WO2022143560A1 - Vehicle turning path planning method and apparatus, vehicle, and storage medium - Google Patents

Vehicle turning path planning method and apparatus, vehicle, and storage medium Download PDF

Info

Publication number
WO2022143560A1
WO2022143560A1 PCT/CN2021/141754 CN2021141754W WO2022143560A1 WO 2022143560 A1 WO2022143560 A1 WO 2022143560A1 CN 2021141754 W CN2021141754 W CN 2021141754W WO 2022143560 A1 WO2022143560 A1 WO 2022143560A1
Authority
WO
WIPO (PCT)
Prior art keywords
position information
turning
cost
path
turning path
Prior art date
Application number
PCT/CN2021/141754
Other languages
French (fr)
Chinese (zh)
Inventor
冯壮
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 WO2022143560A1 publication Critical patent/WO2022143560A1/en

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
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Definitions

  • the present invention relates to the technical field of artificial intelligence, and in particular, to a vehicle turning path planning method, device, vehicle and storage medium.
  • sampling There are generally three methods for path planning of autonomous vehicles: sampling, optimization, and search. Among them, the method based on sampling is the most efficient one, so it is also the most widely used in the market.
  • the sampling-based method is not flexible enough in complex environments, such as parking lots, mixed pedestrian and vehicle communities, etc., and cannot take into account the kinematic characteristics of the vehicle and complex driving needs, and is powerless for situations such as large-angle turns.
  • embodiments of the present invention are proposed to provide a vehicle turning path planning method and a corresponding vehicle turning path planning device, vehicle, and storage medium that overcome or at least partially solve the above problems.
  • an embodiment of the present invention discloses a method for planning a turning path of a vehicle, and the method includes:
  • the cost of the turning path is calculated, and the turning path with the smallest cost is selected as the target turning path.
  • the determining the sampling range and the turning arc length according to the navigation path includes:
  • the sampling range and the turning arc length are determined according to the position information of the end point of the curve.
  • the determining the sampling range and the turning arc length according to the position information of the end point of the curve includes:
  • the turning arc length is calculated according to the current vehicle position information and the curve end point position information.
  • the current vehicle position information includes a first coordinate position and a first heading angle
  • the target vehicle position information includes a second heading angle
  • the curve end point position information includes a third coordinate position
  • the calculated The cost of the turning path is selected, and the turning path with the minimum cost is selected as the target turning path, including:
  • a heading angle difference cost is calculated according to the first heading angle and the second heading angle, wherein the heading angle difference cost is less than a second preset threshold;
  • the distance cost, the heading angle difference cost and the curvature change cost are weighted and summed to obtain the total cost of the turning path, and the turning path with the smallest total cost is selected as the target turning path.
  • the calculation of the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length includes:
  • the fifth spiral parameter is calculated according to the current vehicle position information, the target vehicle position information and the turning arc length.
  • the target vehicle position information includes a second curvature and a second curvature change rate, wherein the second curvature is smaller than a third preset threshold, and the second curvature change rate is smaller than a fourth preset threshold.
  • the embodiment of the present invention discloses a vehicle turning path planning device, and the device includes:
  • a location information acquisition module configured to acquire the current vehicle location information of the vehicle and a pre-planned navigation path
  • a sampling range determination module configured to determine the sampling range and the turning arc length according to the navigation path
  • a position information sampling module used for sampling the sampling range to obtain target vehicle position information
  • a helix parameter calculation module configured to calculate a helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length;
  • a turning path calculation module used for calculating the turning path according to the helix parameters
  • the target turning path selection module is used to calculate the cost of the turning path, and select the turning path with the minimum cost as the target turning path.
  • the sampling range determination module includes:
  • a position information confirmation submodule used for determining the position information of the end point of the curve in the navigation path
  • a sampling range confirmation sub-module configured to determine the sampling range and the turning arc length according to the position information of the end point of the curve.
  • the sampling range confirmation sub-module includes:
  • a sampling range calculation unit configured to calculate the sampling range according to the position information of the end point of the curve and preset parameters
  • a curve arc length calculation unit configured to calculate the turning arc length according to the current vehicle position information and the position information of the end point of the curve.
  • the current vehicle position information includes a first coordinate position and a first heading angle
  • the target vehicle position information includes a second heading angle
  • the curve end point position information includes a third coordinate position
  • the target turning Path selection module including:
  • a coordinate position calculation submodule configured to calculate the second coordinate position of the target vehicle position information according to the helix parameter and the turning arc length;
  • a distance cost calculation submodule configured to calculate a distance cost according to the first coordinate position, the second coordinate position and the third coordinate position, wherein the distance cost is less than a first preset threshold
  • a heading angle difference cost calculation sub-module configured to calculate a heading angle difference cost according to the first heading angle and the second heading angle, wherein the heading angle difference cost is less than a second preset threshold
  • a curvature change cost calculation submodule configured to calculate a curvature change cost according to the turning arc length and the helix parameter
  • a target turning path selection sub-module used for weighted summation of the distance cost, the heading angle difference cost and the curvature change cost to obtain the total cost of the turning path, and select the minimum cost of the total cost.
  • a turning path is used as the target turning path.
  • the helix parameter calculation module includes:
  • the helix parameter calculation sub-module is configured to calculate the fifth helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length.
  • the target vehicle position information includes a second curvature and a second curvature change rate, wherein the second curvature is smaller than a third preset threshold, and the second curvature change rate is smaller than a fourth preset threshold.
  • An embodiment of the present invention discloses a vehicle, including a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program being executed by the processor to achieve the above-mentioned The steps of a vehicle turning path planning method.
  • An embodiment of the present invention discloses a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned method for planning a turning path of a vehicle are implemented.
  • the current vehicle position information of the vehicle and the pre-planned navigation path are obtained, the sampling range and the turning arc length are determined according to the navigation path, the sampling range is sampled, and the target vehicle position information is obtained.
  • the position information of the target vehicle and the length of the turning arc are used to calculate the helix parameters, the turning path is calculated according to the helix parameters, the cost of the turning path is calculated, and the turning path with the minimum cost is selected as the target turning path.
  • the current vehicle position information is acquired, and at the same time, multiple target vehicle position information is sampled from the sampling range, and the corresponding spiral parameters are calculated by the current vehicle position information and the multiple target vehicle position information, and multiple target vehicles are determined.
  • the turning path corresponding to the location information, and by calculating the cost of the turning path, the target turning path with the least cost is selected from the multiple turning paths, which can adapt to various complex and large-angle turning environments, such as parking lots, people and vehicles. In mixed communities and other places, the optimal target turning path can be quickly determined, turning comfortably, bringing users an excellent automatic driving experience.
  • Fig. 1 is a flow chart of steps of an embodiment of a vehicle turning path planning method according to the present invention
  • FIG. 2 is a flow chart of steps of another embodiment of a vehicle turning path planning method according to the present invention.
  • Fig. 3 is a kind of vehicle turning path planning schematic diagram of the present invention.
  • FIG. 4 is a structural block diagram of an embodiment of a vehicle turning path planning device according to the present invention.
  • FIG. 1 a flow chart of steps of an embodiment of a vehicle turning path planning method of the present invention is shown.
  • the embodiment of the present invention may specifically include the following steps:
  • Step 101 Acquire current vehicle position information of the vehicle and a pre-planned navigation path.
  • the navigation path is the path from the departure place to the destination planned by a third-party map platform or other global planning methods.
  • the current vehicle position information of the vehicle at the current moment and the starting point to the destination planned by a third-party map platform or other global planning methods are obtained.
  • Navigation path of the ground is obtained.
  • Step 102 Determine the sampling range and the turning arc length according to the navigation path.
  • the turning arc length is the arc length of the curve ahead of the vehicle. Specifically, after the vehicle perceives a curve ahead and obtains the current vehicle position information and the navigation path, the sampling range is determined according to the end point of the curve in the navigation path, and the direct turning arc length between the current vehicle position and the end point of the curve.
  • Step 103 Sampling the sampling range to obtain target vehicle location information.
  • sampling is started within the sampling range to obtain a plurality of target vehicle position information.
  • Step 104 Calculate the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length.
  • Step 105 Calculate the turning path according to the helix parameters.
  • the turning path corresponding to the target vehicle position information is calculated according to the fifth-order helix parameter.
  • Step 106 Calculate the cost of the turning path, and select the turning path with the minimum cost as the target turning path.
  • the calculated costs of multiple turning paths are compared, and the turning path with the minimum cost is selected as the target turning path, and the vehicle is controlled to pass the front comfortably according to the target turning path. corner.
  • the current vehicle position information of the vehicle and the pre-planned navigation path are obtained, the sampling range and the turning arc length are determined according to the navigation path, the sampling range is sampled, and the target vehicle position information is obtained.
  • the position information, target vehicle position information and turning arc length are used to calculate the helix parameters, the turning path is calculated according to the helix parameters, the cost of the turning path is calculated, and the turning path with the minimum cost is selected as the target turning path.
  • the current vehicle position information is acquired, and at the same time, multiple target vehicle position information is sampled from the sampling range, and the corresponding spiral parameters are calculated by the current vehicle position information and the multiple target vehicle position information, and multiple target vehicles are determined.
  • the turning path corresponding to the location information, and by calculating the cost of the turning path, the target turning path with the least cost is selected from the multiple turning paths, which can adapt to various complex and large-angle turning environments, such as parking lots, people and vehicles. In mixed communities and other places, the optimal target turning path can be quickly determined, turning comfortably, bringing users an excellent automatic driving experience.
  • FIG. 2 there is shown a flow chart of the steps of another vehicle turning path planning method embodiment of the present invention, and the embodiment of the present invention may specifically include the following steps:
  • Step 101 Acquire current vehicle position information of the vehicle and a pre-planned navigation path.
  • Step 102 Determine the position information of the end point of the curve in the navigation path.
  • the middle of the end position of the curve is acquired according to the navigation path as the end point of the curve, and the position information of the end point of the curve is acquired.
  • Step 103 Determine the sampling range and the turning arc length according to the position information of the end point of the curve.
  • the determining the sampling range and the turning arc length according to the position information of the end point of the curve includes: calculating the sampling range according to the position information of the end point of the curve and a preset parameter; The turning arc length is calculated according to the current vehicle position information and the curve end point position information.
  • the obtained position information of the end point of the curve includes the third coordinate position (x t , y t ), the third heading angle ⁇ t , the third curvature k t and the third curvature change rate dk t , and the preset parameter is ⁇ , ⁇ k, ⁇ dk.
  • the third curvature k t and the third curvature change rate dk t in the position information of the end point of the curve and the preset parameters ⁇ , ⁇ k , ⁇ dk calculates the sampling range ⁇ t - ⁇ t + ⁇ , k t - ⁇ k ⁇ k t + ⁇ k, dk t - ⁇ dk ⁇ dk t + ⁇ dk; the turning arc length s f is to intercept the current vehicle position in the original navigation path The curve path between the curve end point and the curve end point is calculated, and the turn arc length is the curve length.
  • Step 104 Sampling the sampling range to obtain target vehicle location information.
