WO2019080781A1 - 无人驾驶车辆的路径规划方法、装置及计算机设备 - Google Patents

无人驾驶车辆的路径规划方法、装置及计算机设备

Info

Publication number
WO2019080781A1
WO2019080781A1 PCT/CN2018/111084 CN2018111084W WO2019080781A1 WO 2019080781 A1 WO2019080781 A1 WO 2019080781A1 CN 2018111084 W CN2018111084 W CN 2018111084W WO 2019080781 A1 WO2019080781 A1 WO 2019080781A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
endpoint
path
lane
road segment
Prior art date
Application number
PCT/CN2018/111084
Other languages
English (en)
French (fr)
Inventor
甘新华
查鸿山
黄少堂
徐伟
裴锋
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 US16/488,948 priority Critical patent/US20210080267A1/en
Publication of WO2019080781A1 publication Critical patent/WO2019080781A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/06—Road conditions
    • B60W40/072—Curvature of the road
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3602—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
    • 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
    • G01C21/3605—Destination input or retrieval
    • G01C21/3617—Destination input or retrieval using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/806—Relative heading
    • 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
    • B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
    • B60W2555/60—Traffic rules, e.g. speed limits or right of way
    • 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/45—External transmission of data to or from the vehicle
    • B60W2556/50—External transmission of data to or from the vehicle of positioning data, e.g. GPS [Global Positioning System] data

