WO2019080782A1 - 施工路段无人驾驶车辆的路径生成方法及装置 - Google Patents

施工路段无人驾驶车辆的路径生成方法及装置

Info

Publication number
WO2019080782A1
WO2019080782A1 PCT/CN2018/111087 CN2018111087W WO2019080782A1 WO 2019080782 A1 WO2019080782 A1 WO 2019080782A1 CN 2018111087 W CN2018111087 W CN 2018111087W WO 2019080782 A1 WO2019080782 A1 WO 2019080782A1
Authority
WO
WIPO (PCT)
Prior art keywords
waypoint
current
area
section
obstacle
Prior art date
Application number
PCT/CN2018/111087
Other languages
English (en)
French (fr)
Inventor
甘新华
查鸿山
黄少堂
徐伟
修彩靖
Original Assignee
广州汽车集团股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广州汽车集团股份有限公司 filed Critical 广州汽车集团股份有限公司
Priority to US16/489,365 priority Critical patent/US11221224B2/en
Publication of WO2019080782A1 publication Critical patent/WO2019080782A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • E—FIXED CONSTRUCTIONS
    • E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
    • E02F—DREDGING; SOIL-SHIFTING
    • E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
    • E02F9/26—Indicating devices
    • E02F9/261—Surveying the work-site to be treated
    • E02F9/262—Surveying the work-site to be treated with follow-up actions to control the work tool, e.g. controller
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • E—FIXED CONSTRUCTIONS
    • E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
    • E02F—DREDGING; SOIL-SHIFTING
    • E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
    • E02F9/20—Drives; Control devices
    • E02F9/2025—Particular purposes of control systems not otherwise provided for
    • E02F9/2045—Guiding machines along a predetermined path
    • E—FIXED CONSTRUCTIONS
    • E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
    • E02F—DREDGING; SOIL-SHIFTING
    • E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
    • E02F9/20—Drives; Control devices
    • E02F9/2025—Particular purposes of control systems not otherwise provided for
    • E02F9/205—Remotely operated machines, e.g. unmanned vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3602—Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
    • 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
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/165—Anti-collision systems for passive traffic, e.g. including static obstacles, trees