  • sampling is performed in the sampling range to obtain the first position information of the target vehicle.
  • Two heading angle ⁇ 1 , second curvature k 1 and second curvature change rate dk 1 wherein the sampling steps of heading angle, curvature and curvature change rate are ⁇ step , k step , dk step , so the total number of samples is It should be noted that the sampled vehicle position information does not include the coordinate position.
  • Step 105 Calculate the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length.
  • the current vehicle position information includes a first coordinate position (x 0 , y 0 ), a first heading angle ⁇ 0 , a first curvature k 0 and a first curvature change rate dk 0 .
  • the first heading angle ⁇ 0 the first curvature k 0 and the first curvature change rate dk 0 in the current vehicle position information
  • ⁇ (s) a 0 +a 1 s+a 2 s 2 +a 3 s 3 +a 4 s 4 +a 5 s 5
  • k (s) a 1 +2a 2 s+3a 3 s 2 +4a 4 s 3 +5a 5 s 4
  • Step 106 Calculate the turning path according to the helix parameters.
  • the six helical parameters a 0 , a 1 , a 2 , a 3 , a 4 , and a 5 are obtained by calculation, the six helical parameters and any turning arc length s in the curve can be substituted into the following formula:
  • ⁇ (s) a 0 +a 1 s+2a 2 s 2 +3a 3 s 3 +4a 4 s 4 +5a 5 s 5
  • the coordinate position corresponding to any turning arc length s f in the curve can be obtained, that is, all the coordinate positions in the turning path can be obtained.
  • FIG. 3 it is a schematic diagram of a vehicle turning path planning according to the present invention.
  • the current vehicle position information of the vehicle and the position information of multiple target vehicles it can be calculated according to the current vehicle position information and the position information of multiple target vehicles.
  • a plurality of sampling spirals (turning paths) are obtained, and the positions of the calculated end points of the plurality of turning paths are near the position of the end point of the curve.
  • Step 107 Calculate the cost of the turning path, and select the turning path with the minimum cost as the target turning path.
  • the current vehicle position information includes a first coordinate position and a first heading angle
  • the target vehicle position information includes a second heading angle
  • the curve end point position information includes a third coordinate position
  • the calculating the cost of the turning path and selecting the turning path with the minimum cost as the target turning path, including: calculating the second coordinate position of the target vehicle position information according to the helix parameter and the turning arc length ; Calculate a distance cost according to the first coordinate position, the second coordinate position and the third coordinate position, wherein the distance cost is less than a first preset threshold;
  • the heading angle difference cost is calculated by the heading angle, wherein the heading angle difference cost is smaller than the second preset threshold;
  • the curvature change cost is calculated according to the turning arc length and the helix parameter;
  • the heading angle difference cost and the curvature change cost are weighted and summed to obtain the total cost of the turning path, and the turning path with the smallest total cost is selected as the target turning path
  • the second coordinate position of the target vehicle position information can be calculated by bringing the fifth helix parameter and the turning arc length into the following formula:
  • ⁇ (s) a 0 +a 1 s+2a 2 s 2 +3a 3 s 3 +4a 4 s 4 +5a 5 s 5
  • the heading angle difference cost is calculated according to the first heading angle and the second heading angle, and the calculation formula is as follows:
  • the cost of curvature change is calculated according to the turning arc length and the helix parameters.
  • the calculation formula is as follows:
  • the distance cost, heading angle difference cost and curvature change cost are weighted and summed to obtain the total cost of the turning path, and the turning path with the smallest total cost is selected as the target.
  • the turning path in addition, for the rigid requirements of the turning path, the calculated distance cost must be less than the first preset threshold, and the heading angle difference cost must be less than the second preset threshold, as follows:
  • the optimal turning path can be quickly selected in a complex road environment, and the vehicle can be controlled according to the The turning path is comfortable through the bends in front of the vehicle.
  • the target vehicle position information includes a second curvature and a second curvature change rate, wherein the second curvature is less than a third preset threshold, and the second curvature change rate is less than a fourth preset threshold Set the threshold.
  • the second curvature is required to be smaller than the third preset threshold, and the second curvature change rate is smaller than the fourth preset threshold.
  • the distance cost must be less than the first preset threshold
  • the heading angle difference cost must be less than the second preset threshold
  • the second curvature must be less than the third preset threshold
  • the embodiment of the present invention adopts the quintic helix, which can cover more complex road conditions compared with other polynomial curves, and the embodiment of the present invention is not limited to the quintic helix. , four times, three times and even other times can also be used.
  • the current vehicle position information of the vehicle and the pre-planned navigation path are obtained, the position information of the end point of the curve is determined in the navigation path, and the sampling range and the length of the turning arc are determined according to the position information of the end point of the curve , Sampling the sampling range to obtain the target vehicle position information, calculate the helix parameters according to the current vehicle position information, the target vehicle position information and the turning arc length, calculate the turning path according to the helix parameters, calculate the cost of the turning path, and select the one with the smallest cost.
  • the turn path serves as the target turn path.
  • the current vehicle position information is acquired, and at the same time, multiple target vehicle position information is sampled from the sampling range, and the corresponding spiral parameters are calculated by the current vehicle position information and the multiple target vehicle position information, and multiple target vehicles are determined.
  • the turning path corresponding to the location information, and by calculating the cost of the turning path, the target turning path with the least cost is selected from the multiple turning paths, which can adapt to various complex and large-angle turning environments, such as parking lots, people and vehicles. In mixed communities and other places, the optimal target turning path can be quickly determined, turning comfortably and bringing users an excellent automatic driving experience.
  • the distance cost must be less than the first preset threshold
  • the heading angle difference cost must be less than the second preset threshold
  • the second curvature must be less than the third preset threshold
  • the second curvature change rate If it is less than the fourth preset threshold, it can ensure that the turning path planned by the vehicle will not deviate from the real curve path and can drive safely.
  • FIG. 4 a structural block diagram of an embodiment of a vehicle turning path planning device of the present invention is shown.
  • the embodiment of the present invention may specifically include the following modules:
  • a location information acquisition module 401 configured to acquire the current vehicle location information of the vehicle and a pre-planned navigation path
  • a sampling range determination module 402 configured to determine a sampling range and a turning arc length according to the navigation path
  • a location information sampling module 403, configured to sample the sampling range to obtain target vehicle location information
  • the helix parameter calculation module 404 is used to calculate the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length;
  • a turning path calculation module 405, configured to calculate a turning path according to the helix parameters
  • the target turning path selection module 406 is configured to calculate the cost of the turning path, and select the turning path with the minimum cost as the target turning path.
  • the sampling range determination module 402 includes:
  • a position information confirmation submodule used for determining the position information of the end point of the curve in the navigation path
  • a sampling range confirmation sub-module configured to determine the sampling range and the turning arc length according to the position information of the end point of the curve.
  • the sampling range confirmation sub-module includes:
  • a sampling range calculation unit configured to calculate the sampling range according to the position information of the end point of the curve and preset parameters
  • a curve arc length calculation unit configured to calculate the turning arc length according to the current vehicle position information and the position information of the end point of the curve.
  • the current vehicle position information includes a first coordinate position and a first heading angle
  • the target vehicle position information includes a second heading angle
  • the curve end point position information includes a third coordinate position
  • the target turning path selection module 406 includes:
  • a coordinate position calculation submodule configured to calculate the second coordinate position of the target vehicle position information according to the helix parameter and the turning arc length;
  • a distance cost calculation submodule configured to calculate a distance cost according to the first coordinate position, the second coordinate position and the third coordinate position, wherein the distance cost is less than a first preset threshold
  • a heading angle difference cost calculation sub-module configured to calculate a heading angle difference cost according to the first heading angle and the second heading angle, wherein the heading angle difference cost is less than a second preset threshold
  • a curvature change cost calculation submodule configured to calculate a curvature change cost according to the turning arc length and the helix parameter
  • a target turning path selection sub-module used for weighted summation of the distance cost, the heading angle difference cost and the curvature change cost to obtain the total cost of the turning path, and select the minimum cost of the total cost.
  • a turning path is used as the target turning path.
  • the spiral parameter calculation module 404 includes:
  • the helix parameter calculation sub-module is configured to calculate the fifth helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length.
  • the target vehicle position information includes a second curvature and a second curvature change rate, wherein the second curvature is less than a third preset threshold, and the second curvature change rate is less than a fourth preset threshold Set the threshold.
  • the current vehicle position information of the vehicle and the pre-planned navigation path are obtained, the sampling range and the turning arc length are determined according to the navigation path, and the sampling range is sampled to obtain the target vehicle position information.
  • the position information, target vehicle position information and turning arc length are used to calculate the helix parameters, the turning path is calculated according to the helix parameters, the cost of the turning path is calculated, and the turning path with the minimum cost is selected as the target turning path.
  • the current vehicle position information is acquired, and at the same time, multiple target vehicle position information is sampled from the sampling range, and the corresponding spiral parameters are calculated by the current vehicle position information and the multiple target vehicle position information, and multiple target vehicles are determined.
  • the turning path corresponding to the location information, and by calculating the cost of the turning path, the target turning path with the least cost is selected from the multiple turning paths, which can adapt to various complex and large-angle turning environments, such as parking lots, people and vehicles. In mixed communities and other places, the optimal target turning path can be quickly determined, turning comfortably, bringing users an excellent automatic driving experience.
  • An embodiment of the present invention discloses a vehicle, including a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program being executed by the processor to implement the above-mentioned turning of the vehicle The steps described in the embodiment of the path planning method.
  • An embodiment of the present invention discloses a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps described in the above embodiments of the method for planning a turning path of a vehicle are implemented.
  • embodiments of the embodiments of the present invention may be provided as a method, an apparatus, or a computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • Embodiments of the present invention are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present invention. It will be understood that each process and/or block in the flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions.
  • These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing terminal equipment to produce a machine that causes the instructions to be executed by the processor of the computer or other programmable data processing terminal equipment Means are created for implementing the functions specified in a flow or flows of the flowcharts and/or a block or blocks of the block diagrams.
  • These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal equipment to operate in a particular manner, such that the instructions stored in the computer readable memory result in an article of manufacture comprising instruction means, the The instruction means implement the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Navigation (AREA)

Abstract

A vehicle turning path planning method and apparatus, a vehicle, and a storage medium. The method comprises: obtaining current vehicle position information of the vehicle and a pre-planned navigation path (101); determining a sampling range and a turning arc length according to the navigation path (102); sampling the sampling range to obtain target vehicle position information (103); calculating a helical parameter according to the current vehicle position information, the target vehicle position information, and the turning arc length (104); calculating a turning path according to the helical parameter (105); and calculating a cost for the turning path, and selecting the turning path having the minimum cost as a target turning path (106). The method can adapt to various complex and large-angle turning environments, rapidly determines an optimal target turning path in, for example, a parking lot, a residential area where vehicles and pedestrians run together, and other places, achieves comfortable turning, and brings an excellent automatic driving experience for users.