Definitions

  • the present invention relates to the field of driverless technology, and in particular, to a path planning method and apparatus for an unmanned vehicle, a computer readable storage medium, and a computer device.
  • Path planning is one of the key technologies for driving vehicle research.
  • planning a path it is generally a pure geometric path between the starting point and the destination (also called the target point).
  • the route planning of vehicles is generally road-level planning, that is, planning the roads to be taken from the starting point to the destination.
  • road-level planning that is, planning the roads to be taken from the starting point to the destination.
  • a path planning method for an unmanned vehicle comprising:
  • the road segment includes a road segment and a connecting channel;
  • the endpoints of the road segments include: an exit endpoint of the road segment where the starting point is located, an entry endpoint of the road segment where the destination is located, and An entry end point and an egress end point of each road segment connecting the exit end point of the road segment where the starting point is located and the entry end point of the road segment where the destination is located;
  • the final planning path is generated based on each endpoint included in the updated initial path.
  • a path planning device for an unmanned vehicle comprising:
  • a starting and ending section obtaining module configured to acquire a road section where the starting point of the path is located, and a road section where the destination is located;
  • the road section includes a road section and a connecting channel;
  • an initial path generating module configured to perform a path search according to the connectivity relationship between the endpoints of the road segments, and generate an initial path;
  • the endpoints of the road segments include: an exit endpoint of the road segment where the starting point is located, and a road segment where the destination is located An entry endpoint and an exit endpoint and an exit endpoint of each segment of the exit endpoint for connecting the segment where the origin is located and the entry endpoint of the segment where the destination is located;
  • An egress endpoint update module configured to update an egress end point of a previous road segment of each connected channel in a passable direction according to an ingress end of each connected channel included in the initial path; wherein an ingress endpoint of the connected channel is the An exit end point of a lane of a predetermined condition included in a previous road section of the connecting passage in a traffic direction, the lane of the predetermined condition being a lane whose attribute category matches an attribute category of the connected channel;
  • the final path generation module is configured to generate a final planned path according to each endpoint included in the updated initial path.
  • a computer readable storage medium having stored thereon computer executable instructions that, when executed by a processor, cause the processor to perform an unmanned vehicle as described above The steps of the path planning method.
  • 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 execute an unmanned vehicle as described above The steps of the path planning method.
  • the exit end point of the previous road segment of each connecting channel of the final planning path is the attribute category of the road segment and the connection
  • the attribute category of the channel matches the exit endpoint of the lane.
  • FIG. 1 is a schematic diagram showing a hierarchical structure of a high-precision map in an embodiment
  • FIG. 2 is a schematic flow chart of a path planning method for an unmanned vehicle in a construction section in an embodiment
  • Figure 3 is a schematic diagram of a road network
  • FIG. 4 is a schematic structural view of a path planning device for an unmanned vehicle in a construction section in an embodiment
  • Figure 5 is a block diagram showing the structure of a computer device in an embodiment.
  • the path planning method of the unmanned vehicle may be applied to a control terminal, and the control terminal may be a mobile terminal or an in-vehicle terminal on an unmanned vehicle.
  • the mobile terminal may specifically be a mobile phone, a tablet computer or a notebook computer.
  • the map data is collected by a dedicated map data collection vehicle in an actual road section, and a series of road points are surveyed in each road section to determine geometric parameters of the road section.
  • the road section may include a road section and a connecting passage, wherein the road section may include a plurality of lanes, and the connecting lane refers to a section between the two road sections and connecting the two road sections. Based on traffic rules, lanes included in both the passage and the road segment have corresponding attribute categories.
  • the lanes of the road segment may include a straight lane, a left lane, a right lane, a U-turn lane, an emergency lane, and the like. It can be understood that in a part of the road section, one lane can have multiple attribute categories, for example, a left turn straight lane, that is, at the exit end of the lane, the vehicle can either go straight at the intersection or turn left at the intersection.
  • the connecting channel may include a cross-track straight-line connecting channel, a straight-line connecting channel at the intersection, a left-turning connecting channel at the intersection, a right-turning connecting channel at the intersection, and a U-turn connecting channel at the intersection.
  • the high-precision map is also involved in the definition of the map data format.
  • the high-precision map data may include a map layer, a link layer, a link layer, a lane layer, and a waypoint layer.
  • the map layer may include the total number of road segments; the road segment layer may include: a serial number of each road segment, a number of lanes included in each road segment, and a number of connected channels at the exit of each road segment; the connecting channel layer may include: a serial number of each connected channel, The serial number of the lane in the road section at the entrance end of each lane, the serial number of the road section at the exit end of each lane, the serial number of the lane in the road section at the exit end of each lane, and each The type of the channel and the number of waypoints included in each channel; the lane layer may include: the number of each lane, the width of each lane, the category of each lane, and the number of waypoints included in each lane; the waypoint layer may include: each waypoint Serial number, longitude, and latitude.
  • FIG. 2 is a flow chart showing a path planning method of an unmanned vehicle in one embodiment.
  • the method is applied to the control terminal described above as an example.
  • the method specifically includes the following steps S202 to S208.
  • Step S202 Acquire a road segment where the starting point of the path is located, and a road segment where the destination is located; the road segment includes a road segment and a connecting channel.
  • the road section generally refers to a traffic line between two adjacent nodes on the traffic network, and the two nodes are respectively an entrance end point and an exit end point of the road section.
  • the road section may include a road section and a connecting passage between the two road sections and connecting the two road sections.
  • the starting point and destination of the path need to be obtained.
  • the starting point and destination of the path can be directly input to the control terminal by the user according to actual needs.
  • the starting point of the path may be acquired based on the current location of the vehicle and the current heading, and the destination of the path may be acquired based on the target position input by the user.
  • the starting point and the road segment where the destination is located can be determined based on the high-precision map. Among them, the starting point may be in the road section, or in the connecting channel, the destination is similar, and will not be described here.
  • Step S204 Perform a path search according to the connectivity relationship between the endpoints of the road segments, and generate an initial path.
  • the endpoints of the road segments include: an exit endpoint of the road segment where the starting point is located, and an entry endpoint of the road segment where the destination is located. And an entry end point and an egress end point of each road segment for connecting the exit end point of the road segment where the starting point is located and the entry end point of the road segment where the destination is located.
  • the high-precision map pre-stores the connectivity information between the endpoints of the link itself and the connectivity information between the endpoints of each segment, and establishes connectivity between the endpoints of the segment itself and each based on the corresponding connectivity information. Connectivity between the endpoints of the road segment. For example, in the high-precision map, the entrance end point A of the road segment AB and its exit end point B are naturally connected, and the connectivity between the entry endpoint A and the exit endpoint B can be established based on the connectivity information.
  • the exit end point B of the road section AB is the entrance end point of the connected channel BC, and based on the connection information, the connectivity between the exit end point of the road section AB and the entrance end point of the connected channel BC can be established.
  • endpoint A is connected to endpoint B
  • endpoint B is connected to endpoint C
  • endpoint B is connected to endpoint D
  • endpoint B is connected to endpoint E
  • endpoint C is connected to endpoint F.
  • Endpoint F is connected to endpoint I
  • endpoint F is connected to endpoint J
  • endpoint I is connected to endpoint L
  • endpoint L is connected to endpoint Q
  • endpoint Q is connected to endpoint R
  • endpoint J is connected to endpoint M
  • endpoint M is connected to endpoint N.
  • Endpoint M is connected to endpoint K
  • endpoint N is connected to endpoint P
  • endpoint P is connected to endpoint Q
  • endpoint K is connected to endpoint O
  • endpoint O is connected to endpoint Q
  • endpoint O is connected to endpoint N
  • endpoint D is connected to endpoint G.
  • G is connected to the endpoint J
  • the endpoint G is connected to the endpoint K
  • the endpoint E is connected to the endpoint H
  • the endpoint H is connected to the endpoint K.
  • the accessible endpoints of the link where the start of the connected path is located and the entry endpoint of the segment where the destination is located can be searched for.
  • the road segment, thereby obtaining the entry end point and the exit end point of each passable road section, may be performed in the exit end point of the road section where the start point is located, the entry end point of the road section where the destination is located, and the entry end point and the exit end point of each passable road section.
  • Path search to generate an initial path from the start of the path to the destination.
  • the search starts from the exit end B of the link AB where the starting point of the path is located, and searches for all available road sections connecting the exit end point B and the entrance end point Q (such as the road section BC, the road section CF, and the road section FI).
  • a path search is performed in the entry and exit endpoints of the link to generate an initial path from the start of the path to the destination, such as the path BCFILQ. It should be noted that there are various ways to generate the initial path. It is only necessary to ensure that the generated initial path can be from the beginning of the path to the destination. For example, the path BEHKOQ or the path BDGJMNPQ can meet the requirements. One by one example.
  • Step S206 updating, according to the entrance end point of each connected channel included in the initial path, an exit end point of a previous road segment of each connected channel in the passable direction; wherein the entry end point of the connected channel is in the passable direction An exit end point of a lane of a predetermined condition included in a previous road section of the passage, the lane of the predetermined condition being a lane whose attribute category matches the attribute category of the connected passage.
  • the initial path may refer to a path based on road level planning, that is, the unmanned vehicle may determine a road segment that passes from the start point of the path to the destination according to the initial path, and a positional relationship between the road segments, for example, based on The path BCFILQR in Fig. 3 can be determined to pass through the connecting channel BC, the road segment CF, the connecting channel FI, the road segment IL and the connecting channel LQ, wherein the previous road segment of the connecting channel FI is CF, and the previous one of the channel LQ
  • the road section is IL.
  • the exit lane to be driven at the exit end point of each road segment included in the initial path has not been determined.
  • the exit endpoint of each connected channel in the passable direction is updated according to the entry endpoint of each connected channel included in the initial path.
  • the initial path BCFILQ shown in FIG. 3 its road segment CF, at the road segment level, the exit end point of the road segment CF is F, but refined to the lane level, if the road segment CF includes a left turn lane, a straight lane, and a right Three lanes of the lane, assuming that the exit endpoints of the three lanes are f1, f2, and f3 (not shown), respectively, and the connected channel FI is a left-linking channel, in the high-precision map, the entrance endpoint of the connected channel FI is The exit end point f1 of the left turn lane in the previous road section CF.
  • the exit endpoint of the previous road segment CF can be updated from the F endpoint in the link level to the f1 endpoint in the lane level based on the ingress endpoint of the connected channel FI.
