助和批量的测试文件读取，使用c++对代码维护要求较高，而且无法做到和代码不耦合的可视化。
Hybrid A star算法在使用时，没有使用三维数组形式的真栅各地图，而是使用std::vector<std::map<Point,State>>该形式有点像稀疏矩阵的表达方式，大大节约了空间消耗，也大大减轻的坐标系转换的工作。最终的轨迹经过了拟合以及重采样，为了让轨迹是平滑的，同时也是为了计算kappa kappa的计算根据该公式得出：
Figure PCTCN2020086577-appb-000003
其中，曲线是由参数方程
Figure PCTCN2020086577-appb-000004
给出，利用参数方程求导法可以得出K值。
进一步地，Hybrid A star算法的代替方案，可以生成半圆曲线作为reference line,然后使用qp进行优化。使用目标lane的入口作为end-configuration space，然后使用Jerk minimize直接求解汽车可执行轨迹，然后检查轨迹是超过边界或存在碰撞。该方法可能导致计算出的trajectory不满足车子的物理特性，比如某些点的curve过大。
一种参考行驶线快速生成***，包括：
地图模块，所述地图模块包含某一城市的市级地图、某一区的区级地图、某一乡镇的乡镇级地图、街道级地图、或者某一室内场景的地图；
全局路径规划模块，所述全局路径规划模块包含车辆的起始点、终止点位置以及从起始点到终止点所经过的道路路径点；
行驶难度分割模块，所述行驶难度分割模块用于分割***预加载局部地图的路径，在分割前经过道路行驶难度分析，当认定行驶难度高于额定值时，将该部分划分为高难度局部路径部分，提取高难度局部路径部分覆盖范围内的路径规划点，形成高难度局部路径规划点集；当行驶难度低于额定值时，将该部分划分为低难度局部路径部分，提取低难度局部路径部分覆盖范围内的路径规划点，形成低难度路径规划点集；
参考行驶线生成模块，所述参考行驶线生成模块根据行驶难度分割模块分割结果，分别将高难度局部路径规划点和低难度局部路径规划点以不同的方式生成行驶参考行驶线，再将行驶参考行驶线拼接成完成的行驶参考行驶线。
进一步地，所述行驶难度分割模块分割高难度局部路径规划点集时，先获取高难度局部路径区域，获取方式为：
逐一提取高难度局部路径划分编号的高难度路径规划点集，路径规划点集中的每一个路径规划点均含有该路径规划点的x坐标信息、y坐标信息，遍历高难度路径规划点集中所有路径规划点的x坐标信息，找出x坐标的最大值和x坐标的最小值；遍历高难度路径规划点集中所有路径规划点的y坐标信息，找出y坐标的最大值和y坐标的最小值；以x坐标最大值、x坐标最小值、y坐标最大值，y坐标最小值为边界形成高难度局部路径区域。
一种参考行驶线快速生成终端，如可以执行上述参考行驶线快速生成方法的智能手机或可以执行上述参考行驶线快速生成***的车载终端控制设备。
一种计算机可读存储介质，其上存储有计算机程序，其特征在于：该程序被处理器执行参考行驶线快速生成方法中的步骤。
作为优选实施例，本实施例还提供一种终端设备，如可以执行程序的智能手机、平板电脑、笔记本电脑、台式计算机、机架式云端、刀片式云端、塔式云端或机柜式云端(包括独立的云端，或者多个云端所组成的云端集群)等。本实施例的终端设备至少包括但不限于：可通过***总线相互通信连接的存储器、处理器。需要指出的是，具有组件存储器、处理器的终端设备，但是应理解的是，并不要求实施所有示出的组件，可以替代的符合车辆动力学的参考行驶线生成方法实施更多或者更少的组件。
作为优选实施例，存储器(即可读存储介质)包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，存储器可以是计算机设备的内部存储单元，例 如该计算机设备的硬盘或内存。在另一些实施例中，存储器也可以是计算机设备的外部存储设备，例如该计算机设备上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。当然，存储器还可以既包括计算机设备的内部存储单元也包括其外部存储设备。本实施例中，存储器通常用于存储安装于计算机设备的操作***和各类应用软件，例如实施例中的符合车辆动力学的参考行驶线生成方法程序代码等。此外，存储器还可以用于暂时地存储已经输出或者将要输出的各类数据。
本实施例还提供一种计算机可读存储介质，如闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘、云端、App应用商城等等，其上存储有计算机程序，程序被处理器执行时实现相应功能。本实施例的计算机可读存储介质用于存储符合车辆动力学的参考行驶线生成方法程序，被处理器执行时实现符合车辆动力学的参考行驶线生成方法程序实施例中的符合车辆动力学的参考行驶线生成方法。
上述实施例仅例示性说明本发明的原理及其功效，而非用于限制本发明。任何熟悉此技术的人士皆可在不违背本发明的精神及范畴下，对上述实施例进行修饰或改变。因此，举凡所属技术领域中包括通常知识者在未脱离本发明所揭示的精神与技术思想下所完成的一切等效修饰或改变，仍应由本发明的权利要求所涵盖。