Description

车辆转弯路径规划方法、装置、车辆和存储介质Vehicle turning path planning method, device, vehicle and storage medium
本申请要求在2020年12月30日提交中国专利局、申请号202011629184.X、发明名称为“车辆转弯路径规划方法、装置、车辆和存储介质”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。This application claims the priority of the Chinese patent application filed on December 30, 2020 with the Chinese Patent Office, application number 202011629184.X, and the invention title is "vehicle turning path planning method, device, vehicle and storage medium", the entire content of which is approved by Reference is incorporated in this application.
技术领域technical field
本发明涉及人工智能技术领域，特别是涉及一种车辆转弯路径规划方法、装置、车辆和存储介质。The present invention relates to the technical field of artificial intelligence, and in particular, to a vehicle turning path planning method, device, vehicle and storage medium.
背景技术Background technique
自动驾驶车辆路径规划一般有采样，优化，搜索三种方法，其中基于采样的方法是实现效率最高的一种，因此在市场应用上也最为广泛。There are generally three methods for path planning of autonomous vehicles: sampling, optimization, and search. Among them, the method based on sampling is the most efficient one, so it is also the most widely used in the market.
然而，基于采样的方法在复杂环境，如停车场、人车混行小区等地方不够灵活，无法兼顾车辆的运动学特性和复杂的驾驶需求，对于大角度转弯等情况无能为力。However, the sampling-based method is not flexible enough in complex environments, such as parking lots, mixed pedestrian and vehicle communities, etc., and cannot take into account the kinematic characteristics of the vehicle and complex driving needs, and is powerless for situations such as large-angle turns.
发明内容SUMMARY OF THE INVENTION
鉴于上述问题，提出了本发明实施例以便提供一种克服上述问题或者至少部分地解决上述问题的一种车辆转弯路径规划方法和相应的一种车辆转弯路径规划装置、车辆、存储介质。In view of the above problems, embodiments of the present invention are proposed to provide a vehicle turning path planning method and a corresponding vehicle turning path planning device, vehicle, and storage medium that overcome or at least partially solve the above problems.
为了解决上述问题，本发明实施例公开了一种车辆转弯路径规划方法，所述方法包括：In order to solve the above problems, an embodiment of the present invention discloses a method for planning a turning path of a vehicle, and the method includes:
获取所述车辆的当前车辆位置信息以及预先规划的导航路径；obtaining the current vehicle position information of the vehicle and the pre-planned navigation path;
根据所述导航路径确定采样范围和转弯弧长；Determine the sampling range and the turning arc length according to the navigation path;
对所述采样范围进行采样，得到目标车辆位置信息；Sampling the sampling range to obtain target vehicle location information;
根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算螺旋线参数；Calculate the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length;
根据所述螺旋线参数计算转弯路径；calculating a turning path according to the helix parameters;
计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径。The cost of the turning path is calculated, and the turning path with the smallest cost is selected as the target turning path.
优选地，所述根据所述导航路径确定采样范围和转弯弧长，包括：Preferably, the determining the sampling range and the turning arc length according to the navigation path includes:
在所述导航路径中确定弯道结束点位置信息；determining the position information of the end point of the curve in the navigation path;
根据所述弯道结束点位置信息确定所述采样范围和所述转弯弧长。The sampling range and the turning arc length are determined according to the position information of the end point of the curve.
优选地，所述根据所述弯道结束点位置信息确定所述采样范围和所述转弯弧长，包括：Preferably, the determining the sampling range and the turning arc length according to the position information of the end point of the curve includes:
根据所述弯道结束点位置信息和预设参数计算采样范围；Calculate the sampling range according to the position information of the end point of the curve and preset parameters;
根据所述当前车辆位置信息和所述弯道结束点位置信息计算所述转弯弧长。The turning arc length is calculated according to the current vehicle position information and the curve end point position information.
优选地，所述当前车辆位置信息包括第一坐标位置、第一航向角，所述目标车辆位置信息包括第二航向角，所述弯道结束点位置信息包括第三坐标位置，所述计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径，包括：Preferably, the current vehicle position information includes a first coordinate position and a first heading angle, the target vehicle position information includes a second heading angle, the curve end point position information includes a third coordinate position, and the calculated The cost of the turning path is selected, and the turning path with the minimum cost is selected as the target turning path, including:
根据所述螺旋线参数和所述转弯弧长计算所述目标车辆位置信息的第二坐标位置；Calculate the second coordinate position of the target vehicle position information according to the helix parameter and the turning arc length;
根据所述第一坐标位置、所述第二坐标位置以及所述第三坐标位置计算距离代价，其中，所述距离代价小于第一预设阈值；Calculate a distance cost according to the first coordinate position, the second coordinate position and the third coordinate position, wherein the distance cost is less than a first preset threshold;
根据所述第一航向角和所述第二航向角计算航向角差值代价，其中，所述航向角差值代价小于第二预设阈值；A heading angle difference cost is calculated according to the first heading angle and the second heading angle, wherein the heading angle difference cost is less than a second preset threshold;
根据所述转弯弧长和所述螺旋线参数计算曲率变化代价；calculating a curvature change cost according to the turning arc length and the helix parameter;
将所述距离代价、所述航向角差值代价以及所述曲率变化代价加权求和得到所述转弯路径的总代价，并选取所述总代价最小的所述转弯路径作为所述目标转弯路径。The distance cost, the heading angle difference cost and the curvature change cost are weighted and summed to obtain the total cost of the turning path, and the turning path with the smallest total cost is selected as the target turning path.
优选地，所述根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算螺旋线参数，包括：Preferably, the calculation of the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length includes:
根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算五次螺旋线参数。The fifth spiral parameter is calculated according to the current vehicle position information, the target vehicle position information and the turning arc length.
优选地，所述目标车辆位置信息包括第二曲率、第二曲率变化率，其中，所述第二曲率小于第三预设阈值，所述第二曲率变化率小于第四预设阈值。Preferably, the target vehicle position information includes a second curvature and a second curvature change rate, wherein the second curvature is smaller than a third preset threshold, and the second curvature change rate is smaller than a fourth preset threshold.
本发明实施例公开了一种车辆转弯路径规划装置，所述装置包括：The embodiment of the present invention discloses a vehicle turning path planning device, and the device includes:
位置信息获取模块，用于获取所述车辆的当前车辆位置信息以及预先规划的导航路径；a location information acquisition module, configured to acquire the current vehicle location information of the vehicle and a pre-planned navigation path;
采样范围确定模块，用于根据所述导航路径确定采样范围和转弯弧长；a sampling range determination module, configured to determine the sampling range and the turning arc length according to the navigation path;
位置信息采样模块，用于对所述采样范围进行采样，得到目标车辆位置信息；a position information sampling module, used for sampling the sampling range to obtain target vehicle position information;
螺旋线参数计算模块，用于根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算螺旋线参数；a helix parameter calculation module, configured to calculate a helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length;
转弯路径计算模块，用于根据所述螺旋线参数计算转弯路径；a turning path calculation module, used for calculating the turning path according to the helix parameters;
目标转弯路径选取模块，用于计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径。The target turning path selection module is used to calculate the cost of the turning path, and select the turning path with the minimum cost as the target turning path.
优选地，所述采样范围确定模块，包括：Preferably, the sampling range determination module includes:
位置信息确认子模块，用于在所述导航路径中确定弯道结束点位置信息；a position information confirmation submodule, used for determining the position information of the end point of the curve in the navigation path;
采样范围确认子模块，用于根据所述弯道结束点位置信息确定所述采样范围和所述转弯弧长。A sampling range confirmation sub-module, configured to determine the sampling range and the turning arc length according to the position information of the end point of the curve.
优选地，所述采样范围确认子模块，包括：Preferably, the sampling range confirmation sub-module includes:
采样范围计算单元，用于根据所述弯道结束点位置信息和预设参数计算采样范围；a sampling range calculation unit, configured to calculate the sampling range according to the position information of the end point of the curve and preset parameters;
弯道弧长计算单元，用于根据所述当前车辆位置信息和所述弯道结束点位置信息计算所述转弯弧长。A curve arc length calculation unit, configured to calculate the turning arc length according to the current vehicle position information and the position information of the end point of the curve.
优选地，所述当前车辆位置信息包括第一坐标位置、第一航向角，所述目标车辆位置信息包括第二航向角，所述弯道结束点位置信息包括第三坐标位置，所述目标转弯路径选取模块，包括：Preferably, the current vehicle position information includes a first coordinate position and a first heading angle, the target vehicle position information includes a second heading angle, the curve end point position information includes a third coordinate position, and the target turning Path selection module, including:
坐标位置计算子模块，用于根据所述螺旋线参数和所述转弯弧长计算所述目标车辆位置信息的第二坐标位置；a coordinate position calculation submodule, configured to calculate the second coordinate position of the target vehicle position information according to the helix parameter and the turning arc length;
距离代价计算子模块，用于根据所述第一坐标位置、所述第二坐标位置以及所述第三坐标位置计算距离代价，其中，所述距离代价小于第一预设阈值；a distance cost calculation submodule, configured to calculate a distance cost according to the first coordinate position, the second coordinate position and the third coordinate position, wherein the distance cost is less than a first preset threshold;
航向角差值代价计算子模块，用于根据所述第一航向角和所述第二航向角计算航向角差值代价，其中，所述航向角差值代价小于第二预设阈值；a heading angle difference cost calculation sub-module, configured to calculate a heading angle difference cost according to the first heading angle and the second heading angle, wherein the heading angle difference cost is less than a second preset threshold;
曲率变化代价计算子模块，用于根据所述转弯弧长和所述螺旋线参数计算曲率变化代价；a curvature change cost calculation submodule, configured to calculate a curvature change cost according to the turning arc length and the helix parameter;
目标转弯路径选取子模块，用于将所述距离代价、所述航向角差值代价以及所述曲率变化代价加权求和得到所述转弯路径的总代价，并选取所述总代价最小的所述转弯路径作为所述目标转弯路径。A target turning path selection sub-module, used for weighted summation of the distance cost, the heading angle difference cost and the curvature change cost to obtain the total cost of the turning path, and select the minimum cost of the total cost. A turning path is used as the target turning path.
优选地，所述螺旋线参数计算模块，包括：Preferably, the helix parameter calculation module includes:
螺旋线参数计算子模块，用于根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算五次螺旋线参数。The helix parameter calculation sub-module is configured to calculate the fifth helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length.
优选地，所述目标车辆位置信息包括第二曲率、第二曲率变化率，其中，所述第二曲率小于第三预设阈值，所述第二曲率变化率小于第四预设阈值。Preferably, the target vehicle position information includes a second curvature and a second curvature change rate, wherein the second curvature is smaller than a third preset threshold, and the second curvature change rate is smaller than a fourth preset threshold.
本发明实施例公开了一种车辆，包括处理器、存储器及存储在所述存储器上并能够在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现如上所述的车辆转弯路径规划方法的步骤。An embodiment of the present invention discloses a vehicle, including a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program being executed by the processor to achieve the above-mentioned The steps of a vehicle turning path planning method.
本发明实施例公开了一种计算机可读存储介质，所述计算机可读存储介质上存储计算机程序，所述计算机程序被处理器执行时实现如上所述的车辆转弯路径规划方法的步骤。An embodiment of the present invention discloses a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned method for planning a turning path of a vehicle are implemented.
本发明实施例包括以下优点：The embodiments of the present invention include the following advantages:
在本发明实施例中，获取车辆的当前车辆位置信息以及预先规划的导航路径，根据导航路径确定采样范围和转弯弧长，对采样范围进行采样，得到目标车辆位置信息，根据当前车辆位置信息、目标车辆位置信息以及转弯弧长计算螺旋线参数，根据螺旋线参数计算转弯路径，计算转弯路径的代价，选取最小代价的转弯路径作为目标转弯路径。本发明实施例中，获取当前车辆位置信息，同时从采样范围中采样得到多个目标车辆位置信息，通过当前 车辆位置信息与多个目标车辆位置信息计算对应的螺旋线参数，确定多个目标车辆位置信息对应的转弯路径，并通过计算转弯路径的代价，从多个转弯路径中选取出代价最小的目标转弯路径，能够适应各种复杂，大角度转弯的环境，例如可以在停车场、人车混行小区等地方快速确定出最优的目标转弯路径，舒适转弯，给用户带来优良的自动驾驶体验。In the embodiment of the present invention, the current vehicle position information of the vehicle and the pre-planned navigation path are obtained, the sampling range and the turning arc length are determined according to the navigation path, the sampling range is sampled, and the target vehicle position information is obtained. The position information of the target vehicle and the length of the turning arc are used to calculate the helix parameters, the turning path is calculated according to the helix parameters, the cost of the turning path is calculated, and the turning path with the minimum cost is selected as the target turning path. In the embodiment of the present invention, the current vehicle position information is acquired, and at the same time, multiple target vehicle position information is sampled from the sampling range, and the corresponding spiral parameters are calculated by the current vehicle position information and the multiple target vehicle position information, and multiple target vehicles are determined. The turning path corresponding to the location information, and by calculating the cost of the turning path, the target turning path with the least cost is selected from the multiple turning paths, which can adapt to various complex and large-angle turning environments, such as parking lots, people and vehicles. In mixed communities and other places, the optimal target turning path can be quickly determined, turning comfortably, bringing users an excellent automatic driving experience.
附图说明Description of drawings
图1是本发明的一种车辆转弯路径规划方法实施例的步骤流程图；Fig. 1 is a flow chart of steps of an embodiment of a vehicle turning path planning method according to the present invention;
图2是本发明的另一种车辆转弯路径规划方法实施例的步骤流程图；2 is a flow chart of steps of another embodiment of a vehicle turning path planning method according to the present invention;
图3是本发明的一种车辆转弯路径规划示意图；Fig. 3 is a kind of vehicle turning path planning schematic diagram of the present invention;
图4是本发明的一种车辆转弯路径规划装置实施例的结构框图。FIG. 4 is a structural block diagram of an embodiment of a vehicle turning path planning device according to the present invention.
具体实施方式Detailed ways
为使本发明的上述目的、特征和优点能够更加明显易懂，下面结合附图和具体实施方式对本发明作进一步详细的说明。In order to make the above objects, features and advantages of the present invention more clearly understood, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments.
参照图1，示出了本发明的一种车辆转弯路径规划方法实施例的步骤流程图，本发明实施例具体可以包括如下步骤：Referring to FIG. 1 , a flow chart of steps of an embodiment of a vehicle turning path planning method of the present invention is shown. The embodiment of the present invention may specifically include the following steps:
步骤101，获取所述车辆的当前车辆位置信息以及预先规划的导航路径。Step 101: Acquire current vehicle position information of the vehicle and a pre-planned navigation path.
其中，导航路径为第三方地图平台或其他全局规划方法规划的从出发地到目的地的路径。The navigation path is the path from the departure place to the destination planned by a third-party map platform or other global planning methods.
具体地，在车辆自动驾驶过程中，通过导航地图或者车载传感器获知车辆前方存在弯道时，获取当前时刻车辆的当前车辆位置信息与第三方地图平台或其他全局规划方法规划的从出发地到目的地的导航路径。Specifically, in the process of automatic driving of the vehicle, when it is known that there is a curve ahead of the vehicle through the navigation map or the on-board sensor, the current vehicle position information of the vehicle at the current moment and the starting point to the destination planned by a third-party map platform or other global planning methods are obtained. Navigation path of the ground.
步骤102，根据所述导航路径确定采样范围和转弯弧长。Step 102: Determine the sampling range and the turning arc length according to the navigation path.
其中，转弯弧长为车辆前方弯道弧长。具体地，在车辆感知前方存在弯道，并获取当前车辆位置信息与导航路径后，根据导航路径中的弯道结束点确定采样范围，以及当前车辆位置与弯道结束点直接的转弯弧长。Among them, the turning arc length is the arc length of the curve ahead of the vehicle. Specifically, after the vehicle perceives a curve ahead and obtains the current vehicle position information and the navigation path, the sampling range is determined according to the end point of the curve in the navigation path, and the direct turning arc length between the current vehicle position and the end point of the curve.
步骤103，对所述采样范围进行采样，得到目标车辆位置信息。Step 103: Sampling the sampling range to obtain target vehicle location information.
具体地，在根据导航路径中的弯道结束点确定采样范围后，开始在采样范围内开始采样，得到多个目标车辆位置信息。Specifically, after the sampling range is determined according to the end point of the curve in the navigation path, sampling is started within the sampling range to obtain a plurality of target vehicle position information.
步骤104，根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算螺旋线参数。Step 104: Calculate the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length.
在获取到车辆当前位置信息、转弯弧长，以及采样得到的多个目标车辆位置信息后，根据车辆当前位置信息、转弯弧长以及目标车辆位置信息通过五次螺旋线计算目标车辆位置信息对应的五次螺旋线参数。After obtaining the current position information of the vehicle, the length of the turning arc, and the position information of multiple target vehicles obtained by sampling, calculate the corresponding position information of the target vehicle through five spirals according to the current position information of the vehicle, the length of the turning arc and the position information of the target vehicle. Quintic helix parameters.
步骤105，根据所述螺旋线参数计算转弯路径。Step 105: Calculate the turning path according to the helix parameters.
在计算得到目标车辆位置信息对应的五次螺旋线参数后，再根据五次螺旋线参数计算目标车辆位置信息对应转弯路径。After the fifth-order helix parameter corresponding to the target vehicle position information is calculated and obtained, the turning path corresponding to the target vehicle position information is calculated according to the fifth-order helix parameter.
步骤106，计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径。Step 106: Calculate the cost of the turning path, and select the turning path with the minimum cost as the target turning path.
在根据五次螺旋线计算目标车辆位置信息对应转弯路径后，计算得到的多个转弯路径的代价，并进行比较，选取最小代价的转弯路径作为目标转弯路径，控制车辆根据目标转弯路径舒适通过前方弯道。After calculating the turning path corresponding to the position information of the target vehicle according to the five spirals, the calculated costs of multiple turning paths are compared, and the turning path with the minimum cost is selected as the target turning path, and the vehicle is controlled to pass the front comfortably according to the target turning path. corner.
综上，在本发明实施例中，获取车辆的当前车辆位置信息以及预先规划的导航路径，根据导航路径确定采样范围和转弯弧长，对采样范围进行采样，得到目标车辆位置信息，根据当前车辆位置信息、目标车辆位置信息以及转弯弧长计算螺旋线参数，根据螺旋线参数计算转弯路径，计算转弯路径的代价，选取最小代价的转弯路径作为目标转弯路径。本发明实施例中，获取当前车辆位置信息，同时从采样范围中采样得到多个目标车辆位置信息，通过当前车辆位置信息与多个目标车辆位置信息计算对应的螺旋线参数，确定多个目标车辆位置信息对应的转弯路径，并通过计算转弯路径的代价，从多个转弯路径中选取出代价最小的目标转弯路径，能够适应各种复杂，大角度转弯的环境，例如可以在停车场、人车混行小区等地方快速确定出最优的目标转弯路径，舒适转弯，给用户带来优良的自动驾驶体验。To sum up, in the embodiment of the present invention, the current vehicle position information of the vehicle and the pre-planned navigation path are obtained, the sampling range and the turning arc length are determined according to the navigation path, the sampling range is sampled, and the target vehicle position information is obtained. The position information, target vehicle position information and turning arc length are used to calculate the helix parameters, the turning path is calculated according to the helix parameters, the cost of the turning path is calculated, and the turning path with the minimum cost is selected as the target turning path. In the embodiment of the present invention, the current vehicle position information is acquired, and at the same time, multiple target vehicle position information is sampled from the sampling range, and the corresponding spiral parameters are calculated by the current vehicle position information and the multiple target vehicle position information, and multiple target vehicles are determined. The turning path corresponding to the location information, and by calculating the cost of the turning path, the target turning path with the least cost is selected from the multiple turning paths, which can adapt to various complex and large-angle turning environments, such as parking lots, people and vehicles. In mixed communities and other places, the optimal target turning path can be quickly determined, turning comfortably, bringing users an excellent automatic driving experience.
参照图2，示出了本发明的另一种车辆转弯路径规划方法实施例的步骤 流程图，本发明实施例具体可以包括如下步骤：Referring to Fig. 2, there is shown a flow chart of the steps of another vehicle turning path planning method embodiment of the present invention, and the embodiment of the present invention may specifically include the following steps:
步骤101，获取所述车辆的当前车辆位置信息以及预先规划的导航路径。Step 101: Acquire current vehicle position information of the vehicle and a pre-planned navigation path.
步骤102，在所述导航路径中确定弯道结束点位置信息。Step 102: Determine the position information of the end point of the curve in the navigation path.
具体地，在获取到导航路径后，根据导航路径获取弯道结束位置的中间作为弯道结束点，获取弯道结束点位置信息。Specifically, after the navigation path is acquired, the middle of the end position of the curve is acquired according to the navigation path as the end point of the curve, and the position information of the end point of the curve is acquired.
步骤103，根据所述弯道结束点位置信息确定所述采样范围和所述转弯弧长。Step 103: Determine the sampling range and the turning arc length according to the position information of the end point of the curve.
在本发明一实施例中，所述根据所述弯道结束点位置信息确定所述采样范围和所述转弯弧长，包括：根据所述弯道结束点位置信息和预设参数计算采样范围；根据所述当前车辆位置信息和所述弯道结束点位置信息计算所述转弯弧长。In an embodiment of the present invention, the determining the sampling range and the turning arc length according to the position information of the end point of the curve includes: calculating the sampling range according to the position information of the end point of the curve and a preset parameter; The turning arc length is calculated according to the current vehicle position information and the curve end point position information.
其中，获取到的弯道结束点位置信息包括第三坐标位置(x t，y t)、第三航向角θ t、第三曲率k t以第三曲率变化率dk t，预设参数为Δθ，Δk，Δdk。 The obtained position information of the end point of the curve includes the third coordinate position (x t , y t ), the third heading angle θ t , the third curvature k t and the third curvature change rate dk t , and the preset parameter is Δθ , Δk, Δdk.
具体地，在获取到弯道结束点位置信息后，根据弯道结束点位置信息中第三航向角θ t、第三曲率k t以第三曲率变化率dk t的和预设参数Δθ，Δk，Δdk计算出采样范围θ t-Δθ～θ t+Δθ，k t-Δk～k t+Δk，dk t-Δdk～dk t+Δdk；转弯弧长s f为截取原导航路径中当前车辆位置和弯道结束点位置之间的弯道路径计算得到，转弯弧长为弯道长度。 Specifically, after obtaining the position information of the end point of the curve, according to the third heading angle θ t , the third curvature k t and the third curvature change rate dk t in the position information of the end point of the curve and the preset parameters Δθ, Δk , Δdk calculates the sampling range θ t -Δθ～θ t +Δθ, k t -Δk～k t +Δk, dk t -Δdk～dk t +Δdk; the turning arc length s f is to intercept the current vehicle position in the original navigation path The curve path between the curve end point and the curve end point is calculated, and the turn arc length is the curve length.
步骤104，对所述采样范围进行采样，得到目标车辆位置信息。Step 104: Sampling the sampling range to obtain target vehicle location information.
具体地，获取采样范围θ t-Δθ～θ t+Δθ，k t-Δk～k t+Δk，dk t-Δdk～dk t+Δdk后，在采样范围中进行采样得到目标车辆位置信息的第二航向角θ 1、第二曲率k 1以及第二曲率变化率dk 1，其中，航向角、曲率、曲率变化率采样步长为θ step，k step，dk step，因此总采样数量为
Figure PCTCN2021141754-appb-000001
需要说明的是采样得到的车辆位置信息不包括坐标位置。 Specifically, after obtaining the sampling range θ t -Δθ ~ θ t +Δθ, k t -Δk ~ k t +Δk, dk t -Δdk ~ dk t +Δdk, sampling is performed in the sampling range to obtain the first position information of the target vehicle. Two heading angle θ 1 , second curvature k 1 and second curvature change rate dk 1 , wherein the sampling steps of heading angle, curvature and curvature change rate are θ step , k step , dk step , so the total number of samples is
Figure PCTCN2021141754-appb-000001
It should be noted that the sampled vehicle position information does not include the coordinate position.
步骤105，根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算螺旋线参数。Step 105: Calculate the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length.
其中，当前车辆位置信息包括第一坐标位置(x 0，y 0)、第一航向角θ 0、第 一曲率k 0以及第一曲率变化率dk 0。 The current vehicle position information includes a first coordinate position (x 0 , y 0 ), a first heading angle θ 0 , a first curvature k 0 and a first curvature change rate dk 0 .