  • the road segment can be updated based on the entry endpoint B of the connected channel BC.
  • the exit endpoint B of the AB updates the exit endpoint L of the road segment IL based on the entry endpoint L of the connected channel LQ, which is not described here.
  • Step S208 generating a final planning path according to each endpoint included in the updated initial path.
  • the exit end points of each road segment included in the initial path are the exit endpoints of the lane, and the final planned path can be generated.
  • the road segment and the connecting channel include several road points in addition to the inlet end point and the exit end point, so the generated final planned path covers the entrance end point, the exit end point and the way point of several road sections, and several sections. The entrance endpoint, exit endpoint, and waypoint for the channel.
  • the exit end point of the previous road segment of each connecting channel of the final planning path is an exit end point of the lane whose lane category matches the attribute category of the connected channel . It can be seen that when the unmanned vehicle travels according to the final generation path, the lane can be driven from the road section into the connecting passage through the lane complying with the traffic rules, thereby ensuring that the unmanned vehicle complies with the traffic rules and ensures the driving safety.
  • the manner of obtaining the road segment where the starting point of the path is located includes:
  • the preset angle may be 90°.
  • the preset distance value can be set according to the allowable error range of the GPS.
  • the manner in which the road segment where the destination is located includes:
  • the road segment where the waypoint closest to the destination is located is determined as the road segment where the destination is located.
  • the destination refers to the point where the car needs to arrive.
  • the information of the destination can be manually input to the control terminal by the user. Accordingly, after receiving the information of the destination, the control terminal searches for the endpoints included in each road segment and the endpoints included in each channel based on the high-precision map, and searches The road segment where the obtained endpoint closest to the destination is located is determined as the road segment where the destination is located.
  • the method before the step of generating a final planned path according to each endpoint included in the updated initial path, the method further includes:
  • the entry endpoint of the lane corresponding to the exit endpoint is obtained after the update, and the entry endpoint is updated to its entry endpoint.
  • the initial path B-C-F-I-L-Q shown in FIG. 3 for the road segment CF, the entrance end points of the left turn lane, the straight lane, and the right turn lane are c1, c2, and c3, respectively.
  • the exit end point of the road segment CF is the exit end point f1 of the left turn lane in the road segment CF, and the entry end point c1 of the left turn lane corresponding to the exit end point f1 is obtained, and the road segment is The exit endpoint is updated from the C endpoint at the link level to the c1 endpoint at the lane level.
  • the entry endpoint A of the road segment AB can be updated based on the entry endpoint B of the connected channel BC, and the entry endpoint I of the road segment IL is updated based on the entry endpoint L of the connected channel LQ, which is not described here.
  • the entrance lane and the exit lane of the road section are the same lane. Based on the final planning path, after driving into a road section, the unmanned vehicle can directly exit the road section through the driving lane, and there is no need to change lanes in the middle.
  • the entrance lane is the entrance of the road section a lane corresponding to the end point, where the exit lane is a lane corresponding to an exit end point of the road section;
  • step of generating a final planned path according to each endpoint included in the updated initial path including:
  • a final planned path is generated according to each of the changed endpoints and the updated endpoints included in the updated initial path.
  • the road needs to be calculated.
  • the difference between the serial number of the lane where the entrance end point of the road segment is located and the serial number of the lane where the exit endpoint is located, and the number of changed road points having the same number as the difference is determined in the road section to plan to gradually travel through different lanes in the corresponding road section.
  • the final planning path ensures that the vehicle can exit the corresponding road segment from the set exit lane.
  • the changed road point may be determined based on the curvature of the position of all the waypoints included in the road section in the road section. Specifically, the road point with a larger curvature can be avoided, and the road point with a smaller curvature can be selected as the road point to change the road point to the straight road segment. In addition, there may be ample spacing between adjacent two lane changing points.
  • the step of performing a path search according to the connectivity relationship between the endpoints of the road segments, and generating an initial path includes:
  • the path is searched according to the connection relationship between the endpoints of each road segment and the A-star algorithm, and an initial path is generated.
  • the A-star algorithm is used for path search.
  • the total value of the current endpoint is calculated by the following formula:
  • f(t) is the total cost value of the current endpoint
  • g(t) is the actual path cumulative distance cost from the starting point to the current endpoint
  • h(t) is the estimated distance cost of the current endpoint to the destination.
  • the estimated distance cost can be the Manhattan distance cost, that is, the sum of the longitude distance difference between the current endpoint and the destination and the absolute value of the latitude distance difference.
  • the Manhattan distance can be used for estimation. estimate.
  • the estimated distance cost may also be a European distance cost or a diagonal line, etc., and is not specifically limited herein.
  • the parent node of the endpoint computes the total generation value of the C endpoint, D endpoint, and E endpoint in the open table. Assume that among the three endpoints, the total value of the C endpoint is the smallest, and the total value of the endpoint of the E endpoint is the largest.
  • the parent node of the J endpoint is modified from the F endpoint to the G endpoint, and the total generation value of the J endpoint is updated according to the g(t) value calculated based on the GJ path.
  • the parent node is searched sequentially from the Q endpoint, and a shortest path from the B endpoint to the Q endpoint is obtained; if the open table is already If the Q endpoint is not added to the closed table, then the path from the B endpoint to the Q endpoint cannot be planned, and the path planning is stopped.
  • 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 start point of the path to the destination.
  • Fig. 4 is a block diagram showing the structure of a path planning device for an unmanned vehicle in one embodiment.
  • the device 400 specifically includes the following:
  • a starting and ending section obtaining module 402 configured to acquire a road section where the starting point of the path is located, and a road section where the destination is located;
  • the road section includes a road section and a connecting channel;
  • the initial path generating module 404 is configured to perform a path search according to the connectivity relationship between the endpoints of the road segments, and generate an initial path.
  • the endpoints of the road segments include: an exit endpoint of the road segment where the starting point is located, where the destination is located An entry endpoint of the link, and an entry endpoint and an exit endpoint of each segment of the exit endpoint for connecting the segment where the origin is located and the entry endpoint of the segment where the destination is located;
  • An egress endpoint update module 406 configured to update, according to an ingress endpoint of each connected channel included in the initial path, an egress end point of a previous road segment of each connected channel in a passable direction; wherein an ingress endpoint of the connected channel is the An exit end point of the lane of the predetermined condition included in the previous road section of the connecting passage in the direction of the lane, wherein the lane of the predetermined condition is a lane whose attribute category matches the attribute category of the connected channel;
  • the final path generation module 408 is configured to generate a final planned path according to each endpoint included in the updated initial path.
  • the exit end point of the previous road segment of each connecting channel of the final planning path is the exit end point of the lane in the road segment whose attribute category matches the attribute category of the connected channel .
  • the start and stop segment acquisition module 402 includes:
  • a vehicle live acquisition unit for acquiring a current location of the vehicle and a current heading
  • a starting road segment determining module configured to search for a waypoint located within a range that is less than a preset angle from the current heading and is closest to the current location, and determine a road segment where the waypoint is located The road segment where the starting point of the path is.
  • the start and stop segment acquisition module 402 includes:
  • a destination information obtaining unit configured to acquire information of the destination
  • the terminating road segment determining module is configured to determine a road segment where the waypoint closest to the destination is located as the road segment where the destination is located.
  • the apparatus 400 further includes:
  • the ingress endpoint update module acquires an ingress endpoint of a lane corresponding to an egress point of each road segment included in the updated initial path, and updates the ingress endpoint to an ingress endpoint of each road segment included in the initial path.
  • the apparatus 400 further includes:
  • a lane number obtaining module configured to acquire, when the entrance lane and the exit lane of any road section in the initial path after the update are different, the serial number of the entrance lane of the detected road section and the serial number of the exit lane;
  • the entrance lane is a lane corresponding to an entrance end point of the road section
  • the exit lane is a lane corresponding to an exit end point of the road section;
  • a sequence number difference calculation module configured to calculate a difference between the detected serial number of the entrance lane of each road segment and the serial number of the exit lane;
  • a curvature acquiring module configured to acquire a curvature of each of the detected road points included in each road segment detected in each detected road segment;
  • a change road point determining module configured to determine, according to the detected curvature corresponding to each road point included in each road segment, a changed road point having the same number as the difference among the detected road points included in each road segment;
  • the final path generation module 408 is configured to:
  • a final planned path is generated according to each of the changed endpoints and the updated endpoints included in the updated initial path.
  • path planning device of the unmanned vehicle of the present embodiment may be the same as those in the above-described path planning method embodiment of the unmanned vehicle.
  • Figure 5 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 may also store a computer program that, when executed by the processor, causes the processor to implement the path planning method of the above-described unmanned vehicle.
  • the internal memory may also store a computer program that, when executed by the processor, causes the processor to execute the path planning method of the unmanned vehicle 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. 5 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 planning apparatus for an unmanned vehicle can be implemented in the form of a computer program that can be run on a computer device as shown in FIG.
  • the program modules of the path planning device constituting the unmanned vehicle may be stored in a memory of the computer device, such as the start and stop segment acquisition module 402, the initial path generation module 404, the exit endpoint update module 406, and the final path generation shown in FIG. Module 408.
  • the computer program of each program module causes the processor to perform the steps in the path planning method of the unmanned vehicle of the embodiments of the present application described in the present specification.
  • the computer device shown in FIG. 5 can perform the step S202 in FIG. 2 through the start and stop segment acquisition module 402 in the path planning device of the driverless vehicle as shown in FIG. 4, and the initial path generation module 404 executes the process in FIG. Step S204, the exit endpoint update module 406 performs step S206 in FIG. 2, and the final path generation module 408 performs step S208 and the like in FIG.
  • 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 planning method of the unmanned vehicle in any of the embodiments provided by the present application.
  • the exit end point of the previous road section of each connecting channel of the final planning path is an exit end point of the lane that is included in the road section whose attribute category matches the attribute category of the connected channel.
  • 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 planning method for an unmanned vehicle in any of the embodiments provided by the present application.
  • the exit end point of the previous road segment of each connecting channel of the final planning path is an exit end point of the lane in the road segment whose attribute category matches the attribute category of the connected channel.