Claims (11)

  1. 一种参考行驶线快速生成方法，其特征在于，包括：
    S01：获取预加载地图和全局路径规划，找到存在于预加载地图范围内的路径规划点和路径方向；
    S02：按照行驶难度分割路径规划点：
    当行驶难度高于额定值时，将该部分划分为高难度局部路径部分，并给予高难度局部路径划分编号，提取高难度局部路径部分覆盖范围内的路径规划点，形成高难度局部路径规划点集；
    当行驶难度低于额定值时，将该部分划分为低难度局部路径部分，并给予低难度路径划分编号，提取低难度局部路径部分覆盖范围内的路径规划点，形成低难度路径规划点集；
    高难度局部路径部分和低难度路径部分的集合等于该预加载地图中全局路径规划部分；
    S03：逐一提取高难度局部路径划分编号的高难度路径规划点集，路径规划点集中的每一个路径规划点均含有该路径规划点的x坐标信息、y坐标信息，
    遍历高难度路径规划点集中所有路径规划点的x坐标信息，找出x坐标的最大值和x坐标的最小值；
    遍历高难度路径规划点集中所有路径规划点的y坐标信息，找出y坐标的最大值和y坐标的最小值；
    以x坐标最大值、x坐标最小值、y坐标最大值，y坐标最小值为边界形成高难度局部路径区域；
    S04：将每一个高难度局部路径区域的高难度路径点以算法模拟参考行驶线，将每一个低难度局部路径区域中路径规划点以几何方式获取参考行驶线；将高难度局部路径规划和低难度局部路径规划按照编号拼接，形成局部地图的路径规划。
  2. 根据权利要求1所述的参考行驶线快速生成方法，其特征在于，还包括一下情形：
    按照行驶难度分割路径规划点：当行驶难度无法识别时，给予预加载地图范围内路径规划点以统一的划分编号。
  3. 根据权利要求1所述的参考行驶线快速生成方法，其特征在于，在步骤S01获取预加载地图和预加载地图范围内的路径规划点和路径方向时，还包括步骤S011：判断预加载地图的高度信息与车辆行驶过的前一张局部地图高度信息是否一致；若一致，则进入步骤S02；若不一致，则结束。
  4. 根据权利要求1所述的参考行驶线快速生成方法，其特征在于，步骤S04中以算法模拟参考行驶线使用的算法是：Hybrid A star算法生成参考行驶线；
    所述Hybrid A star算法的输入层包括：需要完成掉头的两条车道的中心线数据，中心线的每个点数据包含位置与朝向(x,y,theta)；
    所述Hybrid A star算法用以轨迹生成类计算，能够生成一条位置、曲率平滑的轨迹，让车辆能够完成掉头运动；
    所述Hybrid A star算法输出层包括连接两条车道的完整轨迹，轨迹中每个点包含位置、朝向与曲率数据(x,y,theta,kappa)。
  5. 根据权利要求1所述的参考行驶线快速生成方法，其特征在于，Hybrid A star算法在程序中包括以下步骤：
    S041：使用动力学约束来计算Hybrid A star算法的可扩展区域，即可扩展的栅格格子；约束动力学模型的同时，HeuristicCost也需要根据U-Turn的场景进行适当的优化；
    S042：删除不合理的区域，所述不合理的区域包括障碍物、地图外区域、效率低的区域；
    S043：记录连续的车辆状态以及状态关联的离散栅格格子；
    S044：待得到搜索结果后取出路径相关联的连续状态点数据(x，y，theta)；
    S045：检查曲率是否平滑。
