WO2023071959A1 - 避障方法、装置、电子设备和存储介质 - Google Patents

避障方法、装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2023071959A1
WO2023071959A1 PCT/CN2022/126903 CN2022126903W WO2023071959A1 WO 2023071959 A1 WO2023071959 A1 WO 2023071959A1 CN 2022126903 W CN2022126903 W CN 2022126903W WO 2023071959 A1 WO2023071959 A1 WO 2023071959A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
obstacle
information
expansion
detection frame
Prior art date
Application number
PCT/CN2022/126903
Other languages
English (en)
French (fr)
Inventor
陈志新
陈博
尚秉旭
刘洋
王洪峰
张勇
金百鑫
何柳
Original Assignee
中国第一汽车股份有限公司
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
Priority claimed from CN202111247962.3A external-priority patent/CN113928340B/zh
Application filed by 中国第一汽车股份有限公司 filed Critical 中国第一汽车股份有限公司
Publication of WO2023071959A1 publication Critical patent/WO2023071959A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • B60W60/0016—Planning or execution of driving tasks specially adapted for safety of the vehicle or its occupants
    • 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, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • 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
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers

Definitions

  • the embodiments of the present application relate to the technical field of automatic driving, for example, to an obstacle avoidance method, device, electronic equipment and storage medium.
  • Autonomous driving can not only minimize the danger of driving a car, but also relieve users of heavy driving tasks.
  • the present application provides an obstacle avoidance method, device, electronic equipment and storage medium, so as to realize the planning of the obstacle avoidance driving path of the automatic driving vehicle, and improve the safety and reliability of automatic driving.
  • the embodiment of the present application provides an obstacle avoidance method applied to a vehicle, including:
  • the target obstacle-avoiding driving path is determined.
  • the embodiment of the present application also provides an obstacle avoidance device, which is applied to a vehicle, and the device includes:
  • the obstacle information acquisition module is configured to acquire target obstacle information within the preset area of the target vehicle
  • the expansion detection frame determination module is configured to determine the target expansion detection frame corresponding to the target obstacle information
  • the obstacle avoidance driving path determination module is configured to determine at least A driving path to be used for obstacle avoidance
  • the module for determining the target obstacle-avoiding driving path is configured to determine the target obstacle-avoiding driving path according to the relative position information between the discrete points in the obstacle-avoiding driving path to be used and the target expansion detection frame.
  • the embodiment of the present application also provides an electronic device, the device comprising:
  • memory device configured to store the program
  • the processor When the program is executed by the processor, the processor implements the obstacle avoidance method described in any one of the embodiments of the present application.
  • the embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements any one of the embodiments of the present application.
  • FIG. 1 is a flow chart of an obstacle avoidance method provided in Embodiment 1 of the present application.
  • FIG. 2 is a flow chart of an obstacle avoidance method provided in Embodiment 2 of the present application.
  • FIG. 3 is a flow chart of an obstacle avoidance method provided in Embodiment 3 of the present application.
  • FIG. 4 is a schematic diagram of an obstacle avoidance method provided in Embodiment 3 of the present application.
  • FIG. 5 is a schematic diagram of an obstacle avoidance method provided in Embodiment 3 of the present application.
  • FIG. 6 is a schematic diagram of an obstacle avoidance method provided in Embodiment 3 of the present application.
  • FIG. 7 is a structural block diagram of an obstacle avoidance device provided in Embodiment 4 of the present application.
  • FIG. 8 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application.
  • Fig. 1 is a flow chart of an obstacle avoidance method provided in Embodiment 1 of the present application.
  • This embodiment is applicable to planning the obstacle avoidance driving route of an automatic driving vehicle, thereby improving the safety of automatic driving.
  • This method can be implemented by the present application
  • the obstacle avoidance device in the embodiment is implemented, and the device can be implemented by means of software and/or hardware.
  • it can be implemented by electronic equipment, which can be a mobile terminal, a computer (Personal Computer, PC) or server side etc.
  • the device can be configured in a computing device.
  • the obstacle avoidance method applied to a vehicle provided in this embodiment specifically includes the following steps:
  • the target vehicle refers to the vehicle that needs to perform obstacle avoidance operation during automatic driving, and all vehicles that need to perform automatic obstacle avoidance can be considered as target vehicles.
  • the preset area of the target vehicle can be understood as a pre-set area for monitoring roadblocks based on the target vehicle's own information.
  • the vehicle's own information can be body length, body width, vehicle position, or vehicle speed.
  • the target obstacle can be understood as the roadblock information that appears within the preset area of the target vehicle, which can be a vehicle, tree stump, or warning sign, etc.
  • the target obstacle information can be understood as the information of the target obstacle obtained according to the perception results of the vehicle equipment , the vehicle device may be a sensor device, and the target obstacle information may be information such as the position, length, width, or speed of the obstacle.
  • the vehicle sensor can be used to monitor the preset area of the target vehicle, and the target obstacle is detected within the range of the area, and the information of the target obstacle within the preset area of the target vehicle is collected through the sensor device. It is used to perceive the surrounding environment of the vehicle, locate the vehicle and obtain the status of the vehicle.
  • Sensor devices include cameras, lidar, Global Positioning System (Global Positioning System, GPS), speed sensors, steering wheel angle sensors, and front wheel angle sensors.
  • the preset area of the target vehicle is affected by changes in the current position of the target vehicle and the detected obstacle area.
  • the current position of the target vehicle can be understood as the position of a positioning point during the driving process of the vehicle, which can be obtained by the vehicle positioning device.
  • the positioning device can be GPS
  • the detection obstacle area can be understood as the area information of the sensor detecting the obstacle.
  • This area can be It is a preset specific area, which can be an area of 2 meters (m)*2 meters (m), or an area of 3m*2m.
  • the preset area information of the target vehicle can be updated in real time.
  • the target obstacle can be selected from many obstacles, for example, after obtaining all obstacle information in the preset area of the target vehicle, the The obstacle information is screened, for example, it can be judged whether the attribute information of the obstacle satisfies the obstacle attribute information of the vehicle to avoid, for example, the speed information of the obstacle to be avoided by the vehicle needs to be lower than a threshold speed, and the preset area of the target vehicle can be judged Whether the speed of the obstacle in the target vehicle is lower than the threshold speed, based on the judgment result that the speed of the obstacle in the preset area of the target vehicle is lower than the above threshold speed, the obstacle can be used as an obstacle for the vehicle to avoid.
  • the obstacle is not an obstacle for the vehicle to avoid, and then the obstacle for the vehicle to avoid is determined, and the obstacle for the vehicle to avoid can be used as the target obstacle.
  • the acquiring target obstacle information within a preset area of the target vehicle includes: determining a preset location associated with the target vehicle according to the current position information of the target vehicle and a preset detection area range. Obstacles to be processed within the area; according to the attribute information of the obstacles to be processed, target obstacle information is determined from the obstacles to be processed.
  • any positioning point acquired by the positioning device during vehicle driving can be used as the current position of the target vehicle, and then the current position information can be obtained.
  • the current position information can be the longitude, latitude or heading angle of the current vehicle positioning point information etc.
  • the detection area range refers to the area around the vehicle used to detect obstacles.
  • the detection area range can be determined by setting the detection area size in advance. For example, when the length of the area size is 1m and the width is 1m, the detection area range can be 1m* The range of the area constituted by 1m. According to the current location information of the target vehicle and the preset detection area range, the preset area of the target vehicle can be determined. The preset area of the target vehicle can change with the current position of the target vehicle.
  • the size of the preset area is 1m* 1m
  • the preset area of the target vehicle is a 1m*1m area centered on point A
  • the preset area of the target vehicle is An area of 1m*1m centered on point B.
  • the target obstacle can be understood as the obstacle that the target vehicle needs to perform an avoidance operation and must meet the preset obstacle attribute conditions. It can appear within the preset area associated with the target vehicle and meet the preset obstacle attribute conditions. objects as target obstacles.
  • the preset obstacle attribute condition can be a preset condition that satisfies the attribute information of the obstacle that the target vehicle performs an avoidance operation.
  • the obstacle attribute condition can be that the speed information of the obstacle is lower than a preset speed, or that the obstacle position is within
  • the position at a set distance in front of the target vehicle can also be that the obstacle position information is within the preset area associated with the target vehicle, or an obstacle to be processed that satisfies at least two preset obstacle attribute conditions can also be used as the target obstacle thing.
  • the target expansion detection frame can be understood as a rectangular frame obtained by expanding the attribute information of the target obstacle based on the expansion width.
  • the rectangular frame is composed of the expanded length and width of the target obstacle.
  • the attribute information of the target obstacle can be the target
  • the length information and width information of the obstacle can be understood as the expansion width information set based on the length and width information of the target obstacle itself
  • the expansion width can include the horizontal expansion width and the longitudinal expansion width
  • the horizontal expansion width can be understood as the target obstacle
  • the vertical expansion width can be understood as the expansion size of the target obstacle on the basis of its own length
  • the target expansion detection frame of the target obstacle can be determined according to the horizontal expansion width and the vertical expansion width, for example,
  • the target obstacle is a parked vehicle on the road, the length of the vehicle is 2m, the width is 1m, the horizontal expansion width of the expansion width is 0.6m, and the longitudinal expansion width is 4m, then the length of the target expansion detection frame of the target obstacle is
  • the expansion attribute information of the expansion width can be set in advance, and then the horizontal expansion width and the vertical expansion width information of the expansion width can be determined, and the target obstacle information can be processed.
  • the horizontal expansion width can be added to the width of the target obstacle
  • the vertical expansion width can be added to the length of the target obstacle, and then the target expansion detection frame of the target obstacle can be determined.
  • the determining the target expansion detection frame corresponding to the target obstacle information includes: performing expansion processing on the target obstacle information according to preset expansion attribute information to obtain the target obstacle information corresponding to Object dilation detection box.