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

提供了一种无人驾驶车辆的路径规划方法、装置、存储介质及计算机设备，其中该方法包括：获取路径的起点及目的地所在的路段，路段包括道路路段和连通道（S202）；根据起点所在的路段的出口端点、目的地所在的路段的入口端点、及用于连通起点所在路段的出口端点和目的地所在路段的入口端点的各路段的入口端点和出口端点进行路径搜索，生成初始路径（S204）；根据初始路径中的各连通道的入口端点更新可通行方向上各连通道的前一道路路段的出口端点；连通道的入口端点为可通行方向上该连通道的前一道路路段中包含的其属性类别与该连通道的属性类别相匹配的车道的出口端点（S206）；根据更新后的初始路径中的各端点生成最终规划路径（S208）。该方法提供的方案能保障无人车遵守交通规则及行车安全。

Description

无人驾驶车辆的路径规划方法、装置及计算机设备 技术领域
本发明涉及无人驾驶技术领域，特别是涉及一种无人驾驶车辆的路径规划方法、装置、计算机可读存储介质及计算机设备。
背景技术
路径规划是驾驶车辆研究的关键技术之一，在进行路径规划时，一般是规划从出发点到目的地(也称为目标点)之间的纯几何路径。目前车辆的路径规划一般为道路级的规划，即规划出从出发点到目的地所要经过的道路。然而，基于道路级规划后获得的路径行驶车辆时，特别是对无人驾驶车辆而言，将无法保障无人驾驶车辆遵守交通规则，也无法保障行车安全。
发明内容
基于此，有必要针对传统方式生成的行驶路径无法保障车辆遵守交通规则、无法保障行车安全的问题，提供一种无人驾驶车辆的路径规划方法、装置、计算机可读存储介质及计算机设备。
一种无人驾驶车辆的路径规划方法，所述方法包括：
获取路径的起点所在的路段、以及目的地所在的路段；所述路段包括道路路段和连通道；
根据各路段的端点之间的连通关系进行路径搜索，生成初始路径；所述各路段的端点包括：所述起点所在的路段的出口端点、所述目的地所在的路段的入口端点、以及用于连通所述起点所在的路段的出口端点和所述目的地所在的路段的入口端点的各路段的入口端点和出口端点；
根据所述初始路径包含的各连通道的入口端点更新可通行方向上各连通道的前一道路路段的出口端点；其中，所述连通道的入口端点为所述可通行方向上该连通道的前一道路路段中包含的预定条件的车道的出口端点，所述预定条件的车道为其属性类别与该连通道的属性类别相匹配的车道；
根据更新后的初始路径中包含的各端点生成最终规划路径。
一种无人驾驶车辆的路径规划装置，所述装置包括：
起止路段获取模块，用于获取路径的起点所在的路段、以及目的地所在的路段；所述路段包括道路路段和连通道；
初始路径生成模块，用于根据各路段的端点之间的连通关系进行路径搜索，生成初始路径；所述各路段的端点包括：所述起点所在的路段的出口端点、所述目的地所在的路段的入口端点、以及用于连通所述起点所在的路段的出口端点和所述目的地所在的路段的入口端点的各路段的入口端点和出口端点；
出口端点更新模块，用于根据所述初始路径包含的各连通道的入口端点更新可通行方向上各连通道的前一道路路段的出口端点；其中，所述连通道的入口端点为所述可通行方向上该连通道的前一道路路段中包含的预定条件的车道的出口端点，所述预定条件的车道为其属性类别与该连通道的属性类别相匹配的车道；以及，
最终路径生成模块，用于根据更新后的初始路径中包含的各端点生成最终规划路径。
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无人驾驶车辆的路径规划方法的步骤。
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无人驾驶车辆的路径规划方法的步骤。
上述无人驾驶车辆的路径规划方法、装置、计算机可读存储介质及计算机设备，最终规划路径的各连通道的前一道路路段的出口端点均为该道路路段中包含的其属性类别与该连通道的属性类别相匹配的车道的出口端点。可见，无人驾驶车辆按照该最终生成路径行驶时，能够通过符合交通规则的车道从道路路段驶入与之连接的连通道，因此能保障无人驾驶车辆遵守交通规则，及保障其行车安全。
附图说明
图1为一个实施例中高精度地图的层次结构示意图；
图2为一个实施例中施工路段无人驾驶车辆的路径规划方法的流程示意图；
图3为一个路网示意图；
图4为一个实施例中施工路段无人驾驶车辆的路径规划装置的结构示意图；
图5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无人驾驶车辆的路径规划方法可应用于控制终端，该控制终端可以为移动终端或无人驾驶车辆上的车载终端。其中，移动终端具体可以为手机、平板电脑或笔记本电脑等。
实际应用中，在执行本发明的各实施例中的方法步骤之前，需要采集地图数据及制作高精度地图。
具体地，由专用的地图数据采集车在实际路段中行驶，在各路段中勘测一系列路点以确定该路段的几何参数，以此来采集地图数据。路段可包括道路路段及连通道，其中，道路路段可包括若干条车道，连通道是指位于两条道路路段之间，且将这两条道路路段连通起来的路段。基于交通规则，连通道及道路路段包含的车道均具有相应的属性类别。
基于属性类别，道路路段的车道可包括直行车道、左转车道、右转车道、掉头车道以及应急车道等等。可以理解的是，在部分道路路段中，一条车道可以具有多个属性类别，例如，左转直行车道，即在该车道的出口端点处，车辆既可以路口直行，也可以路口左转。
另外，基于属性类别，连通道可包括分叉道直行连通道、路口直行连通道、路口左转连通道、路口右转连通道以及路口掉头连通道等等。
制作高精度地图还涉及地图数据格式的定义，具体地，参照图1，高精度地 图数据可包括地图层、路段层、连通道层、车道层及路点层。其中，地图层可包括总路段数；路段层可包括：各路段的序号、各路段所包含的车道数、各路段的出口处的连通道数；连通道层可包括：各连通道的序号、位于各连通道的入口端点处的道路路段中的车道的序号、位于各连通道的出口端点处的道路路段的序号、位于各连通道的出口端点处的道路路段中的车道的序号、各连通道的类别、各连通道所包含的路点数；车道层可包括：各车道的序号、各车道的宽度、各车道的类别、各车道所包含的路点数；路点层可包括：各路点的序号、经度以及纬度。
图2示出了一个实施例中无人驾驶车辆的路径规划方法的流程示意图。该实施例中以该方法应用于上文所述的控制终端举例说明。参照图2，该方法具体包括如下步骤S202至步骤S208。
步骤S202，获取路径的起点所在的路段、以及目的地所在的路段；所述路段包括道路路段和连通道。
其中，路段一般是指交通网络上相邻两个节点之间的交通线路，这两个节点分别为路段的入口端点及出口端点。具体地，路段可包括道路路段和位于两条道路路段之间，且将这两条道路路段连通起来的连通道。
需要说明的是，在执行步骤S202之前，需获取路径的起点及目的地。可由用户根据实际需求直接向控制终端输入路径的起点及目的地。或者，可基于本车当前所处的位置及当前航向获取路径的起点，并基于用户输入的目标位置获取路径的目的地。另外，可基于高精度地图确定起点及目的地所在的路段。其中，起点可能处在道路路段中，也可能处在连通道中，目的地类似，此处不加赘述。
步骤S204，根据各路段的端点之间的连通关系进行路径搜索，生成初始路径；所述各路段的端点包括：所述起点所在的路段的出口端点、所述目的地所在的路段的入口端点、以及用于连通所述起点所在的路段的出口端点和所述目的地所在的路段的入口端点的各路段的入口端点和出口端点。
需要说明的是，高精度地图中预先存储了路段自身的端点之间的连通信息以及各路段的端点彼此间的连通信息，基于相应的连通信息即可建立路段自身 的端点之间连通性以及各路段的端点之间的连通性。例如，在高精度地图中，道路路段AB的入口端点A与其出口端点B之间是自然连通的，基于该连通信息即可建立该入口端点A与该出口端点B之间的连通性。另外，在高精度地图中，道路路段AB的出口端点B即为连通道BC的入口端点，基于该连通信息即可建立道路路段AB的出口端点与连通道BC的入口端点之间的连通性。