Definitions

  • the present invention relates to the field of unmanned driving technology, and in particular, to a path generating method, device, computer readable storage medium and computer device for an unmanned vehicle in a construction road section.
  • unmanned vehicles generally rely on pre-stored navigation maps in the vehicle to generate travel paths.
  • the driving route generated based on the navigation map cannot adapt to the real-time road condition of the construction section, and thus the unmanned vehicle cannot be guided smoothly through the construction section.
  • a method for generating a path of an unmanned vehicle in a construction section comprising:
  • the obstacle information includes a category and feature information of the obstacle, and the feature information includes the location information;
  • a path generating device for an unmanned vehicle in a construction section comprising:
  • a feature information acquiring module configured to acquire the detected obstacle information when the construction road segment is detected, the obstacle information includes a category and feature information of the obstacle, and the feature information includes the location information;
  • a pass area determining module configured to determine a current passable area of the construction road segment according to the category and feature information of the obstacle, and determine each waypoint included in the current passable area
  • a terminating waypoint determining module configured to determine a terminating waypoint of the target driving route according to the current passable area
  • a route waypoint determining module configured to use a current location of the vehicle as a starting waypoint, and perform a path search according to the starting waypoint and the terminating waypoint in each of the waypoints included in the current passable zone, Determining a waypoint of the target travel path in the detected construction section;
  • a driving path generating module configured to generate the target driving path according to the starting waypoint, the way waypoint, and the terminating waypoint.
  • a computer readable storage medium having stored thereon computer executable instructions, the computer executable instructions being executed by a processor, causing the processor to perform a construction road unmanned as described above The steps of the path generation method of the vehicle.
  • a computer apparatus comprising a memory and a processor, the memory storing computer readable instructions, the computer readable instructions being executed by the processor, causing the processor to perform a construction road segment as described above The steps of the path generation method of driving the vehicle.
  • the path generation method, device, computer readable storage medium and computer equipment of the unmanned vehicle in the above construction section determine the current state of the construction section according to the category and position information of the obstacle detected in the detection range when the construction section is detected
  • the passable area can be seen.
  • the passable area of the construction section is determined according to the detected real-time obstacle information of the construction section, and can adapt to the real-time road condition of the construction section. Therefore, the travel path generated based on the passable area can also be adapted. Real-time road conditions on construction sections.
  • FIG. 1 is a schematic flow chart showing a path generation method of an unmanned vehicle in a construction road section in an embodiment
  • FIG. 2 is a schematic structural view of a path generating device for an unmanned vehicle in a construction road section in an embodiment
  • FIG. 3 is a block diagram showing the structure of a computer device in an embodiment.
  • the path generation method for the unmanned vehicle of the construction road section can be applied to an unmanned vehicle, where the unmanned vehicle generally relates to an environment sensing system and a control terminal, and the environment sensing system and the control terminal can be wired. Or wirelessly connected for data communication.
  • the control terminal may be an in-vehicle terminal or a mobile terminal, and the mobile terminal may specifically be a mobile phone, a tablet computer or a notebook computer.
  • FIG. 1 is a flow chart showing a path generation method of an unmanned vehicle in a construction section in one embodiment.
  • the method is applied to the above control terminal as an example.
  • the method specifically includes the following steps S102 to S110.
  • Step S102 Acquire, when the construction road segment is detected, the detected obstacle information, where the obstacle information includes the category and feature information of the obstacle, and the feature information includes the location information;
  • the environment sensing system on the vehicle can detect the surrounding environment of the vehicle in real time based on the predetermined detection range, and collect environmental information.
  • the context aware system can include a lidar and a camera, and accordingly, the environmental information can include point cloud data acquired by the lidar and image data acquired by the camera.
  • the point cloud data is generally a set of vectors located in a three-dimensional coordinate system. The vectors in the set are often represented in the form of X, Y, and Z three-dimensional coordinates, and the point cloud data can be used to represent the shape of the three-dimensional object.
  • control terminal may perform data processing and analysis on the environmental information collected by the environment sensing system, thereby acquiring information such as obstacles, traffic signs, and traffic markings on the road surface within the detection range.
  • the control terminal can determine whether there is a construction section in the driving direction of the vehicle based on the environmental information collected by the environment sensing system on the vehicle.
  • the construction mark refers to an object that is often placed near the road construction site, for example, a sign indicating construction information (such as "before construction, please bypass"), traffic protection facilities for construction roads, and Designation of construction vehicles (such as excavators and forklifts) under working conditions.
  • the detection range may refer to a predetermined detection range of the environment sensing system on the vehicle, and the predetermined detection range is related to hardware selection of the environment sensing system. It can be understood that when there is an obstacle in the construction section within the detection range, the environmental information collected by the environment sensing system may include the information of the obstacle, and then the control computer device may detect the detection range based on the environmental information. Obstacle information.
  • the obstacle information includes the category and characteristic information of the obstacle.
  • the categories of obstacles can be divided into pedestrian obstacles, vehicle obstacles and other obstacles that are neither pedestrians nor vehicles.
  • the obtained image data may be captured based on the camera and combined with deep learning to identify the category of the obstacle; or the sample obstacle may be clustered based on the point cloud data of the large number of sample obstacles obtained by the lidar scan, and the sample is sampled.
  • the reflection intensity of the obstacle, the width of the lateral and vertical directions, and the position and posture as its characteristics, the three-dimensional object information is extracted, thereby obtaining a training set, and when the obstacle to be identified is acquired, the obstacle to be identified can be obtained.
  • the laser radar can be integrated with the camera so that it can fully exert its respective advantages, thereby Identify the categories of obstacles more accurately.
  • the position information of the obstacle can be used to determine the position of the obstacle in the detected construction section.
  • the position information of the obstacle may be represented by a two-dimensional matrix, and more specifically, one fixed coordinate in the two-dimensional matrix may be set as the current position of the vehicle, and the other coordinates are the detected obstacles. position.
  • Step S104 determining a current passable area of the construction road segment according to the category and location information of the obstacle, and determining each waypoint included in the current passable area;
  • some areas are inaccessible to the vehicle, such as an area where construction work is required and an area for stacking construction materials, and an area other than the unreachable area is an area through which the vehicle can pass.
  • the position point of the obstacle on the construction road segment is obtained according to the position information of the obstacle, and the area where the distance from the position point exceeds the preset distance value is determined as the current current of the construction road section.
  • Access area For example, if the preset distance value is 1.2 meters and there is only one obstacle to be considered in the detection range, the area covered by the position of the obstacle is 1.2 meters and the area covered by the surrounding area is the current impassable for the construction section. The area, correspondingly, the area of the construction section other than the non-passage area is the current passable area of the construction section.
  • each obstacle corresponds to a current non-passable area, and correspondingly, all the currently inaccessible areas corresponding to the obstacles in the construction section are The area is the current accessible area of the construction section.
  • the environment sensing system is generally placed at the center of the roof, so that after obtaining the position information of the obstacle, the current passable area can be determined together with the width of the vehicle itself.
  • the preset distance value is set according to the width of the vehicle itself.
  • each waypoint included in the current passable area can be determined based on the pre-stored map data.
  • Step S106 determining a termination waypoint of the target travel path according to the current passable area
  • the target driving path refers to a driving path to be detected for the detected construction section, and is used for guiding the unmanned vehicle to pass the detected construction section.
  • the terminating waypoint refers to the end point of the target driving route.
  • a waypoint meeting the preset condition may be selected as the terminating waypoint among the respective waypoints included in the current passable area.
  • Step S108 using the current location of the vehicle as a starting waypoint, performing a path search on each of the waypoints included in the current passable area according to the initial waypoint and the terminating waypoint, and determining the target driving. a waypoint in the path of the construction section;
  • the current location of the vehicle is located by the vehicle positioning technology, wherein the vehicle positioning technology may include any one of GPS positioning, magnetic navigation positioning, and visual navigation positioning. Or a variety. Thereafter, the current location of the vehicle can be used as the starting waypoint of the target travel route.
  • the way way point refers to all the way points covered by one path, except the starting way point and the ending way point. It can be understood that the way of determining the waypoint is not unique, and it is only necessary to ensure that the route of the target driving path in the detected construction section is located in the passable area, and the starting waypoint, each waypoint and the termination Corresponding connectivity is provided between the waypoints, and the starting waypoint and the terminating waypoint can be connected through each route. It can be seen that there are various ways to determine the waypoints, so that for a passable area, multiple sets of waypoints meeting the above conditions can be determined among all the waypoints it contains.
  • Step S110 generating the target driving path according to the starting waypoint, the way waypoint, and the terminating waypoint.
  • the target driving path refers to a path from the starting way point to the ending path and covering all way way points, and can be used to guide the unmanned vehicle to pass the detected construction section.
  • the path generation method of the unmanned vehicle in the above construction section determines the current passable area of the construction section according to the category and position information of the obstacle detected in the detection range when the construction section is detected, and it can be seen that the construction section can pass
  • the area is determined according to the detected real-time obstacle information of the construction section, and can adapt to the real-time road condition of the construction section. Therefore, the driving path generated based on the traversable area can also adapt to the real-time road condition of the construction section.
  • the feature information further includes shape information and size information
  • the manner of determining the current passable area of the construction section according to the category and location information of the obstacle may include:
  • An area of the detected construction road section other than the current non-passable area is determined as the current passable area.
  • an obstacle that is neither a pedestrian nor a vehicle can be used as an obstacle of a specified category, such as a construction sign placed on a road, a traffic protection facility, or the like. Further, it is possible to determine, according to the position information, the shape information, and the size information of the obstacles of the specified categories, the obstacles in the specified construction category in the detected construction road sections, regardless of the obstacles outside the designated category. .
  • the barrier area may be an area occupied by the obstacle of the specified category on the detected construction section. It can be understood that if the vehicle body crosses the boundary of the obstacle area of a certain category of obstacles, The obstacle collides, so the passable area should avoid the obstacled area of the obstacle.
  • the contact area of the obstacle of the specified category and the road surface of the construction road section can be determined as the barrier area.
  • the area corresponding to the projection of the obstacle of the specified category on the road surface of the construction section may also be determined as the obstacle area of the obstacle. It should be noted that determining the barrier region based on the projection can reduce the probability of the unmanned vehicle colliding with the obstacle of the specified category during the running, compared to the above determining the barrier region according to the contact region.
  • the construction section has a "T" shaped obstacle of a specified type, and the contact area of the obstacle with the construction section is an area defined by the bottom of the "
  • the "one" part is an obstacle to the driverless vehicle, so the vehicle may still collide with the obstacle.
  • the area corresponding to the projection of the obstacle on the road surface of the construction section takes into consideration the obstacle of the outer edge of the obstacle to the unmanned vehicle, thereby reducing the obstacle of the unmanned vehicle during the driving and the specified category. The probability of a collision.
  • the step of determining the current non-passable area of the detected construction section based on the barrier area may include:
  • the area obtained by extending the edge of the barrier region to the periphery by a predetermined distance value is determined as the current non-passable area of the detected construction section.
  • the non-passing area needs to be able to completely cover the barrier area, and based on the width of the vehicle itself, a certain distance may be left between the boundary line and the boundary line corresponding to the barrier area, that is, preset The distance corresponding to the distance value.
  • the corresponding non-passable region may have the same shape as the barrier region, can completely cover the barrier region, and between the edge line and the corresponding edge of the barrier region.
  • the distance is the area of the preset distance value.
  • the obstacle area is a square with a side length of 0.5 meters. If the preset distance value is 1 meter, the corresponding non-passable area is, and the edge of the square extends 1 meter to the periphery.
  • the obtained square can completely cover the square, and the four sides thereof have a side length of 2.5 meters, and the four sides thereof and the four sides of the square respectively correspond to parallel squares.
  • the step of determining the ending waypoint of the target driving path according to the current passable area may include:
  • the end point of the target travel path is determined according to the line point in the lane covered by the road cross section of the predetermined condition, and the road cross section of the predetermined condition is: from the predetermined condition
  • the road cross section of all the lanes covered by the road section starting from the detected construction section is located in the cross section of the road in the current passable area;