  • the expansion attribute information can be understood as the horizontal expansion width information and the vertical expansion width information of the expansion width.
  • the target obstacle information is expanded according to the length and width information of the target obstacle.
  • the expansion process It can be to expand the width of the target obstacle, that is, to add the horizontal expansion width to the width of the target obstacle to obtain the expanded width of the target obstacle, or to expand the length of the target obstacle, that is, to add the vertical expansion width to
  • the length of the upper target obstacle is the expanded length of the target obstacle.
  • the target obstacle is a parked vehicle on the road, the length of the vehicle is 2m, and the width is 1m.
  • the initial value of the expansion width is 0.6m in the lateral expansion width, and 4m in the longitudinal expansion width.
  • the expansion process for the length of the vehicle can be The length of the vehicle plus two longitudinal expansion widths, that is, the length of the vehicle after expansion is 10m, and the expansion process for the width of the vehicle can be processed by adding two transverse expansion widths to the width of the vehicle, that is, the vehicle after expansion If the length is 2.2m, the length of the target expansion detection frame of the target obstacle is 10m, and the width is 2.2m, and the target expansion detection frame corresponding to the target obstacle information is obtained, which improves the safety of automatic driving vehicle obstacle avoidance.
  • the target expansion detection frame corresponding to the target obstacle information can be determined according to the preset expansion attribute information, and the expansion attribute information can also be updated to obtain the target expansion detection frame of the target obstacle.
  • the initial value of the horizontal expansion width information or the longitudinal expansion width information of the expansion attribute information is set greater than a preset threshold, the target expansion detection frame obtained by the expansion processing of the target obstacle will exceed the threshold range, causing the target vehicle to be in the When driving on the lane for obstacle avoidance, the obstacle avoidance track route will be planned at a long distance, which wastes the driving time of the vehicle. Therefore, the expansion attribute information can be reduced by a threshold.
  • the target expansion detection frame obtained by the expansion processing of the target obstacle is less than a threshold value range, causing the target vehicle to be in the When driving on the lane for obstacle avoidance, the obstacle avoidance trajectory is planned at a short distance, and the target vehicle may collide with obstacles easily. Therefore, the expansion attribute information can be increased by a threshold.
  • the final target expansion detection frame can be obtained by updating the expansion attribute information.
  • the determining the target expansion detection frame corresponding to the target obstacle information further includes: when a request for updating the expansion attribute information is received, determining the expansion attribute information to be updated corresponding to the update request, And update the target expansion detection frame corresponding to the target obstacle information according to the expansion attribute information to be updated.
  • the update request can be understood as an update request for the expansion attribute information of the target expansion detection frame. For example, it may be that when the determined expansion width of the target expansion detection frame is greater than the minimum preset threshold according to the preset expansion attribute information, an update request for the expansion width may be triggered, or it may be that according to the preset expansion attribute information.
  • a request for updating the expansion width may be triggered, that is, a request for updating the expansion attribute information of the expansion width may be triggered.
  • the expansion property information to be updated can be understood as a triggered update request requesting to update the expansion property information of the expansion width, which can be the horizontal expansion width information of the expansion width, or the vertical expansion width information of the expansion width.
  • the minimum threshold can be preset for the lateral expansion width and the longitudinal expansion width. Assume that the minimum threshold of the lateral expansion width is 0.3m, and the minimum threshold of the longitudinal expansion width is 1m.
  • the expansion property information for reducing the expansion width can be requested, and the expansion property information to be reduced can be used as the expansion property information to be updated, and the expansion property can be
  • the information is reduced by a certain amount of preset values, for example, the horizontal expansion width of the target expansion detection frame can be reduced by 0.05m, and the vertical expansion width can be reduced by 0.1m, and a new target expansion detection frame can be determined according to the reduced horizontal expansion width and vertical expansion width , taking the new target expansion detection frame as the final target expansion detection frame, correspondingly, the final target expansion detection frame corresponding to the target obstacle information can be determined, that is, update the target obstacle information according to the expansion attribute information to be updated.
  • the corresponding target expansion detection frame improves the reliability of automatic driving obstacle avoidance.
  • S130 Determine at least one to-be-used obstacle avoidance driving path corresponding to the target vehicle according to the target expansion detection frame, the current position information of the target vehicle, and the lane boundary line information of the road to which the target vehicle belongs.
  • the lane boundary line can be understood as the boundary line of the road where the target vehicle is driving.
  • the road conditions of the target vehicle can be monitored through the sensor equipment.
  • the left and right lane boundary line information of the target vehicle driving road can be obtained.
  • the boundary line information may be the coordinate information of the boundary points on the boundary line of the lane, or the heading angle information of the boundary points on the boundary line.
  • Lane boundary line markers can be boundary markings on the road, side ditches, curbs or guardrails or pillars and other structural markers. For example, when the vehicle sensor device detects the lane markings on the road where the target vehicle is driving, the lane boundary can be determined In turn, the coordinate information and heading information of the boundary points on the boundary line can be obtained through the sensor device.
  • the obstacle avoidance driving path can be understood as the driving route planned by the target vehicle when avoiding obstacles, and can be determined according to the target expansion detection frame of the obstacle, the current position information of the target vehicle, and the lane boundary information of the road to which the target vehicle belongs. At least one obstacle-avoiding driving path of the target vehicle, and the obtained obstacle-avoiding driving path is used as the obstacle-avoiding driving path to be used. If the location does not exceed the lane boundary line of the driving road and is driving outside the target expansion detection frame of the obstacle, there may be one or more obstacle avoidance driving paths.
  • the minimum distance between the target expansion detection frame of the obstacle and the lane boundary line can be calculated, and the distance information of the calculated minimum distance and the point on the target expansion detection frame can be calculated
  • Determine the information of a track point in the obstacle avoidance driving path based on the location information of for example, by calculating the distance from all vertices in the target expansion detection frame to the lane boundary line, determine the minimum distance from all vertices to the lane boundary line, that is, get the target expansion
  • the minimum distance between the detection frame and the lane boundary line can determine a track point in the obstacle avoidance driving path according to the obtained minimum distance line and the corresponding vertex information of the minimum distance, and this track point can be used as the first driving discrete point.
  • an obstacle-avoiding driving route can be determined according to the current position information of the target vehicle and the first driving discrete point, and can also be determined according to the position information of the first driving discrete point and the left and right lane boundaries
  • the line information determines another track point information in the obstacle avoidance driving path.
  • the preset driving mileage of the target vehicle can be determined according to the preset speed and preset duration information of the target vehicle, and the position of the first discrete driving point is used as the starting point.
  • the driving arrival position is taken as the end point
  • the obstacle avoidance driving path can be determined according to the left and right lane boundary line information and the end position information of the vehicle driving road.
  • Another track point information of as the second driving discrete point.
  • multiple obstacle avoidance driving routes can be planned for the target vehicle during obstacle avoidance driving.
  • the current position information of the target vehicle, and the lane boundary line information of the road to which the target vehicle belongs determine at least one obstacle-avoiding driving path corresponding to the target vehicle to be used, Including: determining all vertices in the target expansion detection frame according to the target expansion detection frame; determining a minimum distance according to the distance from all vertices in the target expansion detection frame to the first boundary line in the lane boundary line information, and determining the minimum distance according to the minimum The distance corresponds to the vertex corresponding to the minimum distance, and the first discrete point of travel is determined; the second discrete point of travel is determined according to the first discrete point of travel, lane boundary line information, preset speed information and preset duration information of the target vehicle ; Determine at least one obstacle-avoiding driving route to be used according to the current position information of the target vehicle, the first driving discrete point information and the second driving discrete point information.
  • All vertices in the target expansion detection frame can be understood as the vertex information of a rectangular frame composed of the length and width of the target expansion detection frame.
  • the position information of the target obstacle can be obtained through the vehicle sensor device, and the target obstacle can be obtained by expanding the target obstacle.
  • the position information of the target expansion detection frame and then obtain the four vertex information of the target expansion detection frame.
  • the first boundary line can be understood as any one of the left and right lane boundary lines of the lane to which the target vehicle belongs, which can be the left lane boundary line of the lane or the right lane boundary line of the lane.
  • the lane boundary lines used are all the same lane boundary line, for example, both use the left lane boundary line or both use the right lane boundary line.
  • the minimum distance can be understood as the distance information with the smallest distance value from all vertices in the target expansion detection frame to the first boundary line in the lane boundary line information.
  • the first driving discrete point can be understood as the point on the closest distance line between the target expansion detection frame corresponding to the target obstacle and the first boundary line in the lane boundary line, and the first driving discrete point information can be the coordinate position of the first driving discrete point
  • the information may also be heading angle information of the first discrete point of travel.
  • the first boundary line is a curved curve, which can be expressed by mathematical equations, and all vertices can be expressed by position coordinates, and the distance from all vertices to the first boundary line can be calculated to obtain the corresponding distance of each vertex, and all The distance with the smallest value among the distances is taken as the minimum distance.
  • the vertex of the target expansion detection frame corresponding to the minimum distance can be obtained, and there is a minimum distance line between the vertex and a boundary point on the first boundary line.
  • the vertex corresponding to the minimum distance can be transferred to The center point on the minimum distance route of the first boundary line is used as the first discrete point of travel, and then the information of the first discrete point of travel is determined.
  • the preset speed information can be understood as preset speed information, and the driving speed of the target vehicle during obstacle avoidance can be used as the preset speed.
  • the maximum The speed limit value is 10 meters per second (m/s) as the preset speed
  • the vehicle obstacle avoidance speed limit lower than the threshold can be set as the preset speed, for example, at the expansion width
  • the vehicle obstacle avoidance speed limit of 3m/s can be used as the preset speed.
  • the preset duration information is understood as preset duration information, which may be 1 second (s) or 1.5s.