以图3所示路网为例，首先需说明的是，图3中的实线表示道路路段，虚线表示连通道。图3所示路网中各端点之间的连通性如下：端点A与端点B连通，端点B与端点C连通，端点B与端点D连通，端点B与端点E连通，端点C与端点F连通，端点F与端点I连通，端点F与端点J连通，端点I与端点L连通，端点L与端点Q连通，端点Q与端点R连通，端点J与端点M连通，端点M与端点N连通，端点M与端点K连通，端点N与端点P连通，端点P与端点Q连通，端点K与端点O连通，端点O与端点Q连通，端点O与端点N连通，端点D与端点G连通，端点G与端点J连通，端点G与端点K连通，端点E与端点H连通，端点H与端点K连通。
在一个具体的示例中，基于高精度地图中存储的各路段的端点之间的连通关系，即可搜索到连通路径的起点所在的路段的出口端点与目的地所在路段的入口端点的各可通行的路段，从而获得各可通行的路段的入口端点和出口端点，即可在起点所在的路段的出口端点、目的地所在的路段的入口端点以及各可通行的路段的入口端点和出口端点中进行路径搜索，从而生成一条可从路径的起点通往目的地的初始路径。
以图3所示路网为例，从路径的起点所在的路段AB的出口端点B开始搜索，搜索获得连通出口端点B和入口端点Q的所有可通行路段(如路段BC、路段CF、路段FI、路段IL和路段LQ等)，从而获得各可通行路段的入口端点及出口端点(如端点B、端点C、端点F、端点I、端点L和端点Q等等)，基于获得的各可通行路段的入口端点及出口端点中进行路径搜索，从而生成一条可从路径的起点通往目的地的初始路径，如路径B-C-F-I-L-Q。需要说明的是，生成的初始路径的方式有多种，只需保证生成的初始路径能从路径的起点通往目的地即可，例如路径B-E-H-K-O-Q、或者路径B-D-G-J-M-N-P-Q均可以符合 要求，此处不再一一举例。
步骤S206，根据所述初始路径包含的各连通道的入口端点更新可通行方向上各连通道的前一道路路段的出口端点；其中，所述连通道的入口端点为所述可通行方向上该连通道的前一道路路段中包含的预定条件的车道的出口端点，所述预定条件的车道为其属性类别与该连通道的属性类别相匹配的车道。
需要说明的是，初始路径可以指基于道路级规划的路径，即无人驾驶车辆根据该初始路径可以确定从路径的起点通往目的地所经过的路段，及各路段间的位置关系，例如基于图3中的路径B-C-F-I-L-Q-R，可确定需经过连通道BC、道路路段CF、连通道FI、道路路段IL以及连通道LQ，其中，连通道FI的前一道路路段为CF，连通道LQ的前一道路路段为IL。但可以理解，在初始路径中，还并未确定初始路径中包含的各道路路段的出口端点处需行驶的出口车道。
在本实施例中，生成初始路径后，根据初始路径包含的各连通道的入口端点更新可通行方向上各连通道的前一道路路段的出口端点。例如，图3中示出的初始路径B-C-F-I-L-Q，其道路路段CF，在路段层面，道路路段CF的出口端点为F，但细化到车道层面，若道路路段CF包括左转车道、直行车道和右转车道三条车道，假设这三条车道的出口端点分别为f1、f2和f3(未图示)，并且，连通道FI为左转连通道，则在高精度地图中，连通道FI的入口端点为其前一道路路段CF中的左转车道的出口端点f1。则，可基于连通道FI的入口端点将其前一道路路段CF的出口端点从路段层面中的F端点更新为车道层面的f1端点，同理，可基于连通道BC的入口端点B更新道路路段AB的出口端点B，基于连通道LQ的入口端点L更新道路路段IL的出口端点L，此处不加赘述。步骤S208，根据更新后的初始路径中包含的各端点生成最终规划路径。
需要说明的是，经过更新后，初始路径中包含的各道路路段的出口端点均为车道的出口端点，进而可生成最终规划路径。可以理解的是，道路路段和连通道除入口端点及出口端点外，还包括若干个路点，因此生成的最终规划路径覆盖了若干条道路路段的入口端点、出口端点和路点、以及若干条连通道的入口端点、出口端点和路点。
上述无人驾驶车辆的路径规划方法，最终规划路径的各连通道的前一道路 路段的出口端点均为该道路路段中包含的其属性类别与该连通道的属性类别相匹配的车道的出口端点。可见，无人驾驶车辆按照该最终生成路径行驶时，能够通过符合交通规则的车道从道路路段驶入与之连接的连通道，因此能保障无人驾驶车辆遵守交通规则，及保障其行车安全。
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，获取路径的起点所在的路段的方式包括：
获取车辆的当前所处位置以及当前航向；
搜索位于与所述当前航向的夹角小于预设角度的范围内、且与所述当前所处位置距离最近的路点，并将该路点所处的路段确定为路径的起点所在的路段。
在实际应用中，可以无需用户手动输入，而是自动定位本车当前所处的位置，以及检测本车的当前航向(即当前行驶方向)，再基于高精度地图在各道路路段包含的端点及各连通道包含的端点中进行搜索，将搜索到的位于与当前航向的夹角小于预设角度的范围内，且与本车当前所处位置最近的端点所在的路段确定为路径的起点所在的路段。优选地，预设角度可为90°。
另外，在将到与本车当前所处位置最近的端点确定为路径的起点之前，可以先判断与本车当前所处位置最近的端点到本车当前所处的位置的距离是否超过预设距离值，若是，则说明本车当前处于未知路径上，可停止路径规划。其中，预设距离值可根据GPS的允许误差范围设定。
在一个实施例中，获取目的地所在的路段的方式包括：
获取所述目的地的信息；
将与所述目的地距离最近的路点所处的路段确定为目的地所在的路段。
其中，目的地是指本车需到达的位置点。可由用户手动向控制终端输入目的地的信息，相应地，控制终端接收到目的地的信息后，再基于高精度地图在各道路路段包含的端点及各连通道包含的端点中进行搜索，将搜索获得的与该目的地距离最近的端点所在的路段确定为目的地所在的路段。
在一个实施例中，在所述根据更新后的初始路径中包含的各端点生成最终规划路径的步骤之前，还包括：
获取更新后的所述初始路径中包含的各道路路段的出口端点对应的车道的入口端点，并将该入口端点更新为所述初始路径中包含的各道路路段的入口端点。
在本实施例中，对于初始路径中包含的各道路路段，获取更新后，其出口端点对应的车道的入口端点，并将该入口端点更新为其入口端点。例如，图3中示出的初始路径B-C-F-I-L-Q，对于道路路段CF，其左转车道、直行车道和右转车道的入口端点分别为c1、c2和c3。更新后(执行过步骤S206后)，道路路段CF的出口端点为道路路段CF中的左转车道的出口端点f1，则获取出口端点f1对应的左转车道的入口端点c1，并将道路路段的出口端点从路段层面的C端点更新为车道层面的c1端点。同理，可基于连通道BC的入口端点B更新道路路段AB的入口端点A，基于连通道LQ的入口端点L更新道路路段IL的入口端点I，此处不加赘述。
本实施例生成的最终规划路径中，道路路段的入口车道和出口车道为同一条车道。基于最终规划路径，无人驾驶车辆在行驶过程中，驶入一条道路路段后，可直接通过驶入的车道驶出该道路路段，中途无需变道行驶。
在一个实施例中，在所述根据更新后的初始路径中包含的各端点生成最终规划路径步骤之前，还包括，
当检测到更新后的初始路径中任一道路路段的入口车道与出口车道不相同时，获取检测到的各道路路段的入口车道的序号与出口车道的序号；所述入口车道为道路路段的入口端点对应的车道，所述出口车道为道路路段的出口端点对应的车道；
计算检测到的各道路路段的入口车道的序号与其出口车道的序号的差值；
获取检测到的各道路路段包含的各路点在检测到的各道路路段中所处位置处的曲率；
根据检测到的各道路路段包含的各路点对应的曲率，在检测到的各道路路段包含的各路点中确定数量与所述差值相同的变道路点；
则所述根据更新后的初始路径中包含的各端点生成最终规划路径的步骤，包括：
根据所述变道路点及更新后的初始路径中包含的各端点生成最终规划路径。
需要说明的是，若基于高精度地图检测到初始路径中存在道路路段的入口端点和出口端点未处于同一条车道上，即道路路段的入口车道与出口车道不是同一条车道，则需计算该道路路段的入口端点所在车道的序号和该出口端点所在车道的序号的差值，并在该道路路段中确定数量与该差值相同的变道路点，以规划出在相应道路路段中渐次行经不同车道的最终规划路径，从而保证车辆能从设定的出口车道驶离相应的道路路段。