  • the terminating waypoint is determined according to the waypoint of the predetermined condition, and the waypoint of the predetermined condition is located in the detecting a farthest point of the range and located in a lane in the current passable area;
  • the position of the road cross section of the predetermined condition is the end position of the entire construction section, that is, the entire construction section is stopped at this position.
  • one of the route points in the lane covered by the road cross section of the predetermined condition may be selected as the termination waypoint of the target travel route, and may be based on the vehicle The driving direction is selected.
  • the road cross section of the predetermined condition covers three lanes, which are a left turn lane, a straight lane, and a right turn lane. If the vehicle needs to turn right, the right cross of the road cross section of the predetermined condition is turned.
  • the route point in the lane of the lane is determined to be the termination waypoint.
  • the terminating waypoint can be determined according to the route point (the waypoint of the predetermined condition) located at the farthest end of the current detection range and located in the current passable area. It can be understood that the current detection range is the most The corresponding position of the distal end is the ending position of the part of the construction section covered in the current detection range.
  • the waypoint of the predetermined condition is not found, it indicates that the detected construction section is impassable, and further searching for the passable gap, such as a U-turn, is found on the cross-section of the farthest road in the detection range.
  • the passable gap is searched, the stop waypoint of the target travel route is determined according to the passable gap. Specifically, the midpoint of the searchable passable gap can be used as the stop waypoint of the target travel route.
  • the step of generating the target driving path according to the starting waypoint, the way waypoint, and the terminating waypoint may include:
  • the initial travel path is filtered to obtain the target travel path.
  • the target driving path may be generated according to the initial waypoint, the waypoint, the terminating waypoint, and the preset path searching algorithm, and the target driving path generated by the preset search algorithm may be rough, so it may be performed
  • the filtering process is performed to smooth the target traveling path, thereby improving the accuracy of the target traveling path.
  • the target travel path can be generated according to the A-star algorithm.
  • the initial travel path obtained by the A-star algorithm is generally not very smooth. After the Bezier curve filtering is performed on the initial travel path obtained by the A-star algorithm, more For a smooth driving path.
  • the preset path search algorithm includes an A-star algorithm, and the formula for calculating the total cost value of the current waypoint in the A-star algorithm is:
  • f(t) is the total cost value of the current waypoint
  • g(t) is the cumulative distance cost of the starting waypoint to the current waypoint
  • h(t) is the current waypoint to The estimated distance cost of the terminating waypoint
  • e(t) is the distance cost of the target obstacle closest to the current waypoint to the current waypoint
  • k is a preset cost constant.
  • the estimated distance cost can be the Manhattan distance cost, that is, the sum of the longitude distance difference between the current waypoint and the ending waypoint and the latitude distance difference, and the Manhattan distance can be used for estimation, which can be easily and quickly estimated.
  • the estimated distance cost may also be a European distance cost or a diagonal line, etc., and is not specifically limited herein.
  • e(t) is the target obstacle distance cost at the current waypoint, which considers the distance between the obstacle of the specified category and the current waypoint closest to the current waypoint.
  • the larger the distance, the smaller e(t), and the distance threshold may be preset such that e(t) is 0 when the distance is greater than the distance threshold.
  • the distance threshold can be set to 1.8 meters based on actual demand.
  • k is a preset cost constant, which can be calibrated based on the measured effect of the construction section.
  • the A-star algorithm is a path search algorithm based on the shortest path principle. Therefore, the present embodiment can obtain the shortest path from the starting waypoint to the ending waypoint. Moreover, the present embodiment improves the cost function of the conventional A-star algorithm, and adds the consideration of the distance between the path and the obstacle of the specified category. Therefore, based on the target driving path generated by the embodiment, the vehicle can be in the passing process. Maintain an appropriate safety margin with obstacles of the specified category.
  • the length of the actual construction section is different.
  • the detection range of the environment sensing system can cover the entire construction section at one time, and correspondingly, the steps of any embodiment provided by the present invention. Execute once, generate a target driving path, and then guide the vehicle through the entire construction section.
  • the detection range of the environment-aware system cannot cover the entire construction section at one time, and it is necessary to generate a corresponding target driving path for each detection range covering the construction section, and generate multiple target driving paths. End to end, the vehicle can travel through the entire construction route in accordance with the multiple target driving routes.
  • the detection range of the environment-aware system set on the vehicle is 100 meters, that is, it can only cover 100 meters at a time, it is necessary to generate a driving path for a construction section with a length of 800 meters.
  • the starting point is A and the ending point is E.
  • the ending point is E.
  • 3 intermediate points B, C and D The distance between adjacent two points is 100 meters. If the current position of the vehicle is just at point A, then you need Mr. Forming a first target travel route from A to B.
  • a second target travel route from B to C is generated, when the vehicle travels according to the second target travel route.
  • a third target driving path from C to D is generated.
  • a fourth target driving path from D to E is finally generated, and the vehicle sequentially According to the four target driving routes, you can pass the entire construction section.
  • Fig. 2 is a block diagram showing the structure of a path generating device for an unmanned vehicle in a construction section in one embodiment.
  • the apparatus 200 may specifically include the following modules:
  • the feature information acquiring module 202 is configured to acquire the detected obstacle information when the construction road segment is detected, the obstacle information includes the category and feature information of the obstacle, and the feature information includes the location information;
  • the pass area determining module 204 is configured to determine a current passable area of the construction road segment according to the category and location information of the obstacle, and determine each waypoint included in the current passable area;
  • the terminating waypoint determining module 206 is configured to determine a terminating waypoint of the target driving route according to the current passable area
  • the waypoint determination module 208 is configured to use the current location of the vehicle as a starting waypoint, and perform path searching according to the starting waypoint and the terminating waypoint in each of the waypoints included in the current passable zone. Determining a waypoint of the target travel path in the construction section;
  • the driving path generating module 210 is configured to generate the target driving path according to the starting waypoint, the way waypoint, and the terminating waypoint.
  • the path generating device of the unmanned vehicle in the above construction section determines the current passable area of the construction section according to the type and position information of the obstacle detected in the detection range when the construction section is detected, and it can be seen that the construction section can pass
  • the area is determined according to the detected real-time obstacle information of the construction section, and can adapt to the real-time road condition of the construction section. Therefore, the driving path generated based on the traversable area can also adapt to the real-time road condition of the construction section.
  • the feature information further includes shape information and size information
  • the transit area determining module 204 may include:
  • the barrier area determining unit is configured to determine, according to the position information, the shape information, and the size information of the obstacle of the specified category, the obstacle in each of the specified categories in the detected construction section;
  • a non-passable area determining unit configured to determine a current non-passable area of the detected construction section based on the barrier area
  • the passable area determining unit is configured to determine an area of the detected construction road section other than the current non-passable area as the current passable area.
  • the non-passable area determining unit may be configured to: determine an area obtained by extending an edge of the barrier area to a circumference by a preset distance value, and determine the current inaccessible area of the detected construction section. .
  • the terminating waypoint determination module 206 can include:
  • a first terminating waypoint determining unit configured to determine a terminating waypoint of the target driving route according to the route point in the lane covered by the road cross section of the predetermined condition when the road cross section of the predetermined condition is searched, the predetermined condition
  • the road cross section is: a road cross section of the lanes of all the lanes covered by the detected construction section starting from the road cross section of the predetermined condition, and the road section in the currently available passage area;
  • a second terminating waypoint determining unit configured to determine the terminating waypoint according to the waypoint of the predetermined condition when the road cross section of the predetermined condition is not searched but the waypoint of the predetermined condition is searched,
  • the waypoint of the predetermined condition is a lane point in the lane located at the farthest end of the detection range and located in the current passable area;
  • a third terminating waypoint determining unit configured to search for a farthest road cross section of the detection range when a road cross section of the predetermined condition is not searched and a waypoint of the predetermined condition is not searched.
  • the passable gap is determined, and the terminating waypoint is determined according to the passable gap.
  • the travel path generating module 210 may include:
  • An initial path generating unit configured to generate an initial driving path according to the starting waypoint, the way waypoint, and the terminating waypoint;
  • a target path generating unit configured to filter the initial driving path to obtain the target driving path.
  • the A-star algorithm is used for path search.
  • the total value of the current waypoint is calculated using the following formula:
  • f(t) is the total cost value of the current waypoint
  • g(t) is the cumulative distance cost of the starting waypoint to the current waypoint
  • h(t) is the current waypoint to The estimated distance cost of the terminating waypoint
  • e(t) is the distance cost of the obstacle of the specified class closest to the current waypoint to the current waypoint
  • k is a cost constant.
  • path generating device of the unmanned vehicle of the construction section of the present embodiment may be the same as those in the embodiment of the path generating method of the unmanned vehicle of the above-described construction section.
  • Figure 3 shows an internal block diagram of a computer device in one embodiment.
  • the computer device may in particular be the control terminal described above.
  • the computer device can include a processor, memory, network interface, input device, and display screen connected by a system bus.
  • the memory comprises a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium of the computer device stores an operating system, and can also store a computer program, which when executed by the processor, can cause the processor to implement the path generation method of the unmanned vehicle in the construction section.
  • the internal memory may also store a computer program that, when executed by the processor, causes the processor to execute the path generation method of the unmanned vehicle of the construction road section described above.
  • the display screen of the computer device may be a liquid crystal display or an electronic ink display screen
  • the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touchpad provided on the computer device casing, and It can be an external keyboard, trackpad or mouse.
  • FIG. 3 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation of the computer device to which the solution of the present application is applied.
  • the specific computer device may It includes more or fewer components than those shown in the figures, or some components are combined, or have different component arrangements.
  • the path generation device for a construction road segment unmanned vehicle may be implemented in the form of a computer program that can be run on a computer device as shown in FIG.
  • the program module of the path generating device of the unmanned vehicle of the construction road section can be stored in the memory of the computer device, for example, the feature information acquiring module 202, the passing area determining module 204, the ending waypoint determining module 206, and the The waypoint determination module 208 and the travel path generation module 210.
  • the computer program of each program module causes the processor to execute the steps in the path generation method of the unmanned vehicle of the construction road section of the embodiments of the present application described in the present specification.
  • the computer device shown in FIG. 3 can execute the step S102 in FIG. 2 by the feature information acquiring module 202 in the path generating device of the unmanned vehicle of the construction road segment as shown in FIG. 2, and can be executed by the pass region determining module 204.
  • Step S104 in FIG. 2, and step S106 in FIG. 2 and the like can be performed by the terminating waypoint determination module 206.
  • an embodiment further provides a computer device comprising a memory and a processor, the memory storing computer readable instructions, the computer readable instructions being executed by the processor, such that the processor The steps of the path generation method of the unmanned vehicle of the construction road section in any of the embodiments provided by the present application.
  • the computer equipment determines the current passable area of the construction road section according to the category and position information of the obstacle detected in the detection range. It can be seen that the trafficable area of the construction road section is based on the detected construction.
  • the real-time obstacle information of the road segment is determined, and can adapt to the real-time road condition of the construction road section. Therefore, the travel path generated based on the passable area can also adapt to the real-time road condition of the construction road section.
  • Non-volatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory can include random access memory (RAM) or external cache memory.
  • RAM is available in a variety of formats, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization chain.
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDRSDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • Synchlink DRAM SLDRAM
  • Memory Bus Radbus
  • RDRAM Direct RAM
  • DRAM Direct Memory Bus Dynamic RAM
  • RDRAM Memory Bus Dynamic RAM
  • an embodiment further provides a computer readable storage medium having stored thereon computer executable instructions that, when executed by a processor, cause the processor to execute The steps of the path generation method of the construction road segment unmanned vehicle in any of the embodiments provided by the present application.
  • the above-mentioned computer readable storage medium determines the current passable area of the construction road section according to the category and position information of the obstacle detected within the detection range when the construction road section is detected, and it can be seen that the passable area of the construction road section is detected according to The real-time obstacle information of the construction section is determined, and can adapt to the real-time road condition of the construction section. Therefore, the travel route generated based on the passable area can also adapt to the real-time road condition of the construction section.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Mining & Mineral Resources (AREA)
  • Civil Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Structural Engineering (AREA)
  • Evolutionary Computation (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Electromagnetism (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