具体地，根据当前车辆位置信息中的第一航向角θ 0、第一曲率k 0以及第一曲率变化率dk 0，目标车辆位置信息中的第二航向角θ 1、第二曲率k 1以及第二曲率变化率dk 1，与转弯弧长s f，其中s f为目标车辆位置对应的转弯弧长，当前车辆位置对应的转弯弧长的长度s 0＝0，将上述两组参数(θ t，k t，dk t，s f)，(θ 0，k 0，dk 0，s 0＝0)带入五次螺旋线中： Specifically, according to the first heading angle θ 0 , the first curvature k 0 and the first curvature change rate dk 0 in the current vehicle position information, the second heading angle θ 1 , the second curvature k 1 and The second curvature change rate dk 1 , and the turning arc length s f , where s f is the turning arc length corresponding to the target vehicle position, and the length s 0 =0 of the turning arc length corresponding to the current vehicle position. t , k t , dk t , s f ), (θ 0 , k 0 , dk 0 , s 0 =0) are brought into the quintic spiral:
θ (s)＝a 0+a 1s+a 2s 2+a 3s 3+a 4s 4+a 5s 5 θ (s) = a 0 +a 1 s+a 2 s 2 +a 3 s 3 +a 4 s 4 +a 5 s 5
k (s)＝a 1+2a 2s+3a 3s 2+4a 4s 3+5a 5s 4 k (s) = a 1 +2a 2 s+3a 3 s 2 +4a 4 s 3 +5a 5 s 4
dk (s)＝2a 2+6a 3s+12a 4s 2+20a 5s 3 dk (s) = 2a 2 +6a 3 s + 12a 4 s 2 +20a 5 s 3
得到：get:
a 0＝θ 0 a 0 =θ 0
a 1＝k 0 a 1 =k 0
2a 2＝dk 0 2a 2 =dk 0
Figure PCTCN2021141754-appb-000002
Figure PCTCN2021141754-appb-000002
Figure PCTCN2021141754-appb-000003
Figure PCTCN2021141754-appb-000003
Figure PCTCN2021141754-appb-000004
Figure PCTCN2021141754-appb-000004
即可得到a 0，a 1，a 2，a 3，a 4，a 5六个螺旋参数。 Six helical parameters a 0 , a 1 , a 2 , a 3 , a 4 , and a 5 can be obtained.
步骤106，根据所述螺旋线参数计算转弯路径。Step 106: Calculate the turning path according to the helix parameters.
具体地，在计算得到a 0，a 1，a 2，a 3，a 4，a 5六个螺旋参数后，可六个螺旋参数以及弯道中的任意转弯弧长s代入下列公式： Specifically, after the six helical parameters a 0 , a 1 , a 2 , a 3 , a 4 , and a 5 are obtained by calculation, the six helical parameters and any turning arc length s in the curve can be substituted into the following formula:
Figure PCTCN2021141754-appb-000005
Figure PCTCN2021141754-appb-000005
Figure PCTCN2021141754-appb-000006
Figure PCTCN2021141754-appb-000006
θ (s)＝a 0+a 1s+2a 2s 2+3a 3s 3+4a 4s 4+5a 5s 5 θ (s) = a 0 +a 1 s+2a 2 s 2 +3a 3 s 3 +4a 4 s 4 +5a 5 s 5
可得到弯道中任意转弯弧长s f对应的坐标位置，即得到转弯路径中所有的坐标位置。 The coordinate position corresponding to any turning arc length s f in the curve can be obtained, that is, all the coordinate positions in the turning path can be obtained.
参考图3，是本发明的一种车辆转弯路径规划示意图，如图可知，在获取车辆当前车辆位置信息和多个目标车辆位置信息后，可根据当前车辆位置信息和多个目标车辆位置信息计算得到多条采样螺旋线(转弯路径)，且计算得到的多条转弯路径结束点位置在弯道结束点位置附近。Referring to FIG. 3, it is a schematic diagram of a vehicle turning path planning according to the present invention. As can be seen from the figure, after obtaining the current vehicle position information of the vehicle and the position information of multiple target vehicles, it can be calculated according to the current vehicle position information and the position information of multiple target vehicles. A plurality of sampling spirals (turning paths) are obtained, and the positions of the calculated end points of the plurality of turning paths are near the position of the end point of the curve.
步骤107，计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径。Step 107: Calculate the cost of the turning path, and select the turning path with the minimum cost as the target turning path.
在本发明一实施例中，所述当前车辆位置信息包括第一坐标位置、第一航向角，所述目标车辆位置信息包括第二航向角，所述弯道结束点位置信息包括第三坐标位置，所述计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径，包括：根据所述螺旋线参数和所述转弯弧长计算所述目标车辆位置信息的第二坐标位置；根据所述第一坐标位置、所述第二坐标位置以及所述第三坐标位置计算距离代价，其中，所述距离代价小于第一预设阈值；根据所述第一航向角和所述第二航向角计算航向角差值代价，其中，所述航向角差值代价小于第二预设阈值；根据所述转弯弧长和所述螺旋线参数计算曲率变化代价；将所述距离代价、所述航向角差值代价以及所述曲率变化代价加权求和得到所述转弯路径的总代价，并选取所述总代价最小的所述转弯路径作为所述目标转弯路径。In an embodiment of the present invention, the current vehicle position information includes a first coordinate position and a first heading angle, the target vehicle position information includes a second heading angle, and the curve end point position information includes a third coordinate position , the calculating the cost of the turning path, and selecting the turning path with the minimum cost as the target turning path, including: calculating the second coordinate position of the target vehicle position information according to the helix parameter and the turning arc length ; Calculate a distance cost according to the first coordinate position, the second coordinate position and the third coordinate position, wherein the distance cost is less than a first preset threshold; According to the first heading angle and the first heading angle Second, the heading angle difference cost is calculated by the heading angle, wherein the heading angle difference cost is smaller than the second preset threshold; the curvature change cost is calculated according to the turning arc length and the helix parameter; The heading angle difference cost and the curvature change cost are weighted and summed to obtain the total cost of the turning path, and the turning path with the smallest total cost is selected as the target turning path.
具体地，目标车辆位置信息的第二坐标位置可由五次螺旋线参数和转弯弧长带入下列公式中计算得到：Specifically, the second coordinate position of the target vehicle position information can be calculated by bringing the fifth helix parameter and the turning arc length into the following formula:
Figure PCTCN2021141754-appb-000007
Figure PCTCN2021141754-appb-000007
Figure PCTCN2021141754-appb-000008
Figure PCTCN2021141754-appb-000008
θ (s)＝a 0+a 1s+2a 2s 2+3a 3s 3+4a 4s 4+5a 5s 5 θ (s) = a 0 +a 1 s+2a 2 s 2 +3a 3 s 3 +4a 4 s 4 +5a 5 s 5
在计算得到目标车辆位置信息的第二坐标位置后，根据第一坐标位置、第二坐标位置以及第三坐标位置计算目标车辆位置与弯道结束点位置的距离代价，计算公式如下：After calculating the second coordinate position of the target vehicle position information, calculate the distance cost between the target vehicle position and the curve end point position according to the first coordinate position, the second coordinate position and the third coordinate position. The calculation formula is as follows:
Figure PCTCN2021141754-appb-000009
Figure PCTCN2021141754-appb-000009
根据第一航向角和第二航向角计算航向角差值代价，计算公式如下：The heading angle difference cost is calculated according to the first heading angle and the second heading angle, and the calculation formula is as follows:
|θ 0-θ t| |θ 0 -θ t |
根据转弯弧长和螺旋线参数计算曲率变化代价，计算公式如下：The cost of curvature change is calculated according to the turning arc length and the helix parameters. The calculation formula is as follows:
Figure PCTCN2021141754-appb-000010
Figure PCTCN2021141754-appb-000010
在计算得到距离代价、航向角差值代价以及曲率变化代价后，则将距离代价、航向角差值代价以及曲率变化代价加权求和得到转弯路径的总代价并 选取总代价最小的转弯路径作为目标转弯路径，此外，对于转弯路径的硬性要求，计算得到的距离代价需小于第一预设阈值、航向角差值代价小于第二预设阈值，如下：After calculating the distance cost, heading angle difference cost and curvature change cost, the distance cost, heading angle difference cost and curvature change cost are weighted and summed to obtain the total cost of the turning path, and the turning path with the smallest total cost is selected as the target The turning path, in addition, for the rigid requirements of the turning path, the calculated distance cost must be less than the first preset threshold, and the heading angle difference cost must be less than the second preset threshold, as follows:
Figure PCTCN2021141754-appb-000011
Figure PCTCN2021141754-appb-000011
|θ 0-θ t|<θ max |θ 0 -θ t |<θ max
在本发明实施例中，通过对采样计算得到的多条转弯路径进行代价计算，并选取代价最小的转弯路径作为目标转弯路径，可以在复杂的道路环境中快速选取最优转弯路径，控制车辆根据转弯路径舒适通过车辆前面的弯道。In the embodiment of the present invention, by performing cost calculation on multiple turning paths obtained by sampling calculation, and selecting the turning path with the smallest cost as the target turning path, the optimal turning path can be quickly selected in a complex road environment, and the vehicle can be controlled according to the The turning path is comfortable through the bends in front of the vehicle.
在本发明一实施例中，所述目标车辆位置信息包括第二曲率、第二曲率变化率，其中，所述第二曲率小于第三预设阈值，所述第二曲率变化率小于第四预设阈值。In an embodiment of the present invention, the target vehicle position information includes a second curvature and a second curvature change rate, wherein the second curvature is less than a third preset threshold, and the second curvature change rate is less than a fourth preset threshold Set the threshold.
具体地，对于转弯路径的硬性要求，在计算得到目标车辆位置信息的第二曲率和人第二曲率变化率后，要求第二曲率小于第三预设阈值，第二曲率变化率小于第四预设阈值，如下：Specifically, for the rigid requirement of the turning path, after calculating the second curvature of the target vehicle position information and the second curvature change rate of the person, the second curvature is required to be smaller than the third preset threshold, and the second curvature change rate is smaller than the fourth preset threshold. Set the threshold as follows:
Figure PCTCN2021141754-appb-000012
Figure PCTCN2021141754-appb-000012
Figure PCTCN2021141754-appb-000013
Figure PCTCN2021141754-appb-000013
在本发明实施例中，通过转弯路径的硬性要求，距离代价需小于第一预设阈值、航向角差值代价小于第二预设阈值，第二曲率小于第三预设阈值，第二曲率变化率小于第四预设阈值，可以确保车辆规划的转弯路径不会偏离真实的弯道路径，能够安全的行驶。In the embodiment of the present invention, according to the rigid requirements of the turning path, the distance cost must be less than the first preset threshold, the heading angle difference cost must be less than the second preset threshold, the second curvature must be less than the third preset threshold, and the second curvature changes If the rate is smaller than the fourth preset threshold, it can ensure that the turning path planned by the vehicle will not deviate from the real curve path and can drive safely.
需要说明的是，本发明实施例采用的是五次螺旋线，相比于其他多项式曲线，能够覆盖更多复杂的道路情况，且本发明实施例并不限于五次螺旋线，实际上六次、四次、三次乃至于其他次数也可以都使用。It should be noted that the embodiment of the present invention adopts the quintic helix, which can cover more complex road conditions compared with other polynomial curves, and the embodiment of the present invention is not limited to the quintic helix. , four times, three times and even other times can also be used.
综上，在本发明实施例中，获取车辆的当前车辆位置信息以及预先规划的导航路径，在导航路径中确定弯道结束点位置信息，根据弯道结束点位置信息确定采样范围和转弯弧长，对采样范围进行采样，得到目标车辆位置信息，根据当前车辆位置信息、目标车辆位置信息以及转弯弧长计算螺旋线参 数，根据螺旋线参数计算转弯路径，计算转弯路径的代价，选取最小代价的转弯路径作为目标转弯路径。本发明实施例中，获取当前车辆位置信息，同时从采样范围中采样得到多个目标车辆位置信息，通过当前车辆位置信息与多个目标车辆位置信息计算对应的螺旋线参数，确定多个目标车辆位置信息对应的转弯路径，并通过计算转弯路径的代价，从多个转弯路径中选取出代价最小的目标转弯路径，能够适应各种复杂，大角度转弯的环境，例如可以在停车场、人车混行小区等地方快速确定出最优的目标转弯路径，舒适转弯，给用户带来优良的自动驾驶体验。To sum up, in the embodiment of the present invention, the current vehicle position information of the vehicle and the pre-planned navigation path are obtained, the position information of the end point of the curve is determined in the navigation path, and the sampling range and the length of the turning arc are determined according to the position information of the end point of the curve , Sampling the sampling range to obtain the target vehicle position information, calculate the helix parameters according to the current vehicle position information, the target vehicle position information and the turning arc length, calculate the turning path according to the helix parameters, calculate the cost of the turning path, and select the one with the smallest cost. The turn path serves as the target turn path. In the embodiment of the present invention, the current vehicle position information is acquired, and at the same time, multiple target vehicle position information is sampled from the sampling range, and the corresponding spiral parameters are calculated by the current vehicle position information and the multiple target vehicle position information, and multiple target vehicles are determined. The turning path corresponding to the location information, and by calculating the cost of the turning path, the target turning path with the least cost is selected from the multiple turning paths, which can adapt to various complex and large-angle turning environments, such as parking lots, people and vehicles. In mixed communities and other places, the optimal target turning path can be quickly determined, turning comfortably and bringing users an excellent automatic driving experience.
本发明实施例中，通过转弯路径的硬性要求，距离代价需小于第一预设阈值、航向角差值代价小于第二预设阈值，第二曲率小于第三预设阈值，第二曲率变化率小于第四预设阈值，可以确保车辆规划的转弯路径不会偏离真实的弯道路径，能够安全的行驶。In the embodiment of the present invention, according to the rigid requirements of the turning path, the distance cost must be less than the first preset threshold, the heading angle difference cost must be less than the second preset threshold, the second curvature must be less than the third preset threshold, and the second curvature change rate If it is less than the fourth preset threshold, it can ensure that the turning path planned by the vehicle will not deviate from the real curve path and can drive safely.