  6. 根据权利要求1所述的参考行驶线快速生成方法，其特征在于，所述Hybrid A star算法在使用时，没有使用三维数组形式的真栅各地图，而是使用std::vector<std::map<Point,State>>形式，形成有点像稀疏矩阵的表达方式。
  7. 根据权利要求1所述的参考行驶线快速生成方法，其特征在于，S045步骤检测曲率是否平滑经过了拟合以及重采样，曲率表达式：
    Figure PCTCN2020086577-appb-100001
  8. 一种参考行驶线快速生成***，其特征在于，包括：
    地图模块，所述地图模块包含某一城市的市级地图、某一区的区级地图、某一乡镇的乡镇级地图、街道级地图、或者某一室内场景的地图；
    全局路径规划模块，所述全局路径规划模块包含车辆的起始点、终止点位置以及从起始点到终止点所经过的道路路径点；
    行驶难度分割模块，所述行驶难度分割模块用于分割***预加载局部地图的路径，在分割前经过道路行驶难度分析，当认定行驶难度高于额定值时，将该部分划分为高难度局部路径部分，提取高难度局部路径部分覆盖范围内的路径规划点，形成高难度局部路径规划点集；当行驶难度低于额定值时，将该部分划分为低难度局部路径部分，提取低难度局部路径部分覆盖范围内的路径规划点，形成低难度路径规划点集；
    参考行驶线生成模块，所述参考行驶线生成模块根据行驶难度分割模块分割结果，分别将高难度局部路径规划点和低难度局部路径规划点以不同的方式生成行驶参考行驶线，再将行驶参考行驶线拼接成完成的行驶参考行驶线。
  9. 根据权利要求9所述的参考行驶线快速生成***，其特征在于，所述行驶难度分割模块分割高难度局部路径规划点集时，先获取高难度局部路径区域，获取方式为：
    逐一提取高难度局部路径划分编号的高难度路径规划点集，路径规划点集中的每一个路径规划点均含有该路径规划点的x坐标信息、y坐标信息，遍历高难度路径规划点集中所有路径规划点的x坐标信息，找出x坐标的最大值和x坐标的最小值；遍历高难度路径规划点集中所有路径规划点的y坐标信息，找出y坐标的最大值和y坐标的最小值；以x坐标最大值、x坐标最小值、y坐标最大值，y坐标最小值为边界形成高难度局部路径区域。
  10. 一种终端设备，其特征在于：如可以执行上述权利要求1-7所述的参考行驶线快速生成方法的智能手机或可以执行上述8-9所述的参考行驶线快速生成***的车载终端控制设备。
  11. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于：该程序被处理器执行时实现如权利要求1至7任一权利要求所述的方法中的步骤。
PCT/CN2020/086577 2019-04-26 2020-04-24 一种参考行驶线快速生成方法、***、终端和存储介质 WO2020216315A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20794378.8A EP3951321A4 (en) 2019-04-26 2020-04-24 METHOD AND SYSTEM FOR RAPID GENERATING REFERENCE DRIVING ROUTE, TERMINAL AND STORAGE MEDIA
US17/606,559 US11592305B2 (en) 2019-04-26 2020-04-24 Method, system, terminal, and storage medium for rapid generation of reference lines