一种施工路段无人驾驶车辆的路径生成方法、装置、计算机设备及存储介质，方法包括：在检测到施工路段时，获取检测到的障碍物信息，障碍物信息包括障碍物的类别和特征信息，特征信息包括位置信息（S102）；根据障碍物的类别和位置信息，确定施工路段的当前可通行区域，并确定当前可通行区域中包含的各路点（S104）；根据当前可通行区域确定目标行驶路径的终止路点（S106）；将车辆当前所处位置作为起始路点，根据起始路点、终止路点在当前可通行区域包含的各路点中进行路径搜索，确定目标行驶路径在施工路段中的途径路点（S108）；根据起始路点、途径路点以及终止路点生成目标行驶路径（S110）。该方法能适应施工路段的道路实况。

Description

施工路段无人驾驶车辆的路径生成方法及装置 技术领域
本发明涉及无人驾驶技术领域，特别是涉及一种施工路段无人驾驶车辆的路径生成方法、装置、计算机可读存储介质及计算机设备。
背景技术
目前，无人驾驶车辆一般是依赖于车辆中预先存储的导航地图生成行驶路径。然而，对于路况复杂多变的施工路段，基于导航地图生成的行驶路径无法适应施工路段的实时路况，从而无法引导无人驾驶车辆顺利地通过施工路段。
发明内容
基于此，有必要针对传统方式中生成的行驶路径无法适应施工路段的实时路况的问题，提供一种施工路段无人驾驶车辆的路径生成方法、装置、计算机可读存储介质及计算机设备。
一种施工路段无人驾驶车辆的路径生成方法，所述方法包括：
在检测到施工路段时，获取检测到的障碍物信息，所述障碍物信息包括障碍物的类别和特征信息，所述特征信息包括位置信息；
根据所述障碍物的类别和位置信息，确定所述施工路段的当前可通行区域，并确定所述当前可通行区域中包含的各路点；
根据所述当前可通行区域确定目标行驶路径的终止路点；
将车辆当前所处位置作为起始路点，根据所述起始路点、所述终止路点在所述当前可通行区域包含的各路点中进行路径搜索，确定所述目标行驶路径在所述施工路段中的途径路点；
根据所述起始路点、所述途径路点以及所述终止路点生成所述目标行驶路径。
一种施工路段无人驾驶车辆的路径生成装置，所述装置包括：
特征信息获取模块，用于在检测到施工路段时，获取检测到的障碍物信息， 所述障碍物信息包括障碍物的类别和特征信息，所述特征信息包括位置信息；
通行区域确定模块，用于根据障碍物的类别和特征信息，确定所述施工路段的当前可通行区域，并确定所述当前可通行区域中包含的各路点；
终止路点确定模块，用于根据所述当前可通行区域确定目标行驶路径的终止路点；
途径路点确定模块，用于将车辆当前所处位置作为起始路点，根据所述起始路点、所述终止路点在所述当前可通行区域包含的各路点中进行路径搜索，确定所述目标行驶路径在检测到的施工路段中的途径路点；以及，
行驶路径生成模块，用于根据所述起始路点、所述途径路点以及所述终止路点生成所述目标行驶路径。
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有计算机可执行指令，所述计算机可执行指令被处理器执行时，使得所述处理器执行如上所述的施工路段无人驾驶车辆的路径生成方法的步骤。
一种计算机设备，包括存储器和处理器，所述存储器中存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述处理器执行如上所述的施工路段无人驾驶车辆的路径生成方法的步骤。
上述施工路段无人驾驶车辆的路径生成方法、装置、计算机可读存储介质及计算机设备，在检测到施工路段时，根据检测范围内检测到的障碍物的类别和位置信息确定该施工路段的当前可通行区域，可见，施工路段的可通行区域是根据检测到的该施工路段的实时障碍物信息确定的，能够适应施工路段的实时路况，因此，基于该可通行区域生成的行驶路径同样能够适应施工路段的实时路况。
附图说明
图1为一个实施例中施工路段无人驾驶车辆的路径生成方法的流程示意图；
图2为一个实施例中施工路段无人驾驶车辆的路径生成装置的结构示意图；
图3为一个实施例中计算机设备的结构框图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
本申请各实施例提供的施工路段无人驾驶车辆的路径生成方法可应用于无人驾驶车辆，该无人驾驶车辆一般涉及环境感知系统及控制终端，该环境感知系统和该控制终端可以通过有线或无线的方式连接，以进行数据通信。其中，控制终端可为车载终端或移动终端，移动终端具体可以为手机、平板电脑或笔记本电脑等。
图1示出了一个实施例中施工路段无人驾驶车辆的路径生成方法的流程示意图。该实施例中以该方法应用于上述控制终端举例说明。参照图1，该方法具体包括如下步骤S102至步骤S110。
步骤S102，在检测到施工路段时，获取检测到的障碍物信息，所述障碍物信息包括障碍物的类别和特征信息，所述特征信息包括位置信息；
在无人驾驶车辆的行驶过程中，可由车辆上的环境感知系统基于预定的检测范围实时检测本车周边环境，并采集环境信息。在一个具体的示例中，环境感知系统可包括激光雷达和摄像头，相应地，环境信息可包括激光雷达采集的点云数据和摄像头采集的图像数据。其中，点云数据一般为位于三维坐标系统中的向量的集合，该集合内的向量常以X、Y、Z三维坐标的形式表示，并且，点云数据可用于表征三维物体的形态。
进一步地，控制终端可对环境感知系统采集的环境信息进行数据的处理与分析，从而获取检测范围内的障碍物、交通指示牌和道路路面上的交通标线等信息。
一个实施例中，控制终端可基于本车上的环境感知系统采集的环境信息，判断本车行驶方向上是否存在施工路段。在一个具体示例中，当通过环境感知系统中的摄像头拍摄获得的图像，识别出本车行驶方向上存在施工标志物时，判定本车行驶方向上存在施工路段，即判定检测到施工路段。其中，施工标志物指的是常放置于道路施工位置附近的物体，例如，标有施工提示信息(如“前 方施工，请绕行”)的指示牌、用于施工道路的交通防护设施及处于指定工作状态下的施工用车(如挖掘机和铲车等)等。
另外，在检测到施工路段时，获取检测范围内检测到的障碍物信息。其中，检测范围可以指本车上的环境感知系统的预定检测范围，该预定检测范围与环境感知系统的硬件选型相关。可以理解的是，当位于检测范围内的施工路段中存在障碍物时，环境感知系统采集的环境信息中会包括该障碍物的信息，进而控制计算机设备可基于该环境信息获取检测范围内检测到的障碍物信息。其中，障碍物信息包括障碍物的类别及特征信息。
一方面，可将障碍物的类别分为行人障碍物、车辆障碍物和既非行人也非车辆的其他障碍物。具体地，可基于摄像头拍摄获得的图像数据，并结合深度学习识别障碍物的类别；或者，可基于激光雷达扫描获得的大量样本障碍物的点云数据，对样本障碍物进行聚类，把样本障碍物的反射强度、横向和纵向的宽度以及位置姿态作为它的特征，进行三维物体信息的提取，从而获得训练集，当获取到待识别的障碍物后，则可将该待识别的障碍物放入预先获得的训练集中，再利用SVM分类器识别障碍物的类别；另外，上述两种识别方式各有利弊，优选地，可将激光雷达与摄像头融合，使得其充分发挥各自的优势，从而更准确地识别障碍物的类别。
另一方面，障碍物的位置信息可用于确定该障碍物在检测到的施工路段中的位置。在一个具体的示例中，可以以二维矩阵表示障碍物的位置信息，更具体地，可设置二维矩阵中的一个固定坐标为本车当前所在的位置，其他坐标为检测到的障碍物的位置。
步骤S104，根据所述障碍物的类别和位置信息，确定所述施工路段的当前可通行区域，并确定所述当前可通行区域中包含的各路点；
一般，对一段施工路段而言，部分区域是车辆不可通行的，例如需要进行施工作业的区域和用于堆放施工物资的区域等，除不可通行的区域外的区域即为车辆可以通行的区域。
在一个实施例中，可根据障碍物的位置信息获得该障碍物在该施工路段上对应的位置点，再将与该位置点的距离超过预设距离值的区域确定为该施工路 段的当前可通行区域。例如，预设距离值为1.2米，且检测范围内仅存在一个需考虑的障碍物，则将以该障碍物的位置点向四周膨胀1.2米后所覆盖的区域作为该施工路段的当前不可通行区域，相应地，该施工路段中除该不可通行区域外的区域即为该施工路段的当前可通行区域。
此外，若检测范围内存在多个需考虑的障碍物，则各障碍物均一一对应一个当前不可通行区域，相应地，该施工路段中除上述各障碍物对应的所有当前不可通行区域外的区域即为该施工路段的当前可通行区域。
还需要说明的是，环境感知系统一般放置在车顶的中心位置，因此获得障碍物的位置信息后，可一并结合本车自身的宽度确定当前可通行区域。具体地，根据本车自身的宽度设定预设距离值。
需要说明的是，在地图数据中，通常使用包含经度、纬度数据的路点来保存车道信息，在每一条车道上勘测一系列连续编号的路点以确定该车道的几何参数。因此，在一个实施例中，可根据预存的地图数据确定当前可通行区域中包含的各路点。
步骤S106，根据所述当前可通行区域确定目标行驶路径的终止路点；