在本实施例中，可基于道路路段中包含的所有路点在该道路路段中所处位置的曲率确定变道路点。具体地，可避开曲率较大的路点，而选取曲率较小的路点作为变道路点，以将变道路点设置在直道路段。另外，相邻的两个变道路点之间可留有充裕的间距。
在一个实施例中，所述根据各路段的端点之间的连通关系进行路径搜索，生成初始路径的步骤，包括：
根据各路段的端点之间的连通关系及A星算法进行路径搜索，生成初始路径。
在本实施例中，采用A星算法进行路径搜索，在路径搜索过程中，采用下述公式计算当前端点的总代价值：
f(t)＝g(t)+h(t)
其中，f(t)为当前端点的总代价值；g(t)为起点到当前端点的实际路径累计距离代价；h(t)是当前端点到目的地的预估距离代价。
在一个具体的示例中，预估距离代价可以为曼哈顿距离代价，即当前端点与目的地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。
接下来，以图3所示路网为例，对基于A星算法进行路径搜索的过程进行说明。
首先，设置open表与closed表。将B端点直接加入closed表中，从B端点 开始搜索，将与B端点相连的所有端点(C端点、D端点及E端点)加入open表中，并设置B端点为C端点、D端点和E端点的父节点，再分别计算open表中的C端点、D端点和E端点的总代价值，假设这三个端点中，C端点的总代价值最小，E端点的总代价值最大。
将open表中当前总代价值最小的C端点移出open表，并加入closed表中。接着，考察与C端点相连，但不位于closed表中的所有端点，即F端点，将C端点设置为F端点的父节点，并计算F端点的总代价值，以及将F端点加入到open表中，假设F端点的总代价值大于D端点及E端点的总代价值。
将open表中当前总代价值最小的D端点移出open表，并加入closed表中。接着，考察与D端点相连，但不位于closed表中的所有端点，即G端点，将D端点设置为G端点的父节点，并计算G端点的总代价值，以及将G端点加入到open表中，假设G端点的总代价值大于E端点和F端点的总代价值。
将open表中当前总代价值最小的E端点移出open表，并加入closed表中。接着，考察与E端点相连，但不位于closed表中的所有端点，即H端点，将E端点设置为H端点的父节点，并计算H端点的总代价值，以及将H端点加入到open表中，假设H端点的总代价值大于F端点和G端点的总代价值。
将open表中当前总代价值最小的F端点移出open表，并加入closed表中。接着，考察与F端点相连，但不位于closed表中的所有端点，即I端点和J端点，将F端点设置为I端点和J端点的父节点，并分别计算I端点和J端点的总代价值，以及将I端点和J端点加入到open表中，假设J端点的总代价值大于I端点的总代价值，I端点的总代价值大于F端点和G端点的总代价值。
将open表中当前总代价值最小的G端点移出open表，并加入closed表中。接着，考察与G端点相连，但不位于closed表中的所有端点，即J端点和K端点。对既不属于open表也不属于closed表的K端点，将G端点设置为其父节点，并计算K端点的总代价值，以及将K端点加入到open表中；对于已经属于open表的J端点，比较基于G-J路径计算的g(t)值和之前基于F-J路径计算的g(t)值，若基于G-J路径计算的g(t)值小于基于F-J路径计算的g(t)，则将J端点的父节点从F端点修改为G端点，并根据基于G-J路径计算的g(t)值更新J端点的总 代价值。
按照以上相同的操作依次类推，直到将Q端点加入到closed表中为止，此时从Q端点开始依次搜索父节点，即可获得一条由B端点通往Q端点的最短路径；若open表已经为空，也仍未将Q端点加入到closed表中，则说明无法规划出一条由B端点通往Q端点的路径，则停止路径规划。
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路径的起点到目的地的最短路径。
图4示出了一个实施例中无人驾驶车辆的路径规划装置的结构示意图。参照图4，该装置400具体包括如下：
起止路段获取模块402，用于获取路径的起点所在的路段、以及目的地所在的路段；所述路段包括道路路段和连通道；
初始路径生成模块404，用于根据各路段的端点之间的连通关系进行路径搜索，生成初始路径；所述各路段的端点包括：所述起点所在的路段的出口端点、所述目的地所在的路段的入口端点、以及用于连通所述起点所在的路段的出口端点和所述目的地所在的路段的入口端点的各路段的入口端点和出口端点；
出口端点更新模块406，用于根据所述初始路径包含的各连通道的入口端点更新可通行方向上各连通道的前一道路路段的出口端点；其中，所述连通道的入口端点为所述可通行方向上该连通道的前一道路路段中包含的预定条件的车道的出口端点，所述预定条件的车道为其属性类别与该连通道的属性类别相匹配的车道；以及，
最终路径生成模块408，用于根据更新后的初始路径中包含的各端点生成最终规划路径。
上述无人驾驶车辆的路径规划装置，最终规划路径的各连通道的前一道路路段的出口端点均为该道路路段中包含的其属性类别与该连通道的属性类别相匹配的车道的出口端点。可见，无人驾驶车辆按照该最终生成路径行驶时，能够通过符合交通规则的车道从道路路段驶入与之连接的连通道，因此能保障无人驾驶车辆遵守交通规则，及保障其行车安全。
在一个实施例中，所述起止路段获取模块402包括：
车辆实况获取单元，用于获取车辆的当前所处位置以及当前航向；以及，
起始路段确定模块，用于搜索位于与所述当前航向的夹角小于预设角度的范围内、且与所述当前所处位置距离最近的路点，并将该路点所处的路段确定为路径的起点所在的路段。
在一个实施例中，所述起止路段获取模块402包括：
目的地信息获取单元，用于获取所述目的地的信息；以及，
终止路段确定模块，用于将与所述目的地距离最近的路点所处的路段确定为目的地所在的路段。
在一个实施例中，所述装置400还包括：
入口端点更新模块，获取更新后的所述初始路径中包含的各道路路段的出口端点对应的车道的入口端点，并将该入口端点更新为所述初始路径中包含的各道路路段的入口端点。
在一个实施例中，所述装置400还包括：
车道序号获取模块，用于当检测到更新后的初始路径中任一道路路段的入口车道与出口车道不相同时，获取检测到的各道路路段的入口车道的序号与出口车道的序号；所述入口车道为道路路段的入口端点对应的车道，所述出口车道为道路路段的出口端点对应的车道；
序号差值计算模块，用于计算检测到的各道路路段的入口车道的序号与其出口车道的序号的差值；
曲率获取模块，用于获取检测到的各道路路段包含的各路点在检测到的各道路路段中所处位置处的曲率；以及，
变道路点确定模块，用于根据检测到的各道路路段包含的各路点对应的曲率，在检测到的各道路路段包含的各路点中确定数量与所述差值相同的变道路点；
且，所述最终路径生成模块408用于：
根据所述变道路点及更新后的初始路径中包含的各端点生成最终规划路径。
本实施例的无人驾驶车辆的路径规划装置中的其他技术特征，可以与上述 无人驾驶车辆的路径规划方法实施例中的相同。
图5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5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无人驾驶车辆的路径规划方法。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无人驾驶车辆的路径规划方法。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5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，本发明提供的无人驾驶车辆的路径规划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5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无人驾驶车辆的路径规划装置的各个程序模块，比如，图4所示的起止路段获取模块402、初始路径生成模块404、出口端点更新模块406和最终路径生成模块408。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无人驾驶车辆的路径规划方法中的步骤。