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910343032.4A CN110207716B (zh) 2019-04-26 2019-04-26 一种参考行驶线快速生成方法、***、终端和存储介质
CN201910343032.4 2019-04-26

Publications (1)

Publication Number Publication Date
WO2020216315A1 true WO2020216315A1 (zh) 2020-10-29

Family

ID=67786553

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/086577 WO2020216315A1 (zh) 2019-04-26 2020-04-24 一种参考行驶线快速生成方法、***、终端和存储介质

Country Status (4)

Country Link
US (1) US11592305B2 (zh)
EP (1) EP3951321A4 (zh)
CN (1) CN110207716B (zh)
WO (1) WO2020216315A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112762950A (zh) * 2020-12-15 2021-05-07 浙江大学 基于人工势场引导的Hybrid A*自主泊车路径规划方法
CN113091750A (zh) * 2021-04-12 2021-07-09 京东数科海益信息科技有限公司 局部路径规划方法、装置、计算机设备和存储介质
CN114676939A (zh) * 2022-05-26 2022-06-28 之江实验室 一种多车型参数自适应的参考线平滑方法和***
CN115077557A (zh) * 2022-07-28 2022-09-20 苏州轻棹科技有限公司 一种路口掉头的路径规划方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110207716B (zh) 2019-04-26 2021-08-17 纵目科技（上海）股份有限公司 一种参考行驶线快速生成方法、***、终端和存储介质
CN111426330B (zh) * 2020-03-24 2022-03-15 江苏徐工工程机械研究院有限公司 路径生成方法和设备、无人化运输***和存储介质
CN112362074B (zh) * 2020-10-30 2024-03-19 重庆邮电大学 一种结构化环境下的智能车辆局部路径规划方法
CN112964271B (zh) * 2021-03-15 2023-03-31 西安交通大学 一种面向多场景的自动驾驶规划方法及***
CN113310492B (zh) * 2021-05-27 2023-04-14 青岛星华智能装备有限公司 一种基于a星算法的单舵轮agv路径规划方法和***
CN114379569B (zh) * 2022-01-19 2023-11-07 浙江菜鸟供应链管理有限公司 一种生成驾驶参考线的方法及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130211656A1 (en) * 2012-02-09 2013-08-15 Electronics And Telecommunications Research Institute Autonomous driving apparatus and method for vehicle
CN103940434A (zh) * 2014-04-01 2014-07-23 西安交通大学 基于单目视觉和惯性导航单元的实时车道线检测***
CN105955273A (zh) * 2016-05-25 2016-09-21 速感科技（北京）有限公司 室内机器人导航***及方法
CN108673496A (zh) * 2018-05-02 2018-10-19 苏州智伟达机器人科技有限公司 一种基于纯追踪模型的工业机器人路径跟踪方法
CN108829105A (zh) * 2018-06-21 2018-11-16 浙江工业大学 一种基于km算法和人工势场法的仓储物流调度避障优化方法
CN110196592A (zh) * 2019-04-26 2019-09-03 纵目科技（上海）股份有限公司 一种轨迹线的更新方法、***、终端和存储介质
CN110207716A (zh) * 2019-04-26 2019-09-06 纵目科技（上海）股份有限公司 一种参考行驶线快速生成方法、***、终端和存储介质

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5590950B2 (ja) * 2010-04-12 2014-09-17 アルパイン株式会社 ナビゲーション装置および誘導経路探索方法
US9686451B2 (en) * 2015-01-21 2017-06-20 Toyota Jidosha Kabushiki Kaisha Real time driving difficulty categorization
JP6304104B2 (ja) * 2015-04-01 2018-04-04 トヨタ自動車株式会社 走行環境評価システム
US20170292843A1 (en) * 2016-04-07 2017-10-12 Delphi Technologies, Inc. Automated vehicle route planner with route difficulty scoring
CN106403970A (zh) * 2016-06-27 2017-02-15 百度在线网络技术（北京）有限公司 一种路网数据处理方法及装置
JP6769892B2 (ja) * 2017-02-22 2020-10-14 クラリオン株式会社 ナビゲーション装置、経路探索サーバ、および経路探索方法
US10816973B2 (en) * 2017-06-02 2020-10-27 Baidu Usa Llc Utilizing rule-based and model-based decision systems for autonomous driving control
US11003183B2 (en) * 2017-09-13 2021-05-11 Baidu Usa Llc Driving scene based path planning for autonomous driving vehicles
CN108981739B (zh) * 2018-06-08 2022-02-22 南方科技大学 一种路径规划方法、装置、服务器及存储介质
US11604464B2 (en) * 2018-10-30 2023-03-14 Here Global B.V. Virtual valet
CN109806590B (zh) * 2019-02-21 2020-10-09 腾讯科技（深圳）有限公司 对象控制方法和装置、存储介质及电子装置
CN111121814A (zh) * 2020-01-08 2020-05-08 百度在线网络技术（北京）有限公司 导航方法、装置、电子设备及计算机可读存储介质
CN113970919A (zh) * 2020-07-21 2022-01-25 图森有限公司 用于自动路线导航的***和方法
US11643103B2 (en) * 2020-09-24 2023-05-09 GM Global Technology Operations LLC Navigation considering route driving difficulty