其中，目标行驶路径指的是待生成的针对检测到的施工路段的行驶路径，用于引导无人驾驶车辆通过该检测到的施工路段。终止路点指的是该目标行驶路径的终点，在一个具体的示例中，可在当前可通行区域所包含的各路点中选取满足预设条件的路点作为终止路点。
步骤S108，将车辆当前所处位置作为起始路点，根据所述起始路点、所述终止路点在所述当前可通行区域包含的各路点中进行路径搜索，确定所述目标行驶路径在所述施工路段中的途径路点；
在实际应用中，当满足生成行驶路径的条件时，通过车辆定位技术定位出车辆当前所处的位置，其中，车辆定位技术可包括GPS定位、磁导航定位及视觉导航定位等中的任意一种或多种。此后，则可将车辆当前所处的位置作为目标行驶路径的起始路点。
其中，途径路点是指一条路径所覆盖的所有路点中，除起始路点和终止路点外的各路点。可以理解的是，途径路点的确定方式不唯一，只需保证目标行 驶路径在检测到的施工路段中的途径路点均位于可通行区域内，且起始路点、各途径路点以及终止路点间具备相应的连通性，通过各途径路径能够将起始路点和终止路点连通即可。可知，确定途径路点的具体方式可以有多种，从而对于一个可通行区域而言，在其所包含的所有路点中可确定出多组符合上述条件的途径路点。
步骤S110，根据所述起始路点、所述途径路点以及所述终止路点生成所述目标行驶路径。
其中，目标行驶路径是指从起始路点通往终止路径，且覆盖所有途径路点的路径，可用于引导无人驾驶车辆通过检测到的施工路段。
上述施工路段无人驾驶车辆的路径生成方法，在检测到施工路段时，根据检测范围内检测到的障碍物的类别和位置信息确定该施工路段的当前可通行区域，可见，施工路段的可通行区域是根据检测到的该施工路段的实时障碍物信息确定的，能够适应施工路段的实时路况，因此，基于该可通行区域生成的行驶路径同样能够适应施工路段的实时路况。
为进一步对本发明的方案进行更详细的说明，下文对本发明的一些优选实施例进行具体描述或举例说明。
在一个实施例中，所述特征信息还包括形状信息和尺寸信息；
所述根据所述障碍物的类别和位置信息，确定所述施工路段的当前可通行区域的方式，可以包括：
根据指定类别的障碍物的位置信息、形状信息和尺寸信息，确定各指定类别的障碍物在检测到的施工路段中的设障区域；
基于所述设障区域确定检测到的施工路段的当前不可通行区域；
将检测到的施工路段中除所述当前不可通行区域外的区域确定为所述当前可通行区域。
需要说明的是，可能检测到多种能够影响本车实际行驶的障碍物，例如行人、外部车辆、放置在施工路段中的提示牌以及交通防护设施等。然而，部分类别的障碍物虽然会影响本车实际行驶，但其本身的位置是可以动态变化的，因此生成行驶路径时可以不考虑，例如能够在道路上进行动态移动的行人或外 部车辆等。基于此，在本实施例中，可将既非行人也非车辆的障碍物作为指定类别的障碍物，如放置在道路上的施工提示牌以及交通防护设施等。进一步地，可仅根据各指定类别的障碍物的位置信息、形状信息和尺寸信息，确定各指定类别的障碍物在检测到的施工路段中的设障区域，而不考虑指定类别外的障碍物。
其中，设障区域可以为指定类别的障碍物在检测到的施工路段上所占据的区域，可以理解的是，若车辆车身越过某个指定类别的障碍物的设障区域的边界，则会与该障碍物发生碰撞，因此可通行区域应避开该障碍物的设障区域。
具体地，可将指定类别的障碍物与施工路段的路面的接触区域确定为设障区域。优选地，也可将指定类别的障碍物在施工路段的路面上的投影对应的区域确定为该障碍物的设障区域。需要说明的是，相较于上述根据接触区域确定设障区域，基于投影确定设障区域能够降低无人驾驶车辆在行驶过程中与指定类别的障碍物发生碰撞的几率。例如，施工路段上立有一个“T”形的指定类别的障碍物，该障碍物与该施工路段的接触区域为由“|”形部分的底部确定的区域，显然未考虑到该障碍物的“一”形部分对无人驾驶车辆的阻碍，因此车辆仍有可能与该障碍物发生碰撞。然而，该障碍物在施工路段的路面上的投影对应的区域则考虑了该障碍物的外缘对无人驾驶车辆的阻碍，因此能够降低无人驾驶车辆在行驶过程中与指定类别的障碍物发生碰撞的几率。
在一个实施例中，所述基于所述设障区域确定检测到的施工路段的当前不可通行区域的步骤，可以包括：
将所述设障区域的边缘向四周延伸预设距离值后获得的区域，确定为检测到的施工路段的当前不可通行区域。
在本实施例中，不可通行区域需能够完全覆盖该设障区域，并且，基于本车自身的宽度考虑，其边界线与设障区域相应的边界线之间可留一定的间距，即预设距离值对应的间距。
具体地，不论设障区域的形状是否规则，其对应的不可通行区域均可为形状与设障区域相同、能够完全覆盖该设障区域、且其边线与该设障区域的相应边线之间的距离为预设距离值的区域。以一个具体的实例进行说明，设障区域 为一个边长为0.5米的正方形，预设距离值为1米，则其对应的不可通行区域为，将该正方形的边缘向四周延伸1米后，获得的能够完全覆盖该正方形、其四条边的边长均为2.5米、且其四条边与该正方形的四条边分别对应平行的正方形。
在一个实施例中，所述根据所述当前可通行区域确定目标行驶路径的终止路点的步骤，可以包括：
当搜索到预定条件的道路横截面时，根据该预定条件的道路横截面所覆盖的车道中线路点确定目标行驶路径的终止路点，所述预定条件的道路横截面为：自该预定条件的道路横截面开始、检测到的施工路段覆盖的所有车道的车道中线路点均位于所述当前可通行区域内的道路横截面；
当未搜索到所述预定条件的道路横截面、但搜索到预定条件的路点时，根据所述预定条件的路点确定所述终止路点，所述预定条件的路点为位于所述检测范围的最远端、且位于所述当前可通行区域内的车道中线路点；
当未搜索到所述预定条件的道路横截面、且未搜索到所述预定条件的路点时，搜索所述检测范围的最远端的道路横截面上的可通行豁口，根据所述可通行豁口确定所述终止路点。
一方面，预定条件的道路横截面所在的位置为整条施工路段的完结位置，即整条施工路段到这个位置打止。在搜索到预定条件的道路横截面的情况下，则可在该预定条件的道路横截面所覆盖的车道中线路点中选取一个路点作为目标行驶路径的终止路点，并且可基于本车的行驶方向选取，例如预定条件的道路横截面覆盖了三个车道，分别为左转车道、直行车道及右转车道，若本车需右转，则将预定条件的道路横截面所覆盖的右转车道的车道中线路点确定为终止路点。
另一方面，若未在检测范围内搜索到预定条件的道路横截面，则说明检测整条施工路段的长度可能较长，当前检测范围内覆盖的可能仅为整条施工路段的一部分。在此情况下，可根据位于当前检测范围的最远端、且位于当前可通行区域内的车道中线路点(预定条件的路点)确定终止路点，可以理解的是，当前检测范围的最远端对应的位置为当前检测范围内覆盖的这一部分施工路段的完结位置。
又一方面，若未搜索到预定条件的路点，则说明检测到的施工路段不可通行，则进一步搜索位于检测范围的最远端的道路横截面上是否存在可通行豁口，例如掉头豁口。当搜索到可通行豁口时，则根据可通行豁口确定目标行驶路径的终止路点，具体地，可将搜索到的可通行豁口的中点作为目标行驶路径的终止路点。
在一个实施例中，所述根据所述起始路点、所述途径路点以及所述终止路点生成所述目标行驶路径的步骤，可以包括：
根据所述起始路点、所述途径路点以及所述终止路点生成初始行驶路径；
对所述初始行驶路径进行滤波，获得所述目标行驶路径。
需要说明的是，可根据起始路点、途径路点、终止路点以及预设的路径搜索算法生成目标行驶路径，经由预设搜索算法生成的目标行驶路径可能较为粗糙，因此可对其进行滤波处理，以使目标行驶路径平滑，从而提高目标行驶路径的精确度。例如，可根据A星算法生成的目标行驶路径，然而，经由A星算法得到的初始行驶路径一般不是十分平滑，对A星算法得到的初始行驶路径进行贝塞尔曲线滤波后，则可以获得更为平滑的行驶路径。
在一个实施例中，预设的路径搜索算法包括A星算法，且所述A星算法中计算当前路点的总代价值的公式为：
f(t)＝g(t)+h(t)+k*e(t)
其中，f(t)为所述当前路点的总代价值；g(t)为所述起始路点到所述当前路点的累计距离代价；h(t)是所述当前路点到所述终止路点的预估距离代价；e(t)为距离所述当前路点最近的目标障碍物到所述当前路点的距离代价；k是预设的代价常数。
其中，预估距离代价可以为曼哈顿距离代价，即当前路点与终止路点的经度距离差与纬度距离差的绝对值之和，采用曼哈顿距离进行预估，可以简便快捷地进行预估。另外，预估距离代价还可以为欧式距离代价或对角线估价等，此处不做具体限定。
其中，e(t)是当前路点处的目标障碍物距离代价，其考量的是与当前路点距离最近的指定类别的障碍物与当前路点的距离。该距离越大，e(t)越小，且可以 预设距离阈值，使得距离大于该距离阈值时，e(t)为0。在一个具体示例中，基于实际需求，距离阈值可设置为1.8米。另外，k是预设的代价常数，可基于施工路段的实测效果进行标定。