  • the second discrete point of travel can be understood as the position at the center point of the lane where the estimated mileage is traveled from the first discrete point of travel to the front of the vehicle.
  • the information of the first discrete point of travel can be the coordinate position information of the first discrete point of travel, or it can be the first The heading angle information of a traveling discrete point.
  • the first discrete point of travel can be used as the starting point of the target vehicle, and the estimated mileage of the target vehicle can be determined according to the preset speed information and preset duration information of the target vehicle, and then the destination of the target vehicle can be determined to obtain the Correspondingly, according to the position information of the target vehicle's travel end point and the center point of the left and right lane boundary lines of the road to which the target vehicle belongs, the position information of the second discrete point of travel can be obtained, and then, A second travel discrete point is determined.
  • the information of the first discrete point of travel and the information of the second discrete point of travel can be planned, and the planned obstacle-avoiding driving paths can be used as the obstacle-avoiding driving paths to be used , which improves the safety and reliability of the target vehicle driving on the obstacle avoidance path.
  • S140 Determine a target obstacle-avoiding driving path according to relative position information between discrete points in the obstacle-avoiding driving path to be used and the target expansion detection frame.
  • the obstacle avoidance driving path to be used can be composed of countless coordinate points, and the positioning points in the obstacle avoidance driving path to be used can be used as discrete points, for example, the longitude of the positioning points in the obstacle avoidance driving path to be used can be obtained through vehicle sensing equipment , latitude or heading angle information, not only the information of discrete points is obtained.
  • the relative position information can be understood as the position information between the discrete point in the obstacle avoidance driving path and the target expansion detection frame.
  • the position information can be distance information, heading angle information or coordinate information, etc.
  • the target expansion detection frame can be calculated by
  • the distance between all the vertices in the target and the discrete points in the obstacle-avoiding driving path to be used can be obtained by multiple distance information, and the distance information can be used as the relative distance information.
  • the angle between the discrete points in the center can obtain multiple heading angle information, and the heading angle information can be used as the relative heading angle information, and the relative distance information or the relative heading angle information can be used as the relative position information.
  • the target obstacle avoidance driving path can be understood as an obstacle avoidance driving path that satisfies preset conditions in the obstacle avoidance driving path to be used. It can be one or more.
  • the relative distance between the target expansion detection frames satisfies a preset distance value, and may also be the relative heading angle information between the discrete points in the obstacle avoidance driving path to be used and the target expansion detection frames.
  • a preset distance value e.g., a preset 0.05
  • it can be Setting the width of the target vehicle itself as the threshold value, the distance between the discrete points in the obstacle avoidance driving path to be used and all vertices of the target expansion detection frame is greater than the width of the target vehicle itself, and the obstacle avoidance driving path to be used can be used as the target obstacle avoidance driving path.
  • the target obstacle information within the preset area of the target vehicle is acquired, the target expansion detection frame corresponding to the target obstacle information is determined through the preset expansion attribute information, and the first obstacle avoidance detection frame is used in the obstacle avoidance driving route through calculation.
  • the traveling discrete point and the second traveling discrete point, and the current position information of the target vehicle determine at least one obstacle-avoiding driving path corresponding to the target vehicle, according to the distance between the discrete point in the obstacle-avoiding driving path to be used and the target expansion detection frame
  • the relative position information of the target vehicle is determined to determine the target obstacle avoidance driving path of the target vehicle in the process of obstacle avoidance driving.
  • this embodiment determines the corresponding target obstacle information by using the expansion width for the target obstacle.
  • the target expansion detection frame detects the relative position information between the discrete points in the obstacle avoidance driving path and the target expansion detection frame, so that the target vehicle can accurately plan the target obstacle avoidance driving path during the automatic obstacle avoidance driving process, Prevent the target vehicle from colliding with obstacles, reduce the occurrence of traffic accidents, and improve the safety and reliability of automatic driving vehicles when avoiding obstacles.
  • FIG. 2 is a flow chart of an obstacle avoidance method provided in Embodiment 2 of the present application.
  • this embodiment modifies the technical solution.
  • the target avoidance The obstacle driving path includes: for the target expansion detection frame, determining the distance information from all vertices in the current target expansion detection frame to each discrete point in the current obstacle avoidance driving path; As a result of judging the width information in the direction, it is determined that the currently to-be-used obstacle-avoiding driving path is the target obstacle-avoiding driving path.
  • the method of this embodiment includes the following steps:
  • S230 Determine at least one to-be-used obstacle avoidance driving path corresponding to the target vehicle according to the target expansion detection frame, the current position information of the target vehicle, and the lane boundary line information of the road to which the target vehicle belongs.
  • the target expansion detection frame determine distance information from all vertices in the current target expansion detection frame to each discrete point in the current obstacle avoidance driving path; based on all the distance information being greater than the target vehicle in the vertical direction According to the determination result of the width information, the currently to-be-used obstacle-avoiding driving path is determined as the target obstacle-avoiding driving path.
  • the current target expansion detection frame can be understood as when determining all the vertices corresponding to the target expansion detection frame, the vertices of any target expansion detection frame can be determined as the vertices for determining the current target expansion detection frame, for example, the target expansion can be determined
  • the coordinate position information or heading angle information of all vertices corresponding to the detection frame is used to illustrate that one of the target expansion detection frames is used as the current target expansion detection frame.
  • any discrete point of the obstacle avoidance travel route to be used may also be determined as the discrete point for determining the current obstacle avoidance travel route to be used, such as, Coordinate position information or heading angle information of discrete points in the to-be-used obstacle-avoiding driving paths may be determined to describe one of the to-be-used obstacle-avoiding driving paths as the current to-be-used obstacle-avoiding driving path.
  • the distance information can be understood as the distance from all vertices in the current target expansion detection frame to each discrete point in the current obstacle avoidance driving path, and at least one distance information can be obtained.
  • the coordinate position information of all vertices in the target expansion detection frame and the coordinate position information of each discrete point in the obstacle avoidance driving path to be used can be obtained according to the vehicle sensor device, and the relationship between all vertices in the target expansion detection frame and the current to-be-used driving path can be calculated. Use the distance of each discrete point in the obstacle avoidance driving path, and use all the calculated distances as distance information.
  • the width information of the target vehicle in the vertical direction can be understood as calculating the body width information of the target vehicle perpendicular to the driving direction of the vehicle in a space of set dimensions, and the dimension can be two-dimensional or three-dimensional.
  • the width information of the target vehicle in the vertical direction may be body width information of the target vehicle.
  • the target obstacle avoidance driving path can be understood as an obstacle avoidance driving path that satisfies the preset condition of the vehicle obstacle avoidance driving among the multiple obstacle avoidance driving paths to be used.
  • the preset condition of the vehicle obstacle avoidance driving can be the target expansion detection of the obstacle A condition that the distance between all vertices on the frame and each discrete point in the obstacle avoidance driving path to be used is greater than a preset threshold.
  • the body width of the target vehicle can be used as a preset threshold, and all vertices in the target expansion detection frame can be detected to match the current obstacle avoidance path to be used.
  • the current obstacle avoidance driving path to be used can be used as the target obstacle avoidance driving path.
  • the target expansion detection frame determine the distance information from all vertices in the current target expansion detection frame to each discrete point in the current obstacle avoidance driving path.
  • the distance of the width information in the vertical direction for example, in practical applications, if the distance information in all distance information is not greater than the distance of the width information of the target vehicle in the vertical direction, the target vehicle is currently driving on the obstacle avoidance path to be used , there may be consequences for the expansion of the vehicle and the obstacle. It may be that the initial pre-set expansion attribute information is too large, causing the problem that the target expansion detection frame corresponding to the determined target obstacle to be processed is unreasonable. You can send a request to the system to update the expansion attribute information corresponding to the target obstacle information.
  • the preset inflation attribute information can be reduced by a threshold to obtain new inflation attribute information, that is, update the inflation attribute information, and then determine the inflation attribute corresponding to the update request to be updated information, and update the target expansion detection frame corresponding to the target obstacle information according to the expansion attribute information to be updated, and re-determine the target obstacle avoidance driving path corresponding to the target vehicle.
  • the current obstacle avoidance driving path to be used is not the target obstacle avoidance path; Based on the judgment result that all the obstacle-avoiding driving paths to be used are not the target obstacle-avoiding driving paths, update the expansion attribute information corresponding to the target obstacle information, so as to re-determine the relationship with the target based on the updated expansion attribute information.
  • the corresponding target obstacle avoidance driving path of the vehicle is not based on the judgment result that the distance information in all the distance information is not greater than the width information of the target vehicle in the vertical direction.
  • the distance information in the distance information is not greater than the distance of the width information of the target vehicle in the vertical direction, it can be determined that the current obstacle avoidance driving path to be used is not the target obstacle avoidance path.
  • the current target expansion detection frame corresponds to Whether the expansion width of the target obstacle is the minimum threshold width, based on the judgment result that the expansion width of the target obstacle corresponding to the current target expansion detection frame is the minimum threshold width, it can be determined that the current obstacle avoidance driving path to be used is not the target obstacle avoidance path, It is not necessary to update the expansion attribute information operation of the expansion width.
  • the longitudinal obstacle avoidance path can be planned, wherein the longitudinal obstacle avoidance path can be understood as the relationship between each discrete point on the target expansion detection frame corresponding to the target obstacle and the current position of the target vehicle Based on the judgment result that the expansion width of the target obstacle corresponding to the current target expansion detection frame is not the minimum threshold width, it can also be determined that the current obstacle avoidance driving path to be used is not the target obstacle avoidance path, but there may be an initial pre-determined If the expansion attribute information of the set expansion width is too large, at this time, a request to update the expansion attribute information can be triggered, and then, when the system receives the request to update the expansion attribute information, the expansion attribute corresponding to the target obstacle information can be The information is updated.