例如，图5所示的计算机设备可以通过如图4所示的无人驾驶车辆的路径规划装置中的起止路段获取模块402执行图2中的步骤S202、初始路径生成模块404执行图2中的步骤S204、出口端点更新模块406执行图2中的步骤S206、以及最终路径生成模块408执行图2中的步骤S208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无人驾驶车辆的路径规划方法的步骤。
上述计算机设备，最终规划路径的各连通道的前一道路路段的出口端点均为该道路路段中包含的其属性类别与该连通道的属性类别相匹配的车道的出口端点。可见，无人驾驶车辆按照该最终生成路径行驶时，能够通过符合交通规则的车道从道路路段驶入与之连接的连通道，因此能保障无人驾驶车辆遵守交通规则，及保障其行车安全。
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无人驾驶车辆的路径规划方法的步骤。
上述计算机可读存储介质，最终规划路径的各连通道的前一道路路段的出口端点均为该道路路段中包含的其属性类别与该连通道的属性类别相匹配的车道的出口端点。可见，无人驾驶车辆按照该最终生成路径行驶时，能够通过符合交通规则的车道从道路路段驶入与之连接的连通道，因此能保障无人驾驶车 辆遵守交通规则，及保障其行车安全。
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. 一种无人驾驶车辆的路径规划方法，其特征在于，所述方法包括：
    获取路径的起点所在的路段、以及目的地所在的路段；所述路段包括道路路段和连通道；
    根据各路段的端点之间的连通关系进行路径搜索，生成初始路径；所述各路段的端点包括：所述起点所在的路段的出口端点、所述目的地所在的路段的入口端点、以及用于连通所述起点所在的路段的出口端点和所述目的地所在的路段的入口端点的各路段的入口端点和出口端点；
    根据所述初始路径包含的各连通道的入口端点更新可通行方向上各连通道的前一道路路段的出口端点；其中，所述连通道的入口端点为所述可通行方向上该连通道的前一道路路段中包含的预定条件的车道的出口端点，所述预定条件的车道为其属性类别与该连通道的属性类别相匹配的车道；
    根据更新后的初始路径中包含的各端点生成最终规划路径。
  2. 如权利要求1所述的无人驾驶车辆的路径规划方法，其特征在于，获取路径的起点所在的路段的方式包括：
    获取车辆的当前所处位置以及当前航向；
    搜索位于与所述当前航向的夹角小于预设角度的范围内、且与所述当前所处位置距离最近的路点，并将该路点所处的路段确定为路径的起点所在的路段。
  3. 如权利要求1所述的无人驾驶车辆的路径规划方法，其特征在于，获取目的地所在的路段的方式包括：
    获取所述目的地的信息；
    将与所述目的地距离最近的路点所处的路段确定为目的地所在的路段。
  4. 如权利要求1所述的无人驾驶车辆的路径规划方法，其特征在于，在所述根据更新后的初始路径中包含的各端点生成最终规划路径的步骤之前，还包括：
    获取更新后的所述初始路径中包含的各道路路段的出口端点对应的车道的入口端点，并将该入口端点更新为所述初始路径中包含的各道路路段的入口端点。
  5. 如权利要求1至4任一项所述的无人驾驶车辆的路径规划方法，其特征在于，在所述根据更新后的初始路径中包含的各端点生成最终规划路径的步骤之前，还包括，
    当检测到更新后的初始路径中任一道路路段的入口车道与出口车道不相同时，获取检测到的各道路路段的入口车道的序号与出口车道的序号；所述入口车道为道路路段的入口端点对应的车道，所述出口车道为道路路段的出口端点对应的车道；
    计算检测到的各道路路段的入口车道的序号与其出口车道的序号的差值；
    获取检测到的各道路路段包含的各路点在检测到的各道路路段中所处位置处的曲率；
    根据检测到的各道路路段包含的各路点对应的曲率，在检测到的各道路路段包含的各路点中确定数量与所述差值相同的变道路点；
    所述根据更新后的初始路径中包含的各端点生成最终规划路径的步骤包括：
    根据所述变道路点及更新后的初始路径中包含的各端点生成最终规划路径。
  6. 一种无人驾驶车辆的路径规划装置，其特征在于，所述装置包括：
    起止路段获取模块，用于获取路径的起点所在的路段、以及目的地所在的路段；所述路段包括道路路段和连通道；
    初始路径生成模块，用于根据各路段的端点之间的连通关系进行路径搜索，生成初始路径；所述各路段的端点包括：所述起点所在的路段的出口端点、所述目的地所在的路段的入口端点、以及用于连通所述起点所在的路段的出口端点和所述目的地所在的路段的入口端点的各路段的入口端点和出口端点；
    出口端点更新模块，用于根据所述初始路径包含的各连通道的入口端点更新可通行方向上各连通道的前一道路路段的出口端点；其中，所述连通道的入口端点为所述可通行方向上该连通道的前一道路路段中包含的预定条件的车道的出口端点，所述预定条件的车道为其属性类别与该连通道的属性类别相匹配的车道；以及，
    最终路径生成模块，用于根据更新后的初始路径中包含的各端点生成最终规划路径。
  7. 如权利要求6所述的无人驾驶车辆的路径规划装置，其特征在于，所述装置还包括：
    入口端点更新模块，获取更新后的所述初始路径中包含的各道路路段的出口端点对应的车道的入口端点，并将该入口端点更新为所述初始路径中包含的各道路路段的入口端点。
  8. 如权利要求6至7任一项所述的无人驾驶车辆的路径规划装置，其特征在于，所述装置还包括：
    车道序号获取模块，用于当检测到更新后的初始路径中任一道路路段的入口车道与出口车道不相同时，获取检测到的各道路路段的入口车道的序号与出口车道的序号；所述入口车道为道路路段的入口端点对应的车道，所述出口车道为道路路段的出口端点对应的车道；
    序号差值计算模块，用于计算检测到的各道路路段的入口车道的序号与其出口车道的序号的差值；
    曲率获取模块，用于获取检测到的各道路路段包含的各路点在检测到的各道路路段中所处位置处的曲率；以及，
    变道路点确定模块，用于根据检测到的各道路路段包含的各路点对应的曲率，在检测到的各道路路段包含的各路点中确定数量与所述差值相同的变道路点；
    且，所述最终路径生成模块用于：
    根据所述变道路点及更新后的初始路径中包含的各端点生成最终规划路径。
  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5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5任一项所述方法的步骤。
PCT/CN2018/111084 2017-10-25 2018-10-19 无人驾驶车辆的路径规划方法、装置及计算机设备 WO2019080781A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/488,948 US20210080267A1 (en) 2017-10-25 2018-10-19 Path Planning Method and Device for Unmanned Vehicle, and Computer Device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711016390.1A CN107817000B (zh) 2017-10-25 2017-10-25 无人驾驶车辆的路径规划方法、装置及计算机设备
CN201711016390.1 2017-10-25