需要说明的是，对于方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明实施例并不受所描述的动作顺序的限制，因为依据本发明实施例，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作并不一定是本发明实施例所必须的。It should be noted that, for the sake of simple description, the method embodiments are expressed as a series of action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequence, because According to embodiments of the present invention, certain steps may be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.
参照图4，示出了本发明的一种车辆转弯路径规划装置实施例的结构框图，本发明实施例具体可以包括如下模块：Referring to FIG. 4 , a structural block diagram of an embodiment of a vehicle turning path planning device of the present invention is shown. The embodiment of the present invention may specifically include the following modules:
位置信息获取模块401，用于获取所述车辆的当前车辆位置信息以及预先规划的导航路径；a location information acquisition module 401, configured to acquire the current vehicle location information of the vehicle and a pre-planned navigation path;
采样范围确定模块402，用于根据所述导航路径确定采样范围和转弯弧长；a sampling range determination module 402, configured to determine a sampling range and a turning arc length according to the navigation path;
位置信息采样模块403，用于对所述采样范围进行采样，得到目标车辆位置信息；a location information sampling module 403, configured to sample the sampling range to obtain target vehicle location information;
螺旋线参数计算模块404，用于根据所述当前车辆位置信息、所述目标 车辆位置信息以及所述转弯弧长计算螺旋线参数；The helix parameter calculation module 404 is used to calculate the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length;
转弯路径计算模块405，用于根据所述螺旋线参数计算转弯路径；a turning path calculation module 405, configured to calculate a turning path according to the helix parameters;
目标转弯路径选取模块406，用于计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径。The target turning path selection module 406 is configured to calculate the cost of the turning path, and select the turning path with the minimum cost as the target turning path.
在本发明一实施例中，所述采样范围确定模块402，包括：In an embodiment of the present invention, the sampling range determination module 402 includes:
位置信息确认子模块，用于在所述导航路径中确定弯道结束点位置信息；a position information confirmation submodule, used for determining the position information of the end point of the curve in the navigation path;
采样范围确认子模块，用于根据所述弯道结束点位置信息确定所述采样范围和所述转弯弧长。A sampling range confirmation sub-module, configured to determine the sampling range and the turning arc length according to the position information of the end point of the curve.
在本发明一实施例中，所述采样范围确认子模块，包括：In an embodiment of the present invention, the sampling range confirmation sub-module includes:
采样范围计算单元，用于根据所述弯道结束点位置信息和预设参数计算采样范围；a sampling range calculation unit, configured to calculate the sampling range according to the position information of the end point of the curve and preset parameters;
弯道弧长计算单元，用于根据所述当前车辆位置信息和所述弯道结束点位置信息计算所述转弯弧长。A curve arc length calculation unit, configured to calculate the turning arc length according to the current vehicle position information and the position information of the end point of the curve.
在本发明一实施例中，所述当前车辆位置信息包括第一坐标位置、第一航向角，所述目标车辆位置信息包括第二航向角，所述弯道结束点位置信息包括第三坐标位置，所述目标转弯路径选取模块406，包括：In an embodiment of the present invention, the current vehicle position information includes a first coordinate position and a first heading angle, the target vehicle position information includes a second heading angle, and the curve end point position information includes a third coordinate position , the target turning path selection module 406 includes:
坐标位置计算子模块，用于根据所述螺旋线参数和所述转弯弧长计算所述目标车辆位置信息的第二坐标位置；a coordinate position calculation submodule, configured to calculate the second coordinate position of the target vehicle position information according to the helix parameter and the turning arc length;
距离代价计算子模块，用于根据所述第一坐标位置、所述第二坐标位置以及所述第三坐标位置计算距离代价，其中，所述距离代价小于第一预设阈值；a distance cost calculation submodule, configured to calculate a distance cost according to the first coordinate position, the second coordinate position and the third coordinate position, wherein the distance cost is less than a first preset threshold;
航向角差值代价计算子模块，用于根据所述第一航向角和所述第二航向角计算航向角差值代价，其中，所述航向角差值代价小于第二预设阈值；a heading angle difference cost calculation sub-module, configured to calculate a heading angle difference cost according to the first heading angle and the second heading angle, wherein the heading angle difference cost is less than a second preset threshold;
曲率变化代价计算子模块，用于根据所述转弯弧长和所述螺旋线参数计算曲率变化代价；a curvature change cost calculation submodule, configured to calculate a curvature change cost according to the turning arc length and the helix parameter;
目标转弯路径选取子模块，用于将所述距离代价、所述航向角差值代价以及所述曲率变化代价加权求和得到所述转弯路径的总代价，并选取所述总 代价最小的所述转弯路径作为所述目标转弯路径。A target turning path selection sub-module, used for weighted summation of the distance cost, the heading angle difference cost and the curvature change cost to obtain the total cost of the turning path, and select the minimum cost of the total cost. A turning path is used as the target turning path.
在本发明一实施例中，所述螺旋线参数计算模块404，包括：In an embodiment of the present invention, the spiral parameter calculation module 404 includes:
螺旋线参数计算子模块，用于根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算五次螺旋线参数。The helix parameter calculation sub-module is configured to calculate the fifth helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length.
在本发明一实施例中，所述目标车辆位置信息包括第二曲率、第二曲率变化率，其中，所述第二曲率小于第三预设阈值，所述第二曲率变化率小于第四预设阈值。In an embodiment of the present invention, the target vehicle position information includes a second curvature and a second curvature change rate, wherein the second curvature is less than a third preset threshold, and the second curvature change rate is less than a fourth preset threshold Set the threshold.
综上，在本发明实施例中，获取车辆的当前车辆位置信息以及预先规划的导航路径，根据导航路径确定采样范围和转弯弧长，对采样范围进行采样，得到目标车辆位置信息，根据当前车辆位置信息、目标车辆位置信息以及转弯弧长计算螺旋线参数，根据螺旋线参数计算转弯路径，计算转弯路径的代价，选取最小代价的转弯路径作为目标转弯路径。本发明实施例中，获取当前车辆位置信息，同时从采样范围中采样得到多个目标车辆位置信息，通过当前车辆位置信息与多个目标车辆位置信息计算对应的螺旋线参数，确定多个目标车辆位置信息对应的转弯路径，并通过计算转弯路径的代价，从多个转弯路径中选取出代价最小的目标转弯路径，能够适应各种复杂，大角度转弯的环境，例如可以在停车场、人车混行小区等地方快速确定出最优的目标转弯路径，舒适转弯，给用户带来优良的自动驾驶体验。To sum up, in the embodiment of the present invention, the current vehicle position information of the vehicle and the pre-planned navigation path are obtained, the sampling range and the turning arc length are determined according to the navigation path, and the sampling range is sampled to obtain the target vehicle position information. The position information, target vehicle position information and turning arc length are used to calculate the helix parameters, the turning path is calculated according to the helix parameters, the cost of the turning path is calculated, and the turning path with the minimum cost is selected as the target turning path. In the embodiment of the present invention, the current vehicle position information is acquired, and at the same time, multiple target vehicle position information is sampled from the sampling range, and the corresponding spiral parameters are calculated by the current vehicle position information and the multiple target vehicle position information, and multiple target vehicles are determined. The turning path corresponding to the location information, and by calculating the cost of the turning path, the target turning path with the least cost is selected from the multiple turning paths, which can adapt to various complex and large-angle turning environments, such as parking lots, people and vehicles. In mixed communities and other places, the optimal target turning path can be quickly determined, turning comfortably, bringing users an excellent automatic driving experience.
对于装置实施例而言，由于其与方法实施例基本相似，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。As for the apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for related parts.
本发明实施例公开了一种车辆，包括处理器、存储器及存储在所述存储器上并能够在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现如上车辆转弯路径规划方法实施例所述的步骤。An embodiment of the present invention discloses a vehicle, including a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program being executed by the processor to implement the above-mentioned turning of the vehicle The steps described in the embodiment of the path planning method.
本发明实施例公开了一种计算机可读存储介质，所述计算机可读存储介质上存储计算机程序，所述计算机程序被处理器执行时实现如上车辆转弯路径规划方法实施例所述的步骤。An embodiment of the present invention discloses a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps described in the above embodiments of the method for planning a turning path of a vehicle are implemented.
本说明书中的各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似的部分互相参见即可。The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments may be referred to each other.
本领域内的技术人员应明白，本发明实施例的实施例可提供为方法、装置、或计算机程序产品。因此，本发明实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。It should be understood by those skilled in the art that the embodiments of the embodiments of the present invention may be provided as a method, an apparatus, or a computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
本发明实施例是参照根据本发明实施例的方法、终端设备(***)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理终端设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理终端设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。Embodiments of the present invention are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present invention. It will be understood that each process and/or block in the flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing terminal equipment to produce a machine that causes the instructions to be executed by the processor of the computer or other programmable data processing terminal equipment Means are created for implementing the functions specified in a flow or flows of the flowcharts and/or a block or blocks of the block diagrams.
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理终端设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal equipment to operate in a particular manner, such that the instructions stored in the computer readable memory result in an article of manufacture comprising instruction means, the The instruction means implement the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.
这些计算机程序指令也可装载到计算机或其他可编程数据处理终端设备上，使得在计算机或其他可编程终端设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程终端设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions can also be loaded on a computer or other programmable data processing terminal equipment, so that a series of operational steps are performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby executing on the computer or other programmable terminal equipment The instructions executed on the above provide steps for implementing the functions specified in the flowchart or blocks and/or the block or blocks of the block diagrams.
尽管已描述了本发明实施例的优选实施例，但本领域内的技术人员一旦 得知了基本创造性概念，则可对这些实施例做出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明实施例范围的所有变更和修改。While preferred embodiments of the embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the embodiments of the present invention.
最后，还需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者终端设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者终端设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者终端设备中还存在另外的相同要素。Finally, it should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply these entities or there is any such actual relationship or sequence between operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion such that a process, method, article or terminal device that includes a list of elements includes not only those elements, but also a non-exclusive list of elements. other elements, or also include elements inherent to such a process, method, article or terminal equipment. Without further limitation, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.
以上对本发明所提供的一种车辆转弯路径规划方法、一种车辆转弯路径规划装置、车辆和存储介质，进行了详细介绍，本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的一般技术人员，依据本发明的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本发明的限制。A vehicle turning path planning method, a vehicle turning path planning device, a vehicle and a storage medium provided by the present invention have been described above in detail. In this paper, specific examples are used to illustrate the principles and implementations of the present invention. The description of the above embodiment is only used to help understand the method of the present invention and its core idea; meanwhile, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in specific embodiments and application scope, In conclusion, the contents of this specification should not be construed as limiting the present invention.