  • the expansion width is reduced by a certain set threshold, for example, the horizontal expansion width is reduced by 0.05m, and the vertical expansion width is reduced by 0.1m.
  • the target expansion detection frame corresponding to the target obstacle information is updated, and the target obstacle-avoiding driving path corresponding to the target vehicle is re-determined.
  • the expansion width of the target obstacle corresponding to the target expansion detection frame is the minimum threshold width, based on the target expansion detection frame corresponding to The judgment result that the expansion width of the target obstacle is the minimum threshold width, optionally, the longitudinal obstacle avoidance path can be planned, and based on the judgment result that the expansion width of the target obstacle corresponding to the target expansion detection frame is not the minimum threshold width, update and target The expansion attribute information corresponding to the obstacle information, and then update the target expansion detection frame corresponding to the target obstacle information, re-determine the target obstacle-avoiding driving path corresponding to the target vehicle, and improve the accuracy and accuracy of planning the obstacle-avoiding driving path. safety.
  • the target obstacle information within the preset area of the target vehicle is acquired, the target expansion detection frame corresponding to the target obstacle information is determined through the preset expansion attribute information, and the first obstacle avoidance detection frame is used in the obstacle avoidance driving route through calculation.
  • the traveling discrete point and the second traveling discrete point, and the current position information of the target vehicle determine at least one obstacle-avoiding driving path corresponding to the target vehicle, according to the distance between the discrete point in the obstacle-avoiding driving path to be used and the target expansion detection frame
  • the relative position information of the target vehicle is determined to determine the target obstacle avoidance driving path of the target vehicle in the process of obstacle avoidance driving.
  • this embodiment determines the corresponding target obstacle information by using the expansion width for the target obstacle.
  • the target expansion detection frame detects the relative position information between the discrete points in the obstacle avoidance driving path and the target expansion detection frame, so that the target vehicle can accurately plan the target obstacle avoidance driving path during the automatic obstacle avoidance driving process, Prevent the target vehicle from colliding with obstacles, reduce the occurrence of traffic accidents, and improve the safety and reliability of automatic driving vehicles when avoiding obstacles.
  • FIG. 3 is a schematic flowchart of an obstacle avoidance method provided in Embodiment 3 of the present application.
  • an obstacle avoidance method provided by Embodiment 3 of the present application can obtain information such as the position, length, width, and speed of obstacles based on the perception results of the vehicle sensors by acquiring information about obstacles around the target vehicle. Furthermore, based on conditions such as the speed of the obstacle being less than a set threshold, the position of the obstacle in front of the target vehicle, or the obstacle being within a preset area associated with the target vehicle, the static obstacles around the driving path of the target vehicle are screened out, and according to the preset
  • the expansion attribute information of the expansion width is set.
  • the expansion width is initially set to the initial value. Generally, the initial value of the expansion width is 0.6m for the horizontal expansion width and 4m for the vertical expansion width.
  • Calculate the expansion width of the obstacle, and for the screened obstacles Perform expansion processing to obtain the target expansion detection frame corresponding to the target obstacle information, and plan the obstacle avoidance path and speed of the target vehicle.
  • set the maximum speed limit of the target vehicle during obstacle avoidance Generally, on urban roads It can be set to 10m/s while driving.
  • set a lower speed limit for obstacle avoidance of the target vehicle Generally, when the lateral distance of the expansion width is less than 0.4m, the speed limit of the target vehicle can be set to 3m/s.
  • the distance of the planned obstacle avoidance path is greater than the width of the target vehicle itself by calculating the distance of the four vertices after the expansion of the obstacle. Judgment result, it is judged that the obstacle will not collide, that is, the obstacle can be avoided in this lane, and the target obstacle avoidance driving path can be planned; based on the judgment result that the above distance is not greater than the width of the target vehicle itself, it is judged whether the current expansion width is the minimum set threshold , based on the judgment result that the current expansion width is the minimum set threshold, plan the longitudinal obstacle avoidance path, and based on the judgment result that the current expansion width is not the minimum set threshold, send a request to reduce the expansion width, then the expansion width is reduced by a certain value, generally Reduce horizontally by 0.05m and vertically by 0.1m, and then re-update the expansion attribute information, calculate the expansion width of the obstacle, and determine the target expansion detection frame corresponding to the target
  • the content of the obstacle avoidance method is shown in FIG. 4 .
  • the target vehicle 410 detects an obstacle 430 ahead when it is driving normally.
  • the target obstacle is expanded to obtain The target expansion detection frame corresponding to the obstacle, refer to box 1 for the target expansion detection frame, and then determine the minimum distance according to the distance from all vertices in the target expansion detection frame to the lane boundary line, and according to the minimum distance and the corresponding vertex of the minimum distance, Determine the first discrete point of travel, this point is point M, then, according to the first discrete point of travel, lane boundary line information, preset speed information and preset duration information of the target vehicle, determine the second discrete point of travel, this point is Point N, and furthermore, according to the current position information of the target vehicle, the information of the first discrete point of travel and the information of the second discrete point of travel, a path to be used for obstacle avoidance is determined, the path is O-M-N, and the target vehicle 420 for obstacle avoid
  • the content of the obstacle avoidance method is shown in Figure 5.
  • an expansion attribute for updating the expansion width can be issued
  • the request for information will reduce the expansion width of the target obstacle 530, that is, reduce the lateral expansion and reduce the longitudinal expansion, and obtain the target expansion detection frame of the target obstacle after reduction.
  • the target vehicle 520 of can avoid obstacles according to the obstacle avoidance driving route.
  • the content of the obstacle avoidance method is shown in Figure 6, judging whether the current expansion width is the minimum horizontal expansion and the minimum longitudinal expansion, and planning the vertical obstacle avoidance path based on the judgment result that the current expansion width is the minimum horizontal expansion and the minimum longitudinal expansion , the longitudinal obstacle avoidance path is the path from the point Q on the centerline of the lane at the closest distance between the obstacle 620 and the target vehicle 610 to the current position O of the target vehicle, the path is O-Q, based on the fact that the current expansion width is not the minimum lateral expansion and the minimum longitudinal expansion According to the judgment result, a request to reduce the expansion width is issued, the expansion attribute information is updated, and the obstacle avoidance path is re-planned.
  • the target obstacle information within the preset area of the target vehicle is acquired, the target expansion detection frame corresponding to the target obstacle information is determined through the preset expansion attribute information, and the first obstacle avoidance detection frame is used in the obstacle avoidance driving route through calculation.
  • the traveling discrete point and the second traveling discrete point, and the current position information of the target vehicle determine at least one obstacle-avoiding driving path corresponding to the target vehicle, according to the distance between the discrete point in the obstacle-avoiding driving path to be used and the target expansion detection frame
  • the relative position information of the target vehicle is determined to determine the target obstacle avoidance driving path of the target vehicle in the process of obstacle avoidance driving.
  • this embodiment determines the corresponding target obstacle information by using the expansion width for the target obstacle.
  • the target expansion detection frame detects the relative position information between the discrete points in the obstacle avoidance driving path and the target expansion detection frame, so that the target vehicle can accurately plan the target obstacle avoidance driving path during the automatic obstacle avoidance driving process, Prevent the target vehicle from colliding with obstacles, reduce the occurrence of traffic accidents, and improve the safety and reliability of automatic driving vehicles when avoiding obstacles.
  • FIG. 7 is a structural block diagram of an obstacle avoidance device provided in Embodiment 4 of the present application.
  • the device includes: an obstacle information acquisition module 710 , an expansion detection frame determination module 520 , an obstacle avoidance driving route determination module 730 and a target obstacle avoidance driving route determination module 740 .
  • the obstacle information acquisition module 710 is configured to acquire target obstacle information within the preset area of the target vehicle
  • the expansion detection frame determination module 720 is configured to determine the target expansion detection frame corresponding to the target obstacle information
  • the obstacle avoidance driving path determination module 730 is configured to determine the path corresponding to the target vehicle according to the target expansion detection frame, the current position information of the target vehicle, and the lane boundary line information of the road to which the target vehicle belongs. At least one obstacle avoidance driving path to be used;
  • the target obstacle-avoiding driving path determination module 740 is configured to determine the target obstacle-avoiding driving path according to the relative position information between the discrete points in the obstacle-avoiding driving path to be used and the target expansion detection frame.
  • the target obstacle information within the preset area of the target vehicle is acquired, the target expansion detection frame corresponding to the target obstacle information is determined through the preset expansion attribute information, and the first obstacle avoidance detection frame is used in the obstacle avoidance driving route through calculation.
  • the traveling discrete point and the second traveling discrete point, and the current position information of the target vehicle determine at least one obstacle-avoiding driving path corresponding to the target vehicle, according to the distance between the discrete point in the obstacle-avoiding driving path to be used and the target expansion detection frame
  • the relative position information of the target vehicle is determined to determine the target obstacle avoidance driving path of the target vehicle in the process of obstacle avoidance driving.
  • this embodiment determines the corresponding target obstacle information by using the expansion width for the target obstacle.
  • the target expansion detection frame detects the relative position information between the discrete points in the obstacle avoidance driving path and the target expansion detection frame, so that the target vehicle can accurately plan the target obstacle avoidance driving path during the automatic obstacle avoidance driving process, Prevent the target vehicle from colliding with obstacles, reduce the occurrence of traffic accidents, and improve the safety and reliability of automatic driving vehicles when avoiding obstacles.
  • the obstacle information acquisition module 710 includes:
  • the obstacle to be processed determining unit is configured to determine the obstacle to be processed within the preset area associated with the target vehicle according to the current position information of the target vehicle and the preset detection area;
  • the target obstacle information determining unit is configured to determine the target obstacle information from the obstacles to be processed according to the attribute information of the obstacles to be processed.
  • the expansion detection frame determination module 720 includes:
  • the target expansion detection frame determination unit is configured to perform expansion processing on the target obstacle information according to the preset expansion attribute information to obtain a target expansion detection frame corresponding to the target obstacle information.