此外，A星算法是基于最短路径原则的路径搜索算法。因此，本实施例能够获得从起始路点到终止路点的最短路径。而且，本实施例对传统A星算法的代价函数做出改进，加入了路径与指定类别的障碍物的间距的考量，因此，基于本实施例生成的目标行驶路径，能够使本车在通行过程中与指定类别的障碍物保持适当的安全间距。
需要说明的是，实际施工路段的长度不一，对于长度较短的施工路段，环境感知系统的检测范围可一次覆盖整条施工路段，相应地，将本发明提供的任一实施例的各步骤执行一次，生成一条目标行驶路径，即可引导本车通过整条施工路段。然而，对于长度较长的施工路段，环境感知系统的检测范围无法一次性覆盖整条施工路段，则需要针对每次检测范围覆盖施工路段分别生成对应的目标行驶路径，生成的多条目标行驶路径首尾相接，车辆依次根据这多条目标行驶路径行驶才可以通过整条施工路段。相应地，针对这种情况，则需要多次执行本发明提供的任一实施例的各步骤，即，每执行一次则可生成一条目标行驶路径。下面以一个具体实例进行说明，若本车上设置的环境感知系统的检测范围为100米，即一次仅能覆盖100米，现需要针对一条长度为800米的施工路段生成行驶路径，该施工路段的起点为A，终点为E，且为方便说明，假设3个中间点B、C和D，相邻两个点之间间隔100米，若本车的当前位置刚好在A点，则需要先生成一条从A到B的第一目标行驶路径，当车辆按照第一目标行驶路径行驶到B处时，再生成一条从B到C的第二目标行驶路径，当车辆按照第二目标行驶路径行驶到C处时，再生成一条从C到D的第三目标行驶路径，当车辆按照第三目标行驶路径行驶到D处时，最后再生成一条从D到E的第四目标行驶路径，车辆依次按照这四条目标行驶路径行驶，则可以通过整条施工路段。
图2示出了一个实施例中施工路段无人驾驶车辆的路径生成装置的结构示意图。参照图2，该装置200具体可以包括如下模块：
特征信息获取模块202，用于在检测到施工路段时，获取检测到的障碍物信息，所述障碍物信息包括障碍物的类别和特征信息，所述特征信息包括位置信息；
通行区域确定模块204，用于根据所述障碍物的类别和位置信息，确定所述施工路段的当前可通行区域，并确定所述当前可通行区域中包含的各路点；
终止路点确定模块206，用于根据所述当前可通行区域确定目标行驶路径的终止路点；
途径路点确定模块208，用于将车辆当前所处位置作为起始路点，根据所述起始路点、所述终止路点在所述当前可通行区域包含的各路点中进行路径搜索，确定所述目标行驶路径在所述施工路段中的途径路点；以及，
行驶路径生成模块210，用于根据所述起始路点、所述途径路点以及所述终止路点生成所述目标行驶路径。
上述施工路段无人驾驶车辆的路径生成装置，在检测到施工路段时，根据检测范围内检测到的障碍物的类别和位置信息确定该施工路段的当前可通行区域，可见，施工路段的可通行区域是根据检测到的该施工路段的实时障碍物信息确定的，能够适应施工路段的实时路况，因此，基于该可通行区域生成的行驶路径同样能够适应施工路段的实时路况。
在一个实施例中，所述特征信息还包括形状信息和尺寸信息；
此时，所述通行区域确定模块204可以包括：
设障区域确定单元，用于根据指定类别的障碍物的位置信息、形状信息和尺寸信息，确定各指定类别的障碍物在检测到的施工路段中的设障区域；
不可通行区域确定单元，用于基于所述设障区域确定检测到的施工路段的当前不可通行区域；
可通行区域确定单元，用于将检测到的施工路段中除所述当前不可通行区域外的区域确定为所述当前可通行区域。
在一个实施例中，所述不可通行区域确定单元具体可以用于：将所述设障区域的边缘向四周延伸预设距离值后获得的区域，确定为检测到的施工路段的当前不可通行区域。
在一个实施例中，所述终止路点确定模块206可以包括：
第一终止路点确定单元，用于当搜索到预定条件的道路横截面时，根据该预定条件的道路横截面所覆盖的车道中线路点确定目标行驶路径的终止路点，所述预定条件的道路横截面为：自该预定条件的道路横截面开始、检测到的施工路段覆盖的所有车道的车道中线路点均位于所述当前可通行区域内的道路横截面；
第二终止路点确定单元，用于当未搜索到所述预定条件的道路横截面、但搜索到预定条件的路点时，根据所述预定条件的路点确定所述终止路点，所述预定条件的路点为位于所述检测范围的最远端、且位于所述当前可通行区域内的车道中线路点；以及，
第三终止路点确定单元，用于当未搜索到所述预定条件的道路横截面、且未搜索到所述预定条件的路点时，搜索所述检测范围的最远端的道路横截面上的可通行豁口，根据所述可通行豁口确定所述终止路点。
在一个实施例中，所述行驶路径生成模块210可以包括：
初始路径生成单元，用于根据所述起始路点、所述途径路点以及所述终止路点生成初始行驶路径；以及，
目标路径生成单元，用于对所述初始行驶路径进行滤波，获得所述目标行驶路径。
在一个实施例中，采用A星算法进行路径搜索，所述路径搜索过程中，采用下述公式计算当前路点的总代价值：
f(t)＝g(t)+h(t)+k*e(t)
其中，f(t)为所述当前路点的总代价值；g(t)为所述起始路点到所述当前路点的累计距离代价；h(t)是所述当前路点到所述终止路点的预估距离代价；e(t)为距离所述当前路点最近的指定类别的障碍物到所述当前路点的距离代价；k为代价常数。
本实施例的施工路段无人驾驶车辆的路径生成装置中的其他技术特征，可以与上述施工路段无人驾驶车辆的路径生成方法实施例中的相同。
图3示出了一个实施例中计算机设备的内部结构图。该计算机设备具体可以是上文所述的控制终端。如图3所示，该计算机设备可包括通过系统总线连接的处理器、存储器、网络接口、输入装置和显示屏。其中，存储器包括非易失性存储介质和内存储器。该计算机设备的非易失性存储介质存储有操作系统，还可存储有计算机程序，该计算机程序被处理器执行时，可使得处理器实现上述施工路段无人驾驶车辆的路径生成方法。该内存储器中也可储存有计算机程序，该计算机程序被处理器执行时，可使得处理器执行上述施工路段无人驾驶车辆的路径生成方法。计算机设备的显示屏可以是液晶显示屏或者电子墨水显示屏，计算机设备的输入装置可以是显示屏上覆盖的触摸层，也可以是计算机设备外壳上设置的按键、轨迹球或触控板，还可以是外接的键盘、触控板或鼠标等。
本领域技术人员可以理解，图3中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一个实施例中，本发明提供的施工路段无人驾驶车辆的路径生成装置可以实现为一种计算机程序的形式，计算机程序可在如图3所示的计算机设备上运行。计算机设备的存储器中可存储组成该施工路段无人驾驶车辆的路径生成装置的各个程序模块，比如，图2所示的特征信息获取模块202、通行区域确定模块204、终止路点确定模块206、途径路点确定模块208和行驶路径生成模块210。各个程序模块构成的计算机程序使得处理器执行本说明书中描述的本申请各实施例的施工路段无人驾驶车辆的路径生成方法中的步骤。
例如，图3所示的计算机设备可以通过如图2所示的施工路段无人驾驶车辆的路径生成装置中的特征信息获取模块202执行图2中的步骤S102、可通过通行区域确定模块204执行图2中的步骤S104、以及可通过终止路点确定模块206执行图2中的步骤S106等等。
为此，一个实施例中还提供一种计算机设备，包括存储器和处理器，所述存储器中存储有计算机可读指令，所述计算机可读指令被所述处理器执行时， 使得所述处理器执行本申请提供的任一实施例中的施工路段无人驾驶车辆的路径生成方法的步骤。
上述计算机设备，在检测到施工路段时，根据检测范围内检测到的障碍物的类别和位置信息确定该施工路段的当前可通行区域，可见，施工路段的可通行区域是根据检测到的该施工路段的实时障碍物信息确定的，能够适应施工路段的实时路况，因此，基于该可通行区域生成的行驶路径同样能够适应施工路段的实时路况。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一非易失性计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
为此，一个实施例中还提供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有计算机可执行指令，所述计算机可执行指令被处理器执行时，使得所述处理器执行本申请提供的任一实施例中的施工路段无人驾驶车辆的路径生成方法的步骤。
上述计算机可读存储介质，在检测到施工路段时，根据检测范围内检测到的障碍物的类别和位置信息确定该施工路段的当前可通行区域，可见，施工路段的可通行区域是根据检测到的该施工路段的实时障碍物信息确定的，能够适应施工路段的实时路况，因此，基于该可通行区域生成的行驶路径同样能够适 应施工路段的实时路况。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本申请专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。