Publications (1)

Publication Number Publication Date
WO2019080781A1 true WO2019080781A1 (zh) 2019-05-02

Family

ID=61604209

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/111084 WO2019080781A1 (zh) 2017-10-25 2018-10-19 无人驾驶车辆的路径规划方法、装置及计算机设备

Country Status (3)

Country Link
US (1) US20210080267A1 (zh)
CN (1) CN107817000B (zh)
WO (1) WO2019080781A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113434624A (zh) * 2021-07-27 2021-09-24 北京百度网讯科技有限公司 车辆的驾驶辅助方法、装置、设备、介质及程序产品
CN113778102A (zh) * 2021-09-22 2021-12-10 重庆长安汽车股份有限公司 Avp全局路径规划系统、方法、车辆及存储介质

Families Citing this family (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107817000B (zh) * 2017-10-25 2020-09-08 广州汽车集团股份有限公司 无人驾驶车辆的路径规划方法、装置及计算机设备
JP6881233B2 (ja) * 2017-10-27 2021-06-02 井関農機株式会社 作業車両
US20190293441A1 (en) * 2018-03-25 2019-09-26 Mitac International Corp. Method of route planning and handling prohibited complex driving maneuvers
CN110657814A (zh) * 2018-06-29 2020-01-07 比亚迪股份有限公司 轨迹规划方法和装置、车辆及其控制方法和系统
CN110839207B (zh) * 2018-08-17 2021-03-19 广州汽车集团股份有限公司 导航方法、装置、系统、计算机设备和存储介质
CN109238270A (zh) * 2018-10-21 2019-01-18 浙江浙大中控信息技术有限公司 基于改进的a星算法的智能导航方法
CN109631873B (zh) * 2018-11-01 2021-01-05 百度在线网络技术（北京）有限公司 高精地图的道路生成方法、装置及可读存储介质
KR20200057507A (ko) * 2018-11-16 2020-05-26 현대자동차주식회사 차량의 주행 차로 관리 장치, 그를 포함한 시스템 및 그 방법
CN111457931B (zh) * 2019-01-21 2021-09-24 广州汽车集团股份有限公司 自动驾驶车辆的局部路径重规划控制方法、装置、系统及存储介质
CN109612496B (zh) * 2019-02-20 2021-03-16 百度在线网络技术（北京）有限公司 一种路径规划方法、装置及车辆
CN109828579B (zh) * 2019-02-25 2021-09-24 广东工业大学 一种目标增量移动的移动机器人路径规划方法
CN110736480A (zh) * 2019-09-27 2020-01-31 西安天和防务技术股份有限公司 路径规划方法、装置、计算机设备和存储介质
CN112579715B (zh) * 2019-09-30 2023-04-25 阿里巴巴集团控股有限公司 数据处理方法、装置、电子设备及存储介质
CN111426330B (zh) * 2020-03-24 2022-03-15 江苏徐工工程机械研究院有限公司 路径生成方法和设备、无人化运输系统和存储介质
WO2021189374A1 (en) * 2020-03-26 2021-09-30 Baidu.Com Times Technology (Beijing) Co., Ltd. A 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
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
CN113689021B (zh) * 2020-05-19 2024-04-30 百度在线网络技术（北京）有限公司 用于输出信息的方法和装置
CN111664864A (zh) * 2020-05-31 2020-09-15 武汉中海庭数据技术有限公司 一种基于自动驾驶的动态规划方法及装置
CN112033421B (zh) * 2020-08-25 2022-07-15 北京三快在线科技有限公司 一种检测电子地图中车道的方法及装置
CN112693445B (zh) * 2021-01-11 2022-04-22 广东科学技术职业学院 控制车辆并入目标车道的方法、装置以及无人驾驶车辆
CN114973641B (zh) * 2021-02-26 2024-05-07 阿里巴巴集团控股有限公司 数据处理方法、装置、电子设备及可读存储介质
CN113320547B (zh) * 2021-07-15 2023-08-25 广州小鹏自动驾驶科技有限公司 路径检测方法、装置及汽车
CN113628471A (zh) * 2021-08-09 2021-11-09 广州文远知行科技有限公司 一种无人驾驶车辆的调度方法、装置、设备和介质
CN114200924A (zh) * 2021-11-02 2022-03-18 深圳优地科技有限公司 一种路径规划方法、无人车及计算机可读存储介质
CN114440905B (zh) * 2022-01-28 2024-06-14 中国第一汽车股份有限公司 中间图层的构建方法、装置、电子设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101608926A (zh) * 2009-07-24 2009-12-23 厦门大学 多层次多模态寻径导航方法
CN101701830A (zh) * 2009-11-30 2010-05-05 四川虹微技术有限公司 一种导航终端的导航方法
CN103900596A (zh) * 2012-12-28 2014-07-02 环达电脑(上海)有限公司 基于路段的导航路径规划方法及其装置
WO2016159172A1 (ja) * 2015-03-31 2016-10-06 アイシン・エィ・ダブリュ株式会社 自動運転支援システム、自動運転支援方法及びコンピュータプログラム
CN106428007A (zh) * 2015-08-10 2017-02-22 现代自动车株式会社 车辆的自主行驶控制装置和自主行驶控制方法
CN107817000A (zh) * 2017-10-25 2018-03-20 广州汽车集团股份有限公司 无人驾驶车辆的路径规划方法、装置及计算机设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6356840B2 (en) * 1998-06-12 2002-03-12 Mitsubishi Denki Kabushiki Kaisha Navigation device with a three dimensional display
JP2006154538A (ja) * 2004-11-30 2006-06-15 Aisin Aw Co Ltd 地図描画方法、地図描画システム、ナビゲーション装置及び入出力装置
CN103471596A (zh) * 2012-06-08 2013-12-25 纽海信息技术（上海）有限公司 最短路径引导方法和最短路径引导系统
CN105043403B (zh) * 2015-08-13 2017-12-01 武汉光庭信息技术有限公司 高精度地图路线规划系统及方法
CN106469505B (zh) * 2015-08-20 2021-05-18 方正国际软件(北京)有限公司 一种浮动车轨迹纠偏方法和装置
JP6419666B2 (ja) * 2015-09-25 2018-11-07 日立オートモティブシステムズ株式会社 自動運転装置
CN105371859B (zh) * 2015-11-05 2018-05-08 武汉光庭信息技术股份有限公司 基于安全驾驶地图的车道级别的导航引导系统和方法
CN105588576B (zh) * 2015-12-15 2019-02-05 招商局重庆交通科研设计院有限公司 一种车道级导航方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101608926A (zh) * 2009-07-24 2009-12-23 厦门大学 多层次多模态寻径导航方法
CN101701830A (zh) * 2009-11-30 2010-05-05 四川虹微技术有限公司 一种导航终端的导航方法
CN103900596A (zh) * 2012-12-28 2014-07-02 环达电脑(上海)有限公司 基于路段的导航路径规划方法及其装置
WO2016159172A1 (ja) * 2015-03-31 2016-10-06 アイシン・エィ・ダブリュ株式会社 自動運転支援システム、自動運転支援方法及びコンピュータプログラム
CN106428007A (zh) * 2015-08-10 2017-02-22 现代自动车株式会社 车辆的自主行驶控制装置和自主行驶控制方法
CN107817000A (zh) * 2017-10-25 2018-03-20 广州汽车集团股份有限公司 无人驾驶车辆的路径规划方法、装置及计算机设备

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113434624A (zh) * 2021-07-27 2021-09-24 北京百度网讯科技有限公司 车辆的驾驶辅助方法、装置、设备、介质及程序产品
CN113434624B (zh) * 2021-07-27 2022-07-29 北京百度网讯科技有限公司 车辆的驾驶辅助方法、装置、设备、介质及程序产品
CN113778102A (zh) * 2021-09-22 2021-12-10 重庆长安汽车股份有限公司 Avp全局路径规划系统、方法、车辆及存储介质
CN113778102B (zh) * 2021-09-22 2023-05-12 重庆长安汽车股份有限公司 Avp全局路径规划系统、方法、车辆及存储介质

Also Published As

Publication number Publication date
CN107817000B (zh) 2020-09-08
US20210080267A1 (en) 2021-03-18
CN107817000A (zh) 2018-03-20

Similar Documents

Publication Publication Date Title
WO2019080781A1 (zh) 无人驾驶车辆的路径规划方法、装置及计算机设备
CN105043403B (zh) 高精度地图路线规划系统及方法
US9558660B1 (en) Method and apparatus for providing state classification for a travel segment with multi-modal speed profiles
US11047699B2 (en) Bloom filter multiple traffic-aware route decoding
US11755553B2 (en) Traffic-aware route decoding using a probabilistic encoding data structure
US20180149488A1 (en) Guide route setting apparatus and guide route setting method
EP3742123A1 (en) Bloom filter route encoding
EP3742122A1 (en) Decoding bloom-encoded shortest path routes from known start and target
US10989553B2 (en) Method, apparatus and computer program product for determining likelihood of a route
CN109579858B (zh) 导航数据处理方法、装置、设备及存储介质
CN105758410A (zh) 基于A‐Star 算法的快速路径规划混合方法
US11193779B2 (en) Decoding routes to pois in proximity searches using bloom filters
JPWO2018033957A1 (ja) ルート探索方法及びルート探索装置
US11054277B2 (en) Bloom filter multiple traffic-aware route encoding
Liu et al. Popular route planning with travel cost estimation
JP2015206725A (ja) 経路生成装置および経路生成方法
US11566911B2 (en) Encoding routes to POIs in proximity searches using bloom filters
JP2017102001A (ja) 経路探索装置及び経路探索方法
US20220082406A1 (en) System, method, and computer program product for identifying a road object
US11578989B2 (en) Encoding parking search cruise routes using bloom filters
US20200370917A1 (en) Decoding parking search cruise routes using bloom filters
León et al. Improvements of a topological map-matching algorithm in post-processing mode
Ali et al. Spatial big data for eco-routing services: computational challenges and accomplishments
US20240194056A1 (en) System and method for determining road work zone start location

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: 18871026

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: 18871026

Country of ref document: EP

Kind code of ref document: A1