  • the target expansion detection frame determining unit is further configured to, in the case of receiving an update request for expansion attribute information, determine the expansion attribute information corresponding to the update request, and update the expansion attribute information corresponding to the update request and the target according to the expansion attribute information to be updated.
  • the obstacle avoidance driving route determination module 730 includes:
  • a vertex determination unit configured to determine all vertices in the target expansion detection frame according to the target expansion detection frame
  • the first driving discrete point determination unit is configured to determine the minimum distance according to the distances from all vertices in the target expansion detection frame to the first boundary line in the lane boundary line information, and determine the minimum distance according to the minimum distance and the minimum The vertex corresponding to the distance is used to determine the first discrete point of travel;
  • the second discrete point of travel determination unit is configured to determine a second discrete point of travel according to the first discrete point of travel, lane boundary information, preset speed information and preset duration information of the target vehicle;
  • the to-be-used obstacle-avoiding driving route determining unit is configured to determine at least one to-be-used obstacle-avoiding driving route according to the current position information of the target vehicle, the first traveling discrete point information and the second traveling discrete point information.
  • the target obstacle avoidance driving route determination module 740 includes:
  • the distance information determination unit is configured to determine, for the target expansion detection frame, distance information from all vertices in the current target expansion detection frame to each discrete point in the current obstacle avoidance driving path to be used;
  • the target obstacle-avoiding driving path determination unit is configured to determine that the currently to-be-used obstacle-avoiding driving path is the target obstacle-avoiding driving based on all judgment results that the distance information is greater than the width information of the target vehicle in the vertical direction path.
  • the target obstacle-avoiding driving path determination unit is further configured to determine that the currently to-be-used obstacle-avoiding driving path is not is the target obstacle avoidance path; based on the judgment result that all the obstacle avoidance travel paths to be used are not the target obstacle avoidance travel path, update the expansion attribute information corresponding to the target obstacle information, so that based on the updated expansion attribute information, and re-determine the target obstacle-avoiding driving path corresponding to the target vehicle.
  • FIG. 8 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application.
  • FIG. 8 shows a block diagram of an exemplary electronic device 80 suitable for implementing the embodiments of the present application.
  • the electronic device 80 shown in FIG. 8 is merely an example.
  • electronic device 80 takes the form of a general-purpose computing device.
  • the components of the electronic device 80 may include: at least one processor or processing unit 801 , a system memory 802 , and a bus 803 connecting different system components (including the system memory 802 and the processing unit 801 ).
  • Bus 803 represents at least one of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures.
  • bus structures include, for example, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MCA) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) ) Local bus and Peripheral Component Interconnect (PCI) bus.
  • ISA Industry Standard Architecture
  • MCA Micro Channel Architecture
  • VESA Video Electronics Standards Association
  • PCI Peripheral Component Interconnect
  • Electronic device 80 may, for example, include a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 80 and include both volatile and nonvolatile media, removable and non-removable media.
  • System memory 802 may include computer system readable media in the form of volatile memory, such as random access memory (Random Access Memory, RAM) 804 and/or cache memory 805 .
  • Electronic device 80 may include other removable/non-removable, volatile/nonvolatile computer system storage media.
  • storage system 806 may be used to read from and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive").
  • a disk drive may be provided for reading and writing to removable nonvolatile disks (such as "floppy disks"), and for removable nonvolatile optical disks (such as the Compact Disc-Read Only Memory, CD-ROM), Digital Video Disc-Read Only Memory (DVD-ROM) or other optical media) CD-ROM drive.
  • each drive may be connected to bus 803 via at least one data medium interface.
  • the memory 802 may include at least one program product, and the program product has a group (for example, at least one) of program modules configured to execute the functions of the above-mentioned embodiments of the present application.
  • a program/utility tool 808 having a set (at least one) of program modules 807 may be stored, for example, in memory 802, such program modules 807 including an operating system, at least one application program, other program modules, and program data, in these examples Each or a combination may include implementations of network environments.