Claims (10)

  1. 一种施工路段无人驾驶车辆的路径生成方法，其特征在于，所述方法包括：
    在检测到施工路段时，获取检测到的障碍物信息，所述障碍物信息包括障碍物的类别和特征信息，所述特征信息包括位置信息；
    根据所述障碍物的类别和位置信息，确定所述施工路段的当前可通行区域，并确定所述当前可通行区域中包含的各路点；
    根据所述当前可通行区域确定目标行驶路径的终止路点；
    将车辆当前所处位置作为起始路点，根据所述起始路点、所述终止路点在所述当前可通行区域包含的各路点中进行路径搜索，确定所述目标行驶路径在所述施工路段中的途径路点；
    根据所述起始路点、所述途径路点以及所述终止路点生成所述目标行驶路径。
  2. 如权利要求1所述的施工路段无人驾驶车辆的路径生成方法，其特征在于，所述特征信息还包括形状信息和尺寸信息；
    所述根据所述障碍物的类别和位置信息，确定所述施工路段的当前可通行区域的方式，包括：
    根据指定类别的障碍物的位置信息、形状信息和尺寸信息，确定各指定类别的障碍物在检测到的施工路段中的设障区域；
    基于所述设障区域确定检测到的施工路段的当前不可通行区域；
    将检测到的施工路段中除所述当前不可通行区域外的区域确定为所述当前可通行区域。
  3. 如权利要求2所述的施工路段无人驾驶车辆的路径生成方法，其特征在于，所述基于所述设障区域确定检测到的施工路段的当前不可通行区域的步骤，包括：
    将所述设障区域的边缘向四周延伸预设距离值后获得的区域，确定为检测到的施工路段的当前不可通行区域。
  4. 如权利要求1所述的施工路段无人驾驶车辆的路径生成方法，其特征在 于，所述根据所述当前可通行区域确定目标行驶路径的终止路点的步骤，包括：
    当搜索到预定条件的道路横截面时，根据该预定条件的道路横截面所覆盖的车道中线路点确定目标行驶路径的终止路点，所述预定条件的道路横截面为：自该预定条件的道路横截面开始、检测到的施工路段覆盖的所有车道的车道中线路点均位于所述当前可通行区域内的道路横截面；
    当未搜索到所述预定条件的道路横截面、但搜索到预定条件的路点时，根据所述预定条件的路点确定所述终止路点，所述预定条件的路点为位于所述检测范围的最远端、且位于所述当前可通行区域内的车道中线路点；
    当未搜索到所述预定条件的道路横截面、且未搜索到所述预定条件的路点时，搜索所述检测范围的最远端的道路横截面上的可通行豁口，根据所述可通行豁口确定所述终止路点。
  5. 如权利要求1所述的施工路段无人驾驶车辆的路径生成方法，其特征在于，所述根据所述起始路点、所述途径路点以及所述终止路点生成所述目标行驶路径的步骤，包括：
    根据所述起始路点、所述途径路点以及所述终止路点生成初始行驶路径；
    对所述初始行驶路径进行滤波，获得所述目标行驶路径。
  6. 如权利要求1至5任一项所述的施工路段无人驾驶车辆的路径生成方法，其特征在于，采用A星算法进行路径搜索，所述路径搜索过程中，采用下述公式计算当前路点的总代价值：
    f(t)＝g(t)+h(t)+k*e(t)
    其中，f(t)为所述当前路点的总代价值；g(t)为所述起始路点到所述当前路点的累计距离代价；h(t)是所述当前路点到所述终止路点的预估距离代价；e(t)为距离所述当前路点最近的指定类别的障碍物到所述当前路点的距离代价；k为代价常数。
  7. 一种施工路段无人驾驶车辆的路径生成装置，其特征在于，所述装置包括：
    特征信息获取模块，用于在检测到施工路段时，获取检测到的障碍物信息，所述障碍物信息包括障碍物的类别和特征信息，所述特征信息包括位置信息；
    通行区域确定模块，用于根据障碍物的类别和特征信息，确定所述施工路段的当前可通行区域，并确定所述当前可通行区域中包含的各路点；
    终止路点确定模块，用于根据所述当前可通行区域确定目标行驶路径的终止路点；
    途径路点确定模块，用于将车辆当前所处位置作为起始路点，根据所述起始路点、所述终止路点在所述当前可通行区域包含的各路点中进行路径搜索，确定所述目标行驶路径在检测到的施工路段中的途径路点；以及，
    行驶路径生成模块，用于根据所述起始路点、所述途径路点以及所述终止路点生成所述目标行驶路径。
  8. 如权利要求7所述的施工路段无人驾驶车辆的路径生成装置，其特征在于，所述特征信息还包括形状信息和尺寸信息；
    所述通行区域确定模块包括：
    设障区域确定单元，用于根据指定类别的障碍物的位置信息、形状信息和尺寸信息，确定各指定类别的障碍物在检测到的施工路段中的设障区域；
    不可通行区域确定单元，用于基于所述设障区域确定检测到的施工路段的当前不可通行区域；以及，
    可通行区域确定单元，用于将检测到的施工路段中除所述当前不可通行区域外的区域确定为所述当前可通行区域。
  9. 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有计算机可执行指令，所述计算机可执行指令被处理器执行时，使得所述处理器执行如权利要求1至6任一项所述方法的步骤。
  10. 一种计算机设备，其特征在于，包括存储器和处理器，所述存储器中存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述处理器执行如权利要求1至6任一项所述方法的步骤。
PCT/CN2018/111087 2017-10-25 2018-10-19 施工路段无人驾驶车辆的路径生成方法及装置 WO2019080782A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/489,365 US11221224B2 (en) 2017-10-25 2018-10-19 Method and device for generating path of unmanned vehicle on construction section

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711010197.7 2017-10-25
CN201711010197.7A CN107843267B (zh) 2017-10-25 2017-10-25 施工路段无人驾驶车辆的路径生成方法及装置

Publications (1)

Publication Number Publication Date
WO2019080782A1 true WO2019080782A1 (zh) 2019-05-02

Family

ID=61663151

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/111087 WO2019080782A1 (zh) 2017-10-25 2018-10-19 施工路段无人驾驶车辆的路径生成方法及装置

Country Status (3)

Country Link
US (1) US11221224B2 (zh)
CN (1) CN107843267B (zh)
WO (1) WO2019080782A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113790725A (zh) * 2020-09-22 2021-12-14 北京京东乾石科技有限公司 路径规划方法、路径规划装置、存储介质与可移动设备
US11338855B2 (en) * 2018-12-26 2022-05-24 Baidu Usa Llc Optimal planner switch method for three point turn of autonomous driving vehicles