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130211656A1 (en) * 2012-02-09 2013-08-15 Electronics And Telecommunications Research Institute Autonomous driving apparatus and method for vehicle
CN103940434A (zh) * 2014-04-01 2014-07-23 西安交通大学 基于单目视觉和惯性导航单元的实时车道线检测***
CN105955273A (zh) * 2016-05-25 2016-09-21 速感科技（北京）有限公司 室内机器人导航***及方法
CN108673496A (zh) * 2018-05-02 2018-10-19 苏州智伟达机器人科技有限公司 一种基于纯追踪模型的工业机器人路径跟踪方法
CN108829105A (zh) * 2018-06-21 2018-11-16 浙江工业大学 一种基于km算法和人工势场法的仓储物流调度避障优化方法
CN110196592A (zh) * 2019-04-26 2019-09-03 纵目科技（上海）股份有限公司 一种轨迹线的更新方法、***、终端和存储介质
CN110207716A (zh) * 2019-04-26 2019-09-06 纵目科技（上海）股份有限公司 一种参考行驶线快速生成方法、***、终端和存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3951321A4 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112762950A (zh) * 2020-12-15 2021-05-07 浙江大学 基于人工势场引导的Hybrid A*自主泊车路径规划方法
CN113091750A (zh) * 2021-04-12 2021-07-09 京东数科海益信息科技有限公司 局部路径规划方法、装置、计算机设备和存储介质
CN114676939A (zh) * 2022-05-26 2022-06-28 之江实验室 一种多车型参数自适应的参考线平滑方法和***
CN114676939B (zh) * 2022-05-26 2022-09-02 之江实验室 一种多车型参数自适应的参考线平滑方法和***
CN115077557A (zh) * 2022-07-28 2022-09-20 苏州轻棹科技有限公司 一种路口掉头的路径规划方法
CN115077557B (zh) * 2022-07-28 2024-05-03 苏州轻棹科技有限公司 一种路口掉头的路径规划方法

Also Published As

Publication number Publication date
EP3951321A8 (en) 2022-11-23
CN110207716A (zh) 2019-09-06
US11592305B2 (en) 2023-02-28
US20220214182A1 (en) 2022-07-07
EP3951321A4 (en) 2022-08-24
CN110207716B (zh) 2021-08-17
EP3951321A1 (en) 2022-02-09

Similar Documents

Publication Publication Date Title
WO2020216315A1 (zh) 一种参考行驶线快速生成方法、***、终端和存储介质
CN110196592B (zh) 一种轨迹线的更新方法、***、终端和存储介质
JP6595182B2 (ja) マッピング、位置特定、及び姿勢補正のためのシステム及び方法
CN108732556B (zh) 一种基于几何体求交运算的车载激光雷达仿真方法
US10109106B2 (en) Scalable curve visualization for conformance testing in vehicle simulation
US11967006B2 (en) Systems and methods for generating road map based on level of nodes and target links
CN113899384B (zh) 车道级道路的路口面显示方法、装置、设备、介质及程序
EP3620945A1 (en) Obstacle distribution simulation method, device and terminal based on multiple models
WO2022121207A1 (zh) 轨迹规划方法、装置、设备、存储介质和程序产品
JP2022166248A (ja) 車両の測位方法、装置及び自動運転車両
CN113971723B (zh) 高精地图中三维地图的构建方法、装置、设备和存储介质
CN110782774A (zh) 一种众包道路数据的分布式处理方法及装置
JP2023022185A (ja) 地図データ処理方法及び装置、電子機器、記憶媒体、並びにコンピュータプログラム
WO2022199195A1 (zh) 地图更新方法、***、车载终端、服务器及存储介质
CN114863047A (zh) 路口虚拟线绘制方法、装置、电子设备及计算机程序产品
CN114661028A (zh) 智能驾驶控制器测试方法、装置、计算机设备和存储介质
EP4206610A1 (en) Map matching method and apparatus, and electronic device and storage medium
CN112507891B (zh) 自动化识别高速路口并构建路口向量的方法及装置
CN109520513B (zh) 一种三维地图绘制方法及装置
CN116753936A (zh) 基于众源视觉图像的自动驾驶矢量地图在线构建方法
CN116107576A (zh) 页面组件的渲染方法、装置、电子设备和车辆
CN113432618A (zh) 轨迹生成方法、装置、计算设备及计算机可读存储介质
CN116502479B (zh) 一种三维物体在仿真环境中的碰撞检测方法和装置
CN113990066B (zh) 道路信息匹配及路口识别方法及装置
CN115438517B (zh) 仿真地图生成方法、电子设备及计算机存储介质

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: 20794378

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020794378

Country of ref document: EP

Effective date: 20211027