  • the program module 807 generally executes the functions and/or methods in the embodiments described in this application.
  • the electronic device 80 can also communicate with at least one external device 809 (such as a keyboard, a pointing device, a display 810, etc.), and can also communicate with at least one device that enables the user to interact with the electronic device 80, and/or communicate with the electronic device that enables the user to interact with the electronic device 80.
  • 80 is a device capable of communicating with at least one other computing device (eg, network card, modem, etc.). Such communication may be performed through an input/output (Input/Output, I/O) interface 811 .
  • the electronic device 80 can also communicate with at least one network (such as a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN) and/or a public network such as the Internet) through the network adapter 812.
  • network adapter 812 communicates with other modules of electronic device 80 via bus 803 .
  • other hardware and/or software modules may be used in conjunction with electronic device 80, including: microcode, device drivers, redundant processing units, external disk drive arrays, Redundant Array of Independent Disks (RAID) systems , tape drives, and data backup storage systems.
  • the processing unit 801 executes various functional applications and data processing by running the programs stored in the system memory 802, such as implementing the obstacle avoidance method provided by the embodiment of the present application.
  • Embodiment 6 of the present application also provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute an obstacle avoidance method when executed by a computer processor.
  • the computer storage medium in the embodiments of the present application may use any combination of one or more computer-readable media.
  • the computer readable medium may be a computer readable signal medium or a computer readable storage medium.
  • the computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination thereof.
  • Examples (non-exhaustive list) of computer-readable storage media include: electrical connection with at least one lead, portable computer disk, hard disk, random access memory (RAM), read only memory (Read Only Memory, ROM), computer Erasable programmable read-only memory (such as electronic programmable read-only memory (Electronic Programable Read Only Memory, EPROM) or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, Or a suitable combination of the above.
  • a computer-readable storage medium may be a tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer readable signal medium may include a data signal carrying computer readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be other computer-readable media other than the computer-readable storage medium, and the computer-readable medium may transmit, propagate or transmit the program for use by or in conjunction with the instruction execution system, device or device .
  • the program code contained on the computer readable medium can be transmitted by appropriate medium, including wireless, electric wire, optical cable, radio frequency (Radio Frequency, RF), etc., or an appropriate combination of the above.
  • Computer program codes for performing the operations of the embodiments of the present application can be written in one or more programming languages or combinations thereof, and the programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and conventional A procedural programming language such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. Where a remote computer is involved, the remote computer may be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g. via the Internet using an Internet Service Provider). .
  • LAN local area network
  • WAN wide area network
  • Internet Service Provider e.g. via the Internet using an Internet Service Provider.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种避障方法、装置、电子设备和存储介质。避障方法包括：S110、获取目标车辆预设区域范围内的目标障碍物信息；S120、确定与目标障碍物信息相对应的目标膨胀检测框；S130、根据所述目标膨胀检测框、所述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径；S140、根据所述待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定目标避障行驶路径。该方法解决了传统车辆在自动驾驶时无法自动避开路障，造成交通事故频发的问题，确定了避障行驶路径，减少了交通事故的发生。

Description

避障方法、装置、电子设备和存储介质
本公开要求在2021年10月26日提交中国专利局、申请号为202111247962.3的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及自动驾驶技术领域，例如涉及一种避障方法、装置、电子设备和存储介质。
背景技术
随着信息和控制技术的快速发展，自动驾驶技术逐渐被汽车厂家和用户所接受。自动驾驶不仅能够将汽车行驶的危险性降到最低，而且能够减轻用户繁重的驾驶任务。
但在实际路况中，车辆行驶时路侧会出现多种情况的障碍物，需要车辆绕行避让，相关的避障技术通常根据障碍物的位置进行避障决策，生成避障轨迹路线，存在对车辆避障轨迹路线规划较差的问题，容易出现交通事故。
发明内容
本申请提供一种避障方法、装置、电子设备和存储介质，以实现对自动驾驶车辆的避障行驶路径的规划，提高自动驾驶的安全性和可靠性。
第一方面，本申请实施例提供了一种避障方法，应用于车辆，包括：
获取目标车辆预设区域范围内的目标障碍物信息；
确定与目标障碍物信息相对应的目标膨胀检测框；
根据所述目标膨胀检测框、所述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径；
根据所述待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定目标避障行驶路径。
第二方面，本申请实施例还提供了一种避障装置，应用于车辆，该装置包括：
障碍物信息获取模块，被设置为获取目标车辆预设区域范围内的目标障碍物信息；
膨胀检测框确定模块，被设置为确定与目标障碍物信息相对应的目标膨胀检测框；
避障行驶路径确定模块，被设置为根据所述目标膨胀检测框、所述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径；
目标避障行驶路径确定模块，被设置为根据所述待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定目标避障行驶路径。
第三方面，本申请实施例还提供了一种电子设备，所述设备包括：
处理器；
存储装置，被设置为存储程序，
在所述程序被所述处理器执行时，所述处理器实现如本申请实施例任一所述的避障方法。
第四方面，本申请实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时实现如本申请实施例任一所述的避障方法。
附图说明
为了说明本申请示例性实施例的技术方案，下面对描述实施例中所需要用到的附图做介绍。所介绍的附图只是本申请所要描述的一部分实施例的附图，而不是全部的附图，对于本领域普通技术人员，在不付出创造性劳动的前提下，还可以根据这些附图得到其他的附图。
图1为本申请实施例一所提供的一种避障方法的流程图；
图2为本申请实施例二所提供的一种避障方法的流程图；
图3为本申请实施例三所提供的一种避障方法的流程图；
图4为本申请实施例三所提供的一种避障方法的示意图；
图5为本申请实施例三所提供的一种避障方法的示意图；
图6为本申请实施例三所提供的一种避障方法的示意图；
图7为本申请实施例四所提供的一种避障装置的结构框图；