Families Citing this family (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107843267B (zh) 2017-10-25 2020-04-17 广州汽车集团股份有限公司 施工路段无人驾驶车辆的路径生成方法及装置
CN108871361A (zh) * 2018-06-11 2018-11-23 江苏盛海智能科技有限公司 一种规划循迹路径的方法及终端
CN109062948B (zh) * 2018-06-22 2020-11-13 广州杰赛科技股份有限公司 目标点确定、目标路径确定方法和系统
CN109213153B (zh) * 2018-08-08 2022-01-07 东风汽车有限公司 一种车辆自动驾驶方法及电子设备
CN110377021B (zh) * 2018-09-29 2022-09-06 北京京东尚科信息技术有限公司 设备控制方法、装置、系统、计算机可读存储介质
CN111238500B (zh) * 2018-11-29 2022-07-26 沈阳美行科技股份有限公司 道路地图区域的道路线段的地图生成方法、装置及系统
CN111238505B (zh) * 2018-11-29 2023-11-24 沈阳美行科技股份有限公司 一种道路地图的道路线段描画方法、装置及相关系统
CN109784526B (zh) 2018-12-05 2023-02-28 阿波罗智能技术(北京)有限公司 通行路径的规划方法、装置、设备及可读存储介质
CN109739219B (zh) * 2018-12-05 2022-02-11 阿波罗智能技术(北京)有限公司 通行路径的规划方法、装置、设备及可读存储介质
CN109634282B (zh) * 2018-12-25 2021-05-28 奇瑞汽车股份有限公司 自动驾驶车辆、方法和装置
CN109827584B (zh) * 2019-01-15 2021-07-09 北京百度网讯科技有限公司 路径规划方法、装置、电子设备与存储介质
CN109765902B (zh) * 2019-02-22 2022-10-11 阿波罗智能技术(北京)有限公司 无人车驾驶参考线处理方法、装置及车辆
US11215985B2 (en) * 2019-03-15 2022-01-04 Nissan North America, Inc. Pathfinding assistance system for teleoperation
CN112085959B (zh) * 2019-06-13 2022-04-12 百度在线网络技术（北京）有限公司 无人车行驶控制方法及设备
CN112257889A (zh) * 2019-07-21 2021-01-22 长沙智能驾驶研究院有限公司 智慧工地中工地移动对象的路径规划方法、装置
CN112578788B (zh) * 2019-09-30 2023-05-02 北京百度网讯科技有限公司 车辆避障二次规划方法、装置、设备和可读存储介质
CN112965472A (zh) * 2019-11-27 2021-06-15 深圳市大富科技股份有限公司 一种无人车及其行进辅助方法、装置、系统
CN111189453A (zh) * 2020-01-07 2020-05-22 深圳南方德尔汽车电子有限公司 基于Bezier全局路径规划方法、装置、计算机设备及存储介质
CN111397611B (zh) * 2020-03-05 2022-07-05 北京百度网讯科技有限公司 路径规划方法、装置以及电子设备
CN111426330B (zh) * 2020-03-24 2022-03-15 江苏徐工工程机械研究院有限公司 路径生成方法和设备、无人化运输系统和存储介质
US11945463B2 (en) 2020-03-26 2024-04-02 Baidu Usa Llc Navigation route planning method for autonomous vehicles
CN113532448A (zh) * 2020-04-13 2021-10-22 广州汽车集团股份有限公司 一种自动驾驶车辆的导航方法及其系统、驾驶控制设备
CN111538335A (zh) * 2020-05-15 2020-08-14 深圳国信泰富科技有限公司 一种驾驶机器人的防碰撞方法
CN113673919A (zh) * 2020-05-15 2021-11-19 北京京东乾石科技有限公司 多车协同路径确定方法及装置、电子设备和存储介质
CN113682299A (zh) * 2020-05-19 2021-11-23 广州汽车集团股份有限公司 一种车辆前向碰撞预警方法及装置
CN113741412B (zh) * 2020-05-29 2023-09-01 杭州海康威视数字技术股份有限公司 自动驾驶设备的控制方法、装置及存储介质
CN111709355B (zh) * 2020-06-12 2023-08-29 阿波罗智联(北京)科技有限公司 识别目标区域的方法、装置、电子设备和路侧设备
US11987261B2 (en) 2020-09-15 2024-05-21 Tusimple, Inc. Detecting a road structure change by a lead autonomous vehicle (AV) and updating routing plans for the lead AV and following AVs
CN112182710A (zh) * 2020-09-28 2021-01-05 杭州品茗安控信息技术股份有限公司 一种施工道路布置方法、装置、设备及可读存储介质
CN112633570A (zh) * 2020-12-17 2021-04-09 广州小马智行科技有限公司 车辆的行驶路线的确定方法、装置、处理器与车辆系统
CN112733923A (zh) * 2021-01-04 2021-04-30 上海高仙自动化科技发展有限公司 一种确定禁行区域的系统及机器人
CN112948520B (zh) * 2021-03-19 2023-02-17 杭州海康威视系统技术有限公司 一种绕行路径的确定方法、装置及存储介质
CN113112622A (zh) * 2021-04-15 2021-07-13 北京世纪高通科技有限公司 一种计费方法、装置和服务器
CN113282088A (zh) * 2021-05-21 2021-08-20 潍柴动力股份有限公司 工程车的无人驾驶方法、装置、设备、存储介质及工程车
CN113792375B (zh) * 2021-08-06 2022-09-09 清华大学 基于云支持的预测性巡航控制车速解析方法、系统及装置
CN113781786B (zh) * 2021-11-11 2022-02-22 中移(上海)信息通信科技有限公司 一种不可通行区域确认方法、装置、设备及可读存储介质
CN114511044B (zh) * 2022-04-18 2022-06-28 新石器慧通（北京）科技有限公司 无人车通行控制方法及装置
CN114911239A (zh) * 2022-05-27 2022-08-16 上海伯镭智能科技有限公司 一种无人驾驶矿车的异常识别方法及系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140063232A1 (en) * 2012-09-05 2014-03-06 Google Inc. Construction Zone Sign Detection
US9056395B1 (en) * 2012-09-05 2015-06-16 Google Inc. Construction zone sign detection using light detection and ranging
CN104809901A (zh) * 2014-01-28 2015-07-29 通用汽车环球科技运作有限责任公司 使用街道级图像增强车辆的自动驾驶模式的方法
CN106323309A (zh) * 2015-06-30 2017-01-11 Lg电子株式会社 车辆驾驶辅助装置、车辆用显示装置以及车辆
WO2017029775A1 (en) * 2015-08-19 2017-02-23 Sony Corporation System and method for determing navigation information for an autonomous vehicle
US20170242436A1 (en) * 2017-03-17 2017-08-24 GM Global Technology Operations LLC Road construction detection systems and methods
US20170300059A1 (en) * 2017-05-03 2017-10-19 GM Global Technology Operations LLC Methods and systems for lidar point cloud anomalies
CN107843267A (zh) * 2017-10-25 2018-03-27 广州汽车集团股份有限公司 施工路段无人驾驶车辆的路径生成方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100023251A1 (en) * 2008-07-25 2010-01-28 Gale William N Cost based open area maps
US8099237B2 (en) * 2008-07-25 2012-01-17 Navteq North America, Llc Open area maps
US9141107B2 (en) * 2013-04-10 2015-09-22 Google Inc. Mapping active and inactive construction zones for autonomous driving

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140063232A1 (en) * 2012-09-05 2014-03-06 Google Inc. Construction Zone Sign Detection
US9056395B1 (en) * 2012-09-05 2015-06-16 Google Inc. Construction zone sign detection using light detection and ranging
CN104809901A (zh) * 2014-01-28 2015-07-29 通用汽车环球科技运作有限责任公司 使用街道级图像增强车辆的自动驾驶模式的方法
CN106323309A (zh) * 2015-06-30 2017-01-11 Lg电子株式会社 车辆驾驶辅助装置、车辆用显示装置以及车辆
WO2017029775A1 (en) * 2015-08-19 2017-02-23 Sony Corporation System and method for determing navigation information for an autonomous vehicle
US20170242436A1 (en) * 2017-03-17 2017-08-24 GM Global Technology Operations LLC Road construction detection systems and methods
US20170300059A1 (en) * 2017-05-03 2017-10-19 GM Global Technology Operations LLC Methods and systems for lidar point cloud anomalies
CN107843267A (zh) * 2017-10-25 2018-03-27 广州汽车集团股份有限公司 施工路段无人驾驶车辆的路径生成方法及装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11338855B2 (en) * 2018-12-26 2022-05-24 Baidu Usa Llc Optimal planner switch method for three point turn of autonomous driving vehicles
CN113790725A (zh) * 2020-09-22 2021-12-14 北京京东乾石科技有限公司 路径规划方法、路径规划装置、存储介质与可移动设备
CN113790725B (zh) * 2020-09-22 2024-03-01 北京京东乾石科技有限公司 路径规划方法、路径规划装置、存储介质与可移动设备

Also Published As

Publication number Publication date
CN107843267B (zh) 2020-04-17
CN107843267A (zh) 2018-03-27
US20200249037A1 (en) 2020-08-06
US11221224B2 (en) 2022-01-11

Similar Documents

Publication Publication Date Title
WO2019080782A1 (zh) 施工路段无人驾驶车辆的路径生成方法及装置
US10197404B2 (en) Path curve confidence factors
EP3673407B1 (en) Automatic occlusion detection in road network data
CN110032181B (zh) 语义地图中障碍物定位方法、装置、计算机设备和存储介质
Hata et al. Feature detection for vehicle localization in urban environments using a multilayer LIDAR
Hata et al. Road marking detection using LIDAR reflective intensity data and its application to vehicle localization
US9140792B2 (en) System and method for sensor based environmental model construction
US20170343374A1 (en) Vehicle navigation method and apparatus
US10928819B2 (en) Method and apparatus for comparing relevant information between sensor measurements
US11170251B2 (en) Method and apparatus for predicting feature space decay using variational auto-encoder networks
EP3762856A1 (en) Automatic identification of roadside objects for localization
CN106855415A (zh) 地图匹配方法和系统
US10210403B2 (en) Method and apparatus for pixel based lane prediction
CN110119138A (zh) 用于自动驾驶车辆的自定位方法、系统和机器可读介质
EP4184119A1 (en) Travelable region determination method, intelligent driving system and intelligent vehicle
US10922558B2 (en) Method and apparatus for localization using search space pruning
CN113551679A (zh) 一种示教过程中的地图信息构建方法、构建装置
KR20200002257A (ko) 꼭지점 검출 기반의 도로 표지판 검출 방법 및 장치
US20210270629A1 (en) Method and apparatus for selecting a path to a destination
US11790667B2 (en) Method and apparatus for localization using search space pruning
JP7344182B2 (ja) 情報処理装置
JPWO2011158482A1 (ja) 事故削減施策シミュレーション装置および事故削減施策シミュレーション方法
KR20160123203A (ko) 도로표지판 검출 기반 주행 차로 추정 방법 및 장치
US20230298363A1 (en) System and method for determining lane width data
US11796323B2 (en) System and method for generating feature line data for a map

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: 18870620

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: 18870620

Country of ref document: EP

Kind code of ref document: A1