Claims (12)

  1. 一种车辆转弯路径规划方法，其特征在于，所述方法包括：A vehicle turning path planning method, characterized in that the method comprises:
    获取所述车辆的当前车辆位置信息以及预先规划的导航路径；obtaining the current vehicle position information of the vehicle and the pre-planned navigation path;
    根据所述导航路径确定采样范围和转弯弧长；Determine the sampling range and the turning arc length according to the navigation path;
    对所述采样范围进行采样，得到目标车辆位置信息；Sampling the sampling range to obtain target vehicle location information;
    根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算螺旋线参数；Calculate the helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length;
    根据所述螺旋线参数计算转弯路径；calculating a turning path according to the helix parameters;
    计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径。The cost of the turning path is calculated, and the turning path with the smallest cost is selected as the target turning path.
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述导航路径确定采样范围和转弯弧长，包括：The method according to claim 1, wherein the determining a sampling range and a turning arc length according to the navigation path comprises:
    在所述导航路径中确定弯道结束点位置信息；determining the position information of the end point of the curve in the navigation path;
    根据所述弯道结束点位置信息确定所述采样范围和所述转弯弧长。The sampling range and the turning arc length are determined according to the position information of the end point of the curve.
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述弯道结束点位置信息确定所述采样范围和所述转弯弧长，包括：The method according to claim 2, wherein the determining the sampling range and the turning arc length according to the position information of the end point of the curve comprises:
    根据所述弯道结束点位置信息和预设参数计算采样范围；Calculate the sampling range according to the position information of the end point of the curve and preset parameters;
    根据所述当前车辆位置信息和所述弯道结束点位置信息计算所述转弯弧长。The turning arc length is calculated according to the current vehicle position information and the curve end point position information.
  4. 根据权利要求2所述的方法，其特征在于，所述当前车辆位置信息包括第一坐标位置、第一航向角，所述目标车辆位置信息包括第二航向角，所述弯道结束点位置信息包括第三坐标位置，所述计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径，包括：The method according to claim 2, wherein the current vehicle position information includes a first coordinate position and a first heading angle, the target vehicle position information includes a second heading angle, and the curve end point position information Including a third coordinate position, calculating the cost of the turning path, and selecting the turning path with the minimum cost as the target turning path, including:
    根据所述螺旋线参数和所述转弯弧长计算所述目标车辆位置信息的第二坐标位置；Calculate the second coordinate position of the target vehicle position information according to the helix parameter and the turning arc length;
    根据所述第一坐标位置、所述第二坐标位置以及所述第三坐标位置计算 距离代价，其中，所述距离代价小于第一预设阈值；Calculate a distance cost according to the first coordinate position, the second coordinate position and the third coordinate position, wherein the distance cost is less than a first preset threshold;
    根据所述第一航向角和所述第二航向角计算航向角差值代价，其中，所述航向角差值代价小于第二预设阈值；A heading angle difference cost is calculated according to the first heading angle and the second heading angle, wherein the heading angle difference cost is less than a second preset threshold;
    根据所述转弯弧长和所述螺旋线参数计算曲率变化代价；calculating a curvature change cost according to the turning arc length and the helix parameter;
    将所述距离代价、所述航向角差值代价以及所述曲率变化代价加权求和得到所述转弯路径的总代价，并选取所述总代价最小的所述转弯路径作为所述目标转弯路径。The distance cost, the heading angle difference cost and the curvature change cost are weighted and summed to obtain the total cost of the turning path, and the turning path with the smallest total cost is selected as the target turning path.
  5. 根据权利要求1所述的方法，其特征在于，所述根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算螺旋线参数，包括：The method according to claim 1, wherein the calculating the spiral parameter according to the current vehicle position information, the target vehicle position information and the turning arc length comprises:
    根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算五次螺旋线参数。The fifth spiral parameter is calculated according to the current vehicle position information, the target vehicle position information and the turning arc length.
  6. 根据权利要求1至5所述的方法，其特征在于，所述目标车辆位置信息包括第二曲率、第二曲率变化率，其中，所述第二曲率小于第三预设阈值，所述第二曲率变化率小于第四预设阈值。The method according to claims 1 to 5, wherein the target vehicle position information includes a second curvature and a second curvature change rate, wherein the second curvature is smaller than a third preset threshold, the second curvature The curvature change rate is less than the fourth preset threshold.
  7. 一种车辆转弯路径规划装置，其特征在于，所述装置包括：A vehicle turning path planning device, characterized in that the device comprises:
    位置信息获取模块，用于获取所述车辆的当前车辆位置信息以及预先规划的导航路径；a location information acquisition module, configured to acquire the current vehicle location information of the vehicle and a pre-planned navigation path;
    采样范围确定模块，用于根据所述导航路径确定采样范围和转弯弧长；a sampling range determination module, configured to determine the sampling range and the turning arc length according to the navigation path;
    位置信息采样模块，用于对所述采样范围进行采样，得到目标车辆位置信息；a position information sampling module, used for sampling the sampling range to obtain target vehicle position information;
    螺旋线参数计算模块，用于根据所述当前车辆位置信息、所述目标车辆位置信息以及所述转弯弧长计算螺旋线参数；a helix parameter calculation module, configured to calculate a helix parameter according to the current vehicle position information, the target vehicle position information and the turning arc length;
    转弯路径计算模块，用于根据所述螺旋线参数计算转弯路径；a turning path calculation module, used for calculating the turning path according to the helix parameters;
    目标转弯路径选取模块，用于计算所述转弯路径的代价，选取最小代价的所述转弯路径作为目标转弯路径。The target turning path selection module is used to calculate the cost of the turning path, and select the turning path with the minimum cost as the target turning path.
  8. 根据权利要求7所述的装置，其特征在于，所述采样范围确定模块，包括：The device according to claim 7, wherein the sampling range determination module comprises:
    位置信息确认子模块，用于在所述导航路径中确定弯道结束点位置信息；a position information confirmation submodule, used for determining the position information of the end point of the curve in the navigation path;
    采样范围确认子模块，用于根据所述弯道结束点位置信息确定所述采样范围和所述转弯弧长。A sampling range confirmation sub-module, configured to determine the sampling range and the turning arc length according to the position information of the end point of the curve.
  9. 根据权利要求8所述的装置，其特征在于，所述采样范围确认子模块，包括：The device according to claim 8, wherein the sampling range confirmation submodule comprises:
    采样范围计算单元，用于根据所述弯道结束点位置信息和预设参数计算采样范围；a sampling range calculation unit, configured to calculate the sampling range according to the position information of the end point of the curve and preset parameters;
    弯道弧长计算单元，用于根据所述当前车辆位置信息和所述弯道结束点位置信息计算所述转弯弧长。A curve arc length calculation unit, configured to calculate the turning arc length according to the current vehicle position information and the position information of the end point of the curve.
  10. 根据权利要求8所述的装置，其特征在于，所述当前车辆位置信息包括第一坐标位置、第一航向角，所述目标车辆位置信息包括第二航向角，所述弯道结束点位置信息包括第三坐标位置，所述目标转弯路径选取模块，包括：The device according to claim 8, wherein the current vehicle position information includes a first coordinate position and a first heading angle, the target vehicle position information includes a second heading angle, and the curve end point position information Including the third coordinate position, the target turning path selection module, including:
    坐标位置计算子模块，用于根据所述螺旋线参数和所述转弯弧长计算所述目标车辆位置信息的第二坐标位置；a coordinate position calculation submodule, configured to calculate the second coordinate position of the target vehicle position information according to the helix parameter and the turning arc length;
    距离代价计算子模块，用于根据所述第一坐标位置、所述第二坐标位置以及所述第三坐标位置计算距离代价，其中，所述距离代价小于第一预设阈值；a distance cost calculation submodule, configured to calculate a distance cost according to the first coordinate position, the second coordinate position and the third coordinate position, wherein the distance cost is less than a first preset threshold;
    航向角差值代价计算子模块，用于根据所述第一航向角和所述第二航向角计算航向角差值代价，其中，所述航向角差值代价小于第二预设阈值；a heading angle difference cost calculation submodule, configured to calculate a heading angle difference cost according to the first heading angle and the second heading angle, wherein the heading angle difference cost is less than a second preset threshold;
    曲率变化代价计算子模块，用于根据所述转弯弧长和所述螺旋线参数计算曲率变化代价；a curvature change cost calculation submodule, configured to calculate a curvature change cost according to the turning arc length and the helix parameter;
    目标转弯路径选取子模块，用于将所述距离代价、所述航向角差值代价以及所述曲率变化代价加权求和得到所述转弯路径的总代价，并选取所述总代价最小的所述转弯路径作为所述目标转弯路径。A target turning path selection sub-module, used for weighted summation of the distance cost, the heading angle difference cost and the curvature change cost to obtain the total cost of the turning path, and select the minimum cost of the total cost. The turning path is used as the target turning path.
  11. 一种车辆，其特征在于，包括处理器、存储器及存储在所述存储器上并能够在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现如权利要求1至6中任一项所述的车辆转弯路径规划方法的步骤。A vehicle, characterized in that it comprises a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program being executed by the processor to realize the invention as claimed in claim 1 to Steps of the vehicle turning path planning method described in any one of 6.
  12. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储计算机程序，所述计算机程序被处理器执行时实现如权利要求1至6中任一项所述的车辆转弯路径规划方法的步骤。A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the vehicle turning path according to any one of claims 1 to 6 is realized Steps in the planning method.
PCT/CN2021/141754 2020-12-30 2021-12-27 Vehicle turning path planning method and apparatus, vehicle, and storage medium WO2022143560A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011629184.X 2020-12-30
CN202011629184.XA CN112683291B (en) 2020-12-30 2020-12-30 Vehicle turning path planning method and device, vehicle and storage medium