图8为本申请实施例五所提供的一种电子设备的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作说明。可以理解的是，此处所描述的实施例仅仅用于解释本申请。另外还需要说明的是，为了便于描述，附图中仅示出了与本申请相关的部分。
实施例一
图1为本申请实施例一所提供的一种避障方法的流程图，本实施例可适用于规划自动驾驶车辆的避障行驶路线，从而提高自动驾驶安全性的情况，该方法可以由本申请实施例中的避障装置来执行，该装置可以采用软件和/或硬件的方式来实现，可选的，通过电子设备来实现，该电子设备可以是移动终端、电脑(Personal Computer，PC)端或服务端等。该装置可配置于计算设备中，本实施例提供的应用于车辆中的避障方法具体包括如下步骤：
S110、获取目标车辆预设区域范围内的目标障碍物信息。
目标车辆是指自动驾驶过程中需要进行避障操作的车辆，可以将需要进行自动避障的所有车辆认为是目标车辆。目标车辆预设区域可以理解为根据目标车辆自身信息，预先设置的用于监测路障的区域，车辆自身信息可以为车身长度、车身宽度、车辆位置或者车辆行驶速度等。目标障碍物可以理解为出现在目标车辆预设区域范围内的路障信息，可以为车辆、树桩或者警示牌等，目标障碍物信息可以理解为根据车辆设备的感知结果，获取的目标障碍物的信息，车辆设备可以为传感器设备，目标障碍物信息可以为障碍物的位置、长度、宽度或者速度等信息。例如，在实际应用中，可以利用车辆传感器对目标车辆预设区域进行监控，监测到区域范围内存在目标障碍物，通过传感器设备采集目标车辆预设区域范围内的目标障碍物信息，传感器设备用于感知车辆周围环境、对车辆进行定位及获得车辆状态。传感器设备包括摄像头、激光雷达、全球定位系统(Global PositioningSystem，GPS)、速度传感器、方向盘转角传感器以及前轮转角传感器等。
需要说明的是，在实际应用中，目标车辆预设区域受目标车辆的当前位置变化以及检测障碍物区域的影响而发生变化。目标车辆的当前位置可以理解为车辆在行驶过程中一定位点的位置，可以通过车辆定位装置获取，定位装置可以为GPS，检测障碍物区域可以理解为传感器检测障碍物的区域信息，该区域可以是预先设置的特定区域，可以为2米(m)*2米(m)的区域，也可以为3m*2m的区域，相应的，根据目标车辆的定位点的位置信息以及检测障碍物区域，可以实时更新目标车辆预设区域信息。
还需要说明的是，为了方便后续可以针对性地对障碍物进行避让，可以在众多障碍物中选择出目标障碍物，如，在获取目标车辆预设区域内的所有障碍物信息之后，可以对障碍物信息进行筛选处理，如，可以判断障碍物的属性信息是否满足车辆避让的障碍物属性信息，例如，车辆避让的障碍物的速度信息需低于一阈值速度，可以判断目标车辆预设区域内的障碍物的速度是否低于这个阈值速度，基于目标车辆预设区域内的障碍物的速度低于上述阈值速度的判断结果，可将该障碍物作为车辆避让的障碍物，基于目标车辆预设区域内的障碍物的速度不低于上述阈值速度的判断结果，该障碍物不是车辆避让的障碍物，进而，确定出车辆避让的障碍物，可以将车辆避让的障碍物作为目标障碍物。
可选的，所述获取目标车辆预设区域范围内的目标障碍物信息，包括：根 据所述目标车辆的当前位置信息和预先设置的检测区域范围，确定与所述目标车辆相关联的预设区域范围内的待处理障碍物；根据所述待处理障碍物的属性信息，从待处理障碍物中确定目标障碍物信息。
示例性的，可以将在车辆行驶过程中，定位装置获取的任意一个定位点作为目标车辆的当前位置，进而，获取当前位置信息，当前位置信息可以为当前车辆定位点的经度、纬度或者航向角信息等。检测区域范围是指车辆周边用于检测障碍物的区域范围，可以通过预先设置检测区域大小，确定检测区域范围，例如，当区域大小的长度为1m和宽度为1m，检测区域范围可以为1m*1m构成的区域范围。根据获取目标车辆的当前位置信息和预先设置的检测区域范围，可以确定目标车辆预设区域，目标车辆预设区域可以随目标车辆的当前位置的变化而变化，例如，预设区域大小为1m*1m，当目标车辆的当前位置为A点时，目标车辆预设区域为以A点为中心的1m*1m的区域范围，当目标车辆的当前位置变为B点时，目标车辆预设区域为以B点为中心的1m*1m的区域范围。利用车辆传感器设备对目标车辆预设区域进行实时检测，将出现在目标车辆相关联的预设区域范围内的障碍物作为待处理障碍物，进而，可以获取待处理障碍物的属性信息，属性可以为位置、长度、宽度或者速度等。
目标障碍物可以理解为目标车辆需要执行避让操作的障碍物，需满足预设障碍物属性条件，可以将出现在目标车辆相关联的预设区域范围内，且满足预设障碍物属性条件的障碍物作为目标障碍物。预设障碍物属性条件可以为预先设置的满足目标车辆执行避让操作的障碍物的属性信息的条件，障碍物属性条件可以为障碍物速度信息低于一预设速度，也可以为障碍物位置在目标车辆前方一设定距离的位置，也可以为障碍物位置信息在目标车辆相关联的预设区域范围内，也可以将至少满足两个预设障碍物属性条件的待处理障碍物作为目标障碍物。通过判断待处理障碍物的属性信息是否满足预设障碍物属性条件，确定目标障碍物，相应的，可以在待处理障碍物中确定目标障碍物信息，提高了检测障碍物的准确性。
S120、确定与目标障碍物信息相对应的目标膨胀检测框。
目标膨胀检测框可以理解为基于膨胀宽度将目标障碍物的属性信息进行膨胀处理获取的矩形框，矩形框是由目标障碍物膨胀后的长度和宽度构成的，目标障碍物的属性信息可以为目标障碍物的长度信息和宽度信息，膨胀宽度可以理解为基于目标障碍物自身长、宽信息设置的膨胀宽度信息，膨胀宽度可以包括横向膨胀宽度和纵向膨胀宽度，横向膨胀宽度可以理解为目标障碍物在自身宽度的基础上膨胀的大小，纵向膨胀宽度可以理解为目标障碍物在自身长度的基础上膨胀的大小，可以根据横向膨胀宽度和纵向膨胀宽度确定目标障碍物的目标膨胀检测框，例如，目标障碍物为道路上的停置车辆，车辆长度为2m，宽度1m，膨胀宽度的横向膨胀宽度为0.6m，纵向膨胀宽度为4m，则目标障碍物的目标膨胀检测框的长度为10m(2m+4m*2)，宽度为2.2m(1m+0.6m*2)，确定出目标障碍物的一个10m*2.2m的目标膨胀检测框。可选地，可以确定出与每个 目标障碍物信息相对应的目标膨胀检测框。
需要说明的是，确定目标障碍物信息相对应的目标膨胀检测框，可以通过预先设置膨胀宽度的膨胀属性信息，进而，确定膨胀宽度的横向膨胀宽度和纵向膨胀宽度信息，对目标障碍物信息进行膨胀处理，如，可以将横向膨胀宽度与目标障碍物的宽度相加，将纵向膨胀宽度与目标障碍物的长度相加，进而，确定该目标障碍物的目标膨胀检测框。
可选的，所述确定与目标障碍物信息相对应的目标膨胀检测框，包括：根据预先设置的膨胀属性信息，对所述目标障碍物信息进行膨胀处理，得到与目标障碍物信息相对应的目标膨胀检测框。
膨胀属性信息可以理解为膨胀宽度的横向膨胀宽度信息和纵向膨胀宽度信息，通过预先设置横向膨胀宽度和纵向膨胀宽度，根据目标障碍物的长度和宽度信息对目标障碍物信息进行膨胀处理，膨胀处理可以是对目标障碍物的宽度进行膨胀处理，即将横向膨胀宽度加上目标障碍物的宽度得到目标障碍物膨胀后的宽度，也可以是对目标障碍物的长度进行膨胀处理，即将纵向膨胀宽度加上目标障碍物的长度得到目标障碍物膨胀后的长度。示例性的，目标障碍物为道路上的停置车辆，车辆长度为2m，宽度1m，膨胀宽度的初始值为横向膨胀宽度0.6m，纵向膨胀宽度4m，对车辆的长度进行膨胀处理，可以为车辆的长度加上两个纵向膨胀宽度的处理，即车辆膨胀后的长度为10m，对车辆的宽度进行膨胀处理，可以为车辆的宽度加上两个横向膨胀宽度的处理，即车辆膨胀后的长度为2.2m，则目标障碍物的目标膨胀检测框的长度为10m，宽度为2.2m，得到与目标障碍物信息相对应的目标膨胀检测框，提高了自动驾驶车辆避障的安全性。
需要说明的是，可以根据预先设置的膨胀属性信息确定目标障碍物信息相对应的目标膨胀检测框，也可以对膨胀属性信息进行更新处理，获取目标障碍物的目标膨胀检测框，例如，在实际应用中，当膨胀属性信息的横向膨胀宽度信息或纵向膨胀宽度信息设置的初始值大于一预设阈值，会使目标障碍物的膨胀处理获取的目标膨胀检测框超出阈值范围，造成目标车辆在所属车道上进行避障行驶时会远距离规划避障轨迹路线，浪费车辆行驶时间，由此，可以将膨胀属性信息减少一阈值。也可能存在当膨胀属性信息的横向膨胀宽度信息或纵向膨胀宽度信息设置的初始值小于一预设阈值，会使目标障碍物的膨胀处理获取的目标膨胀检测框小于一阈值范围，造成目标车辆在所属车道上进行避障行驶时会近距离规划避障轨迹路线，容易发生目标车辆与障碍物撞击的危险，由此，可以将膨胀属性信息增加一阈值。相应的，可以通过更新膨胀属性信息获取最终的目标膨胀检测框。
可选的，所述确定与目标障碍物信息相对应的目标膨胀检测框，还包括：在接收到膨胀属性信息更新请求的情况下，确定与所述更新请求相对应的待更新膨胀属性信息，并根据所述待更新膨胀属性信息更新与目标障碍物信息相对应的目标膨胀检测框。
更新请求可以理解为对目标膨胀检测框的膨胀属性信息的更新请求。例如，可能是当根据预先设置的膨胀属性信息，确定的目标膨胀检测框的膨胀宽度大于最小预设阈值时，可以触发对膨胀宽度的更新请求，也可能是当根据预先设置的膨胀属性信息，确定的目标膨胀检测框的膨胀宽度小于最小预设阈值时，可以触发对膨胀宽度的更新请求，即触发更新膨胀宽度的膨胀属性信息的请求。待更新膨胀属性信息可以理解为触发的更新请求请求更新膨胀宽度的膨胀属性信息，可以为膨胀宽度的横向膨胀宽度信息，也可以为膨胀宽度的纵向膨胀宽度信息，例如，当目标膨胀检测框的膨胀宽度大于最小预设阈值，可以触发对膨胀宽度的减小请求，可以将待减小的膨胀宽度的的膨胀属性信息作为待更新膨胀属性信息。示例性的，为了防止车辆的避障路径范围过大，可以为横向膨胀宽度和纵向膨胀宽度预先设置最小阈值，假设，横向膨胀宽度最小阈值为0.3m，纵向膨胀宽度最小阈值为1m，当根据预先设置的膨胀属性信息确定的目标膨胀检测框的膨胀宽度大于最小阈值时，可以请求减小膨胀宽度的膨胀属性信息，将待减小的膨胀属性信息作为待更新膨胀属性信息，可以将膨胀属性信息减少一定量的预设值，如，可以将目标膨胀检测框的横向膨胀宽度减少0.05m，纵向膨胀宽度减少0.1m，根据减少后的横向膨胀宽度和纵向膨胀宽度确定新的目标膨胀检测框，将新的目标膨胀检测框作为最终的目标膨胀检测框，相应的，可以确定与目标障碍物信息相对应的最终的目标膨胀检测框，即根据待更新膨胀属性信息更新与目标障碍物信息相对应的目标膨胀检测框，提高了自动驾驶避障的可靠性。
S130、根据所述目标膨胀检测框、所述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径。
车道边界线可以理解为目标车辆行驶所在道路的边界线，可以通过传感器设备监测目标车辆行驶的道路路况，当检测到车道边界线标志物，获取目标车辆行驶道路的左、右车道边界线信息，边界线信息可以为车道的边界线上边界点的坐标信息，也可以为边界线上边界点的航向角信息。车道边界线标志物可以为道路上的边界标线、侧沟、路缘或护栏或柱等结构物标志，例如，当车辆传感器设备检测到目标车辆行驶道路上的车道标线，可以确定车道边界线，进而，可以通过传感器设备获取边界线上边界点的坐标信息以及航向信息。避障行驶路径可以理解为目标车辆在避开障碍物时规划的行驶路线，可以根据障碍物的目标膨胀检测框、目标车辆的当前位置信息以及目标车辆所属行驶道路的车道边界线信息，确定出至少一条目标车辆的避障行驶路径，将获取的避障行驶路径作为待使用避障行驶路径，例如，目标车辆在所属行驶道路上行驶，需避开障碍物进行绕行，目标车辆可以根据当前位置，在不超出行驶道路的车道边界线的情况下，且在障碍物的目标膨胀检测框外行驶，可以有一条或多条的避障行驶路径。
需要说明的是，为了有效的为目标车辆规划避障行驶路径，可以计算障碍 物的目标膨胀检测框距离车道边界线最小距离，根据计算出的最小距离的距离信息以及目标膨胀检测框上的点的位置信息确定出避障行驶路径中的一个轨迹点信息，如，可以通过计算目标膨胀检测框中所有顶点到车道边界线的距离，确定所有顶点到车道边界线的最小距离，即得到目标膨胀检测框距离车道边界线最小距离，可以根据获取的最小距离线与最小距离的对应的顶点信息，确定避障行驶路径中的一个轨迹点，可以将这个轨迹点作为第一行驶离散点。
还需要说明的是，根据目标车辆的当前位置信息与第一行驶离散点可以确定出一条避障行驶路径，还可以根据第一行驶离散点位置信息与车辆行驶道路的左、右两条车道边界线信息确定避障行驶路径中的另一个轨迹点信息，如，可以根据目标车辆的预设速度和预设时长信息确定目标车辆的预设行驶里程，将第一行驶离散点的位置作为起点，可以根据目标车辆从起点位置沿车道边界线方向行驶预设里程，将行驶到达位置作为终点，根据车辆行驶道路的左、右两条车道边界线信息以及终点位置信息，可以确定避障行驶路径中的另一个轨迹点信息，作为第二行驶离散点。
示例性的，可以根据目标车辆的当前位置信息以及障碍物的目标膨胀检测框以及车道边界线信息，可以为目标车辆在避障行驶时规划出多条避障行驶路线。