Publications (1)

Publication Number Publication Date
WO2022143560A1 true WO2022143560A1 (en) 2022-07-07

Family

ID=75455881

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/141754 WO2022143560A1 (en) 2020-12-30 2021-12-27 Vehicle turning path planning method and apparatus, vehicle, and storage medium

Country Status (2)

Country Link
CN (1) CN112683291B (en)
WO (1) WO2022143560A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115123217A (en) * 2022-09-02 2022-09-30 青岛慧拓智能机器有限公司 Mining area obstacle vehicle driving track generation method and device and computer equipment
CN116797004A (en) * 2023-08-25 2023-09-22 深圳市金泰谊电子有限公司 Industrial traffic management method, device, equipment and medium based on 5G communication
CN117555340A (en) * 2024-01-12 2024-02-13 北京集度科技有限公司 Path planning method and related device

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112683291B (en) * 2020-12-30 2023-03-31 广州小鹏自动驾驶科技有限公司 Vehicle turning path planning method and device, vehicle and storage medium
CN114001739B (en) * 2021-10-11 2024-04-16 广州小鹏自动驾驶科技有限公司 Path planning method, device, vehicle and storage medium
CN114111788A (en) * 2021-11-09 2022-03-01 武汉乐庭软件技术有限公司 Trajectory planning method and device based on multi-segment clothoid and storage device
CN115200604B (en) * 2022-09-16 2023-05-16 广州小鹏自动驾驶科技有限公司 Turning path planning method, equipment, vehicle and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104303123A (en) * 2012-05-11 2015-01-21 天宝导航有限公司 Path planning autopilot
US9816822B1 (en) * 2016-09-30 2017-11-14 X Development Llc Assisted roadmap generation
CN107662609A (en) * 2016-07-29 2018-02-06 长城汽车股份有限公司 Control method, system and the vehicle of turn inside diameter
CN108082185A (en) * 2017-03-30 2018-05-29 长城汽车股份有限公司 A kind of travel control method of vehicle, device and vehicle
CN110262508A (en) * 2019-07-06 2019-09-20 深圳数翔科技有限公司 Applied to the automated induction systems and method on the closing unmanned goods stock in place
CN110825078A (en) * 2019-10-10 2020-02-21 江苏大学 Ground turning path control system of autonomous navigation tracked vehicle
CN112683291A (en) * 2020-12-30 2021-04-20 广州小鹏自动驾驶科技有限公司 Vehicle turning path planning method and device, vehicle and storage medium

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111552296B (en) * 2020-05-14 2021-03-26 宁波智能装备研究院有限公司 Local smooth track planning method based on curved cylindrical coordinate system
CN112078594B (en) * 2020-08-31 2023-01-13 纵目科技（上海）股份有限公司 Curvature continuous parking path planning device and method for intelligent parking system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104303123A (en) * 2012-05-11 2015-01-21 天宝导航有限公司 Path planning autopilot
CN107662609A (en) * 2016-07-29 2018-02-06 长城汽车股份有限公司 Control method, system and the vehicle of turn inside diameter
US9816822B1 (en) * 2016-09-30 2017-11-14 X Development Llc Assisted roadmap generation
CN108082185A (en) * 2017-03-30 2018-05-29 长城汽车股份有限公司 A kind of travel control method of vehicle, device and vehicle
CN110262508A (en) * 2019-07-06 2019-09-20 深圳数翔科技有限公司 Applied to the automated induction systems and method on the closing unmanned goods stock in place
CN110825078A (en) * 2019-10-10 2020-02-21 江苏大学 Ground turning path control system of autonomous navigation tracked vehicle
CN112683291A (en) * 2020-12-30 2021-04-20 广州小鹏自动驾驶科技有限公司 Vehicle turning path planning method and device, vehicle and storage medium

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115123217A (en) * 2022-09-02 2022-09-30 青岛慧拓智能机器有限公司 Mining area obstacle vehicle driving track generation method and device and computer equipment
CN115123217B (en) * 2022-09-02 2022-11-25 青岛慧拓智能机器有限公司 Mine obstacle vehicle driving track generation method and device and computer equipment
CN116797004A (en) * 2023-08-25 2023-09-22 深圳市金泰谊电子有限公司 Industrial traffic management method, device, equipment and medium based on 5G communication
CN116797004B (en) * 2023-08-25 2023-12-08 深圳市金泰谊电子有限公司 Industrial traffic management method, device, equipment and medium based on 5G communication
CN117555340A (en) * 2024-01-12 2024-02-13 北京集度科技有限公司 Path planning method and related device
CN117555340B (en) * 2024-01-12 2024-04-09 北京集度科技有限公司 Path planning method and related device

Also Published As

Publication number Publication date
CN112683291A (en) 2021-04-20
CN112683291B (en) 2023-03-31

Similar Documents

Publication Publication Date Title
WO2022143560A1 (en) Vehicle turning path planning method and apparatus, vehicle, and storage medium
KR102544948B1 (en) Motion graph construction and lane-level route planning
US11294060B2 (en) System and method for lidar-based vehicular localization relating to autonomous navigation
AU2016203177B2 (en) Navigation application
CN111860228B (en) Method, device, equipment and storage medium for autonomous parking
US8417448B1 (en) Electronic direction technology
EP3769043B1 (en) Methods and systems for generating parking routes
CN108628324B (en) Unmanned vehicle navigation method, device, equipment and storage medium based on vector map
JP6055821B2 (en) Combined radar and GPS location system
US9146125B2 (en) Navigation application with adaptive display of graphical directional indicators
JP2018084573A (en) Robust and efficient algorithm for vehicle positioning and infrastructure
CN109489675A (en) The path planning based on cost for automatic driving vehicle
JP4293751B2 (en) Boeing coefficient display for curvature of geographic form
JP2008059593A (en) Method for recognizing object in image and image recognition device
WO2020063816A1 (en) Method for constructing driving coordinate system, and application thereof
CN111694356A (en) Driving control method and device, electronic equipment and storage medium
WO2022052567A1 (en) Vehicle positioning method and apparatus, vehicle, and storage medium
JP7165586B2 (en) Method and system for determining safe return range
KR102549258B1 (en) Monocular 3d object detection from image semantics network
EP3622251A1 (en) Landmark-assisted navigation
CN112444263A (en) Global path planning method and device
WO2019076119A1 (en) Vehicle positioning method and apparatus
US20170059351A1 (en) Method and apparatus for route calculation involving freeway junction
CN114179815B (en) Method and device for determining vehicle driving track, vehicle, electronic equipment and medium
EP3648021A1 (en) Generation of optimal trajectories for navigation of vehicles

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: 21914296

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21914296

Country of ref document: EP

Kind code of ref document: A1