可选的，根据目标膨胀检测框、所述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径，包括：根据目标膨胀检测框确定目标膨胀检测框中所有顶点；根据所述目标膨胀检测框中所有顶点到所述车道边界线信息中第一边界线上的距离确定最小距离，并根据所述最小距离和所述最小距离对应的顶点，确定第一行驶离散点；根据所述第一行驶离散点、车道边界线信息、目标车辆的预设速度信息和预设时长信息，确定第二行驶离散点；根据所述目标车辆的当前位置信息、第一行驶离散点信息和第二行驶离散点信息，确定至少一条待使用避障行驶路径。
目标膨胀检测框中所有顶点可以理解为由目标膨胀检测框的长和宽构成的矩形框的顶点信息，如，可以通过车辆传感器设备获取目标障碍物位置信息，并将目标障碍物进行膨胀处理获得目标膨胀检测框的位置信息，进而，获取目标膨胀检测框的四个顶点信息。第一边界线可以理解为目标车辆所属车道的左、右车道边界线中任意一条车道边界线，可以为车道的左车道边界线，也可以为车道的右车道边界线，需要说明的是，在确定一条避障行驶路径的过程中，所使用的车道边界线均为同一条车道边界线，如均使用左车道边界线或者均使用右车道边界线。最小距离可以理解为目标膨胀检测框中所有顶点到车道边界线信息中第一边界线上距离数值最小的距离信息。第一行驶离散点可以理解为目标障碍物对应的目标膨胀检测框距离车道边界线中第一边界线的最近距离线上的点，第一行驶离散点信息可以为第一行驶离散点的坐标位置信息，也可以为第一行驶离散点的航向角信息。例如，第一边界线是一条弯曲的曲线，可以用 数学方程进行表示，所有顶点可以用位置坐标表示，可以计算所有顶点到第一边界线上的距离，获得每个顶点对应的距离，取所有距离中数值最小的距离作为最小距离。相应的，可以获得与最小距离对应的目标膨胀检测框的顶点，该顶点与第一边界线上的一边界点之间存在一条最小距离线，可选的，可以将最小距离相对应的顶点到第一边界线的最小距离路线上的中心点，作为第一行驶离散点，进而确定第一行驶离散点信息。
预设速度信息可以理解为预先设置的速度信息，可以将目标车辆在避障时的行驶速度作为预设速度，示例性的，为了保障目标车辆避障的安全性，可以将避障时车辆最高限速值10米/秒(m/s)作为预设速度，也可以在膨胀宽度低于一阈值时，设置低于该阈值的车辆避障限速作为预设速度，例如，在膨胀宽度的横向膨胀宽度低于0.4m的情况下，可以将车辆避障限速3m/s作为预设速度。预设时长信息理解为预先设置的时长信息，可以为1秒(s)，也可以为1.5s。第二行驶离散点可以理解为从第一行驶离散点向车辆前方行驶预计里程的车道中心点处的位置，第一行驶离散点信息可以为第一行驶离散点的坐标位置信息，也可以为第一行驶离散点的航向角信息。例如，可以将第一行驶离散点作为目标车辆的行驶起点，根据目标车辆的预设速度信息和预设时长信息，确定目标车辆的预计行驶里程，进而，确定目标车辆的行驶终点，获取目标车辆的行驶终点的位置信息，相应的，根据目标车辆的行驶终点的位置信息和目标车辆所属道路的左、右两条车道边界线的中心点，可以得到第二行驶离散点的位置信息，进而，确定第二行驶离散点。根据目标车辆的当前位置信息、第一行驶离散点信息和第二行驶离散点信息，可以规划出多条目标车辆的避障行驶路径，将规划出的避障行驶路径作为待使用避障行驶路径，提高了目标车辆在避障行驶路径上行驶的安全性和可靠性。
S140、根据所述待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定目标避障行驶路径。
待使用避障行驶路径可以由无数个坐标点组成，可以将待使用避障行驶路径中的定位点作为离散点，如，通过车辆传感设备获取待使用避障行驶路径中的定位点的经度、纬度或者航向角信息，既获得了离散点的信息。相对位置信息可以理解为待使用避障行驶路径中离散点与目标膨胀检测框之间的位置信息，位置信息可以为距离信息、航向角信息或者坐标信息等，例如，可以通过计算目标膨胀检测框中所有顶点与待使用避障行驶路径中离散点之间的距离，获得多个距离信息，将距离信息作为相对距离信息，也可以通过计算目标膨胀检测框中所有顶点与待使用避障行驶路径中离散点之间的夹角，获得多个航向角夹角信息，将航向角夹角信息作为相对航向角信息，可以将相对距离信息或者相对航向角信息作为相对位置信息。目标避障行驶路径可以理解为待使用避障行驶路径中满足预设条件的避障行驶路径，可以为一条，也可以为多条，预设条件可以为待使用避障行驶路径中离散点与目标膨胀检测框之间的相对距离满足一预设距离值，也可以为待使用避障行驶路径中离散点与目标膨胀检测框 之间的相对航向角信息。示例性的，在实际应用中，可以通过判断待使用避障行驶路径中离散点与目标膨胀检测框的所有顶点之间距离是否大于一预设阈值，为了可以使目标车辆可以平安避障，可以将目标车辆自身宽度设为该阈值，可以将待使用避障行驶路径中离散点与目标膨胀检测框的所有顶点之间距离大于目标车辆自身宽度条件的待使用避障行驶路径作为目标避障行驶路径。
本实施例通过获取目标车辆预设区域范围内的目标障碍物信息，通过预先设置的膨胀属性信息确定与目标障碍物信息相对应的目标膨胀检测框，通过计算使用避障行驶路径中的第一行驶离散点和第二行驶离散点，与目标车辆的当前位置信息确定与目标车辆相对应的至少一条待使用避障行驶路径，根据待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定出目标车辆在避障行驶过程中的目标避障行驶路径。解决相关技术中车辆在自动驾驶时无法自动避开路障，规划避障行驶路径，造成交通事故频发的问题，本实施例通过利用为目标障碍物设置膨胀宽度，确定目标障碍物信息相对应的目标膨胀检测框，检测待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，从而使目标车辆在自动避障行驶过程中，可以准确的规划出目标避障行驶路径，防止目标车辆和障碍物发生碰撞，减少交通事故的发生，提高了自动驾驶车辆避障时的安全性和可靠性。
实施例二
图2为本申请实施例二所提供的一种避障方法的流程图，在上述技术方案的基础上，本实施例对技术方案进行了改动。本实施例在本申请实施例中任一可选技术方案的基础上，可选地，根据所述待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定目标避障行驶路径，包括：针对目标膨胀检测框，确定当前目标膨胀检测框中所有顶点到当前待使用避障行驶路径中各个离散点的距离信息；基于所有所述距离信息大于所述目标车辆在垂直方向上的宽度信息的判断结果，确定所述当前待使用避障行驶路径为所述目标避障行驶路径。
其中，与上述实施例相同或者相应的技术术语在此不再赘述。如图2所示，本实施例的方法包括如下步骤：
S210、获取目标车辆预设区域范围内的目标障碍物信息。
S220、确定与目标障碍物信息相对应的目标膨胀检测框。
S230、根据所述目标膨胀检测框、所述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径。
S240、针对所述目标膨胀检测框，确定当前目标膨胀检测框中所有顶点到当前待使用避障行驶路径中各个离散点的距离信息；基于所有所述距离信息大于所述目标车辆在垂直方向上的宽度信息的判断结果，确定所述当前待使用避障行驶路径为所述目标避障行驶路径。
当前目标膨胀检测框可以理解为当确定目标膨胀检测框相对应的所有顶点时，可以将确定任一目标膨胀检测框的顶点作为确定当前目标膨胀检测框的顶点进行处理，如，可以确定目标膨胀检测框相对应的所有顶点的坐标位置信息或者航向角信息，以对其中一个目标膨胀检测框作为当前目标膨胀检测框进行说明。相应的，当确定待使用避障行驶路径相对应的离散点时，也可以将确定任一待使用避障行驶路径的离散点作为确定当前待使用避障行驶路径的离散点进行处理，如，可以确定待使用避障行驶路径中离散点的坐标位置信息或者航向角信息，以对其中一个待使用避障行驶路径作为当前待使用避障行驶路径进行说明。距离信息可以理解为当前目标膨胀检测框中所有顶点到当前待使用避障行驶路径中各个离散点的距离，可以获得至少一个距离的信息。示例性的，可以根据车辆传感器设备获得目标膨胀检测框中所有顶点的坐标位置信息以及当前待使用避障行驶路径中各个离散点的坐标位置信息，可以计算目标膨胀检测框中所有顶点与当前待使用避障行驶路径中各个离散点的距离，将计算的所有距离作为距离信息。
目标车辆在垂直方向上的宽度信息可以理解为在设定维度的空间中，计算目标车辆在垂直于车辆行驶方向的车身宽度信息，维度可以为二维，也可以为三维。例如，在实际应用中，目标车辆在所属道路上进行避障行驶过程中，目标车辆在垂直方向上的宽度信息可以为目标车辆的车身宽度信息。目标避障行驶路径可以理解为多条待使用避障行驶路径中满足车辆避障行驶的预设条件的避障行驶路径，例如，车辆避障行驶的预设条件可以为障碍物的目标膨胀检测框上的所有顶点与待使用避障行驶路径中各个离散点的距离大于一预设阈值的条件。在实际应用中，为了防止确定的待使用避障行驶路径不能满足目标车辆的车身平稳通过，可以将目标车辆的车身宽度作为预设阈值，可以检测目标膨胀检测框中所有顶点与当前待使用避障行驶路径中各个离散点的距离是否满足目标车辆的车身宽度，基于所有距离信息大于目标车辆的车身宽度的判断结果，可以将当前待使用避障行驶路径作为目标避障行驶路径。
需要说明的是，针对目标膨胀检测框，确定当前目标膨胀检测框中所有顶点到当前待使用避障行驶路径中各个离散点的距离信息，可能出现所有距离信息中存在距离信息不大于目标车辆在垂直方向上的宽度信息的距离，如，在实际应用中，如果所有距离信息中存在距离信息不大于目标车辆在垂直方向上的宽度信息的距离，目标车辆在当前待使用避障行驶路径上行驶时，可能出现车辆与障碍物膨胀的后果。可能是初始预先设置的膨胀属性信息偏大，造成确定的待处理的目标障碍物对应的目标膨胀检测框不合理的问题，可以向系统发出更新目标障碍物信息相对应的膨胀属性信息的请求，如，当接收到膨胀属性信息更新请求时，可以将预先设置的膨胀属性信息减少一阈值，获得新的膨胀属性信息，即更新膨胀属性信息，进而，确定与更新请求相对应的待更新膨胀属性信息，并根据待更新膨胀属性信息更新与目标障碍物信息相对应的目标膨胀检测框，重新确定与目标车辆相对应的目标避障行驶路径。
可选的，基于所有所述距离信息中存在距离信息不大于所述目标车辆在垂直方向上的宽度信息的判断结果，确定所述当前待使用避障行驶路径不为所述目标避障路径；基于所有待使用避障行驶路径均不为所述目标避障行驶路径的判断结果，更新与目标障碍物信息相对应的膨胀属性信息，以基于更新后的膨胀属性信息，重新确定与所述目标车辆相对应的目标避障行驶路径。
在确定当前目标膨胀检测框中所有顶点到当前待使用避障行驶路径中各个离散点的距离信息之后，可能出现所有距离信息中存在不大于目标车辆在垂直方向上的宽度信息的距离，在所有距离信息中存在距离信息不大于目标车辆在垂直方向上的宽度信息的距离的情况下，可以确定当前待使用避障行驶路径不是目标避障路径，可选的，可以判断当前目标膨胀检测框对应的目标障碍物的膨胀宽度是否为最小阈值宽度，基于当前目标膨胀检测框对应的目标障碍物的膨胀宽度为最小阈值宽度的判断结果，可以确定当前待使用避障行驶路径不是目标避障路径，不需要进行更新膨胀宽度的膨胀属性信息操作，可选的，可以规划纵向避障路径，其中，纵向避障路径可以理解为目标障碍物对应的目标膨胀检测框上各个离散点与目标车辆当前位置的最小距离的路径，基于当前目标膨胀检测框对应的目标障碍物的膨胀宽度不为最小阈值宽度的判断结果，也可以确定当前待使用避障行驶路径不是目标避障路径，但是可能存在初始预先设置的膨胀宽度的膨胀属性信息偏大的情况，此时，可以触发更新膨胀属性信息的请求，进而，当系统接收到更新膨胀属性信息的请求，可以将与目标障碍物信息相对应的膨胀属性信息进行更新，例如，发出减少膨胀宽度的请求，则膨胀宽度减少一定量的设定阈值，如，横向膨胀宽度减少0.05m，纵向膨胀宽度减少0.1m。更新目标障碍物信息相对应的目标膨胀检测框，重新确定与目标车辆相对应的目标避障行驶路径。相应的，在所有待使用避障行驶路径均不为目标避障行驶路径的情况下，可以判断目标膨胀检测框对应的目标障碍物的膨胀宽度是否为最小阈值宽度，基于目标膨胀检测框对应的目标障碍物的膨胀宽度为最小阈值宽度的判断结果，可选的，可以规划纵向避障路径，基于目标膨胀检测框对应的目标障碍物的膨胀宽度不为最小阈值宽度的判断结果，更新与目标障碍物信息相对应的膨胀属性信息，进而，更新目标障碍物信息相对应的目标膨胀检测框，重新确定与目标车辆相对应的目标避障行驶路径，提高了规划避障行驶路径的准确性和安全性。
本实施例通过获取目标车辆预设区域范围内的目标障碍物信息，通过预先设置的膨胀属性信息确定与目标障碍物信息相对应的目标膨胀检测框，通过计算使用避障行驶路径中的第一行驶离散点和第二行驶离散点，与目标车辆的当前位置信息确定与目标车辆相对应的至少一条待使用避障行驶路径，根据待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定出目标车辆在避障行驶过程中的目标避障行驶路径。解决相关技术中车辆在自动驾驶时无法自动避开路障，规划避障行驶路径，造成交通事故频发的问题，本实施例通过利用为目标障碍物设置膨胀宽度，确定目标障碍物信息相对应的目标膨 胀检测框，检测待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，从而使目标车辆在自动避障行驶过程中，可以准确的规划出目标避障行驶路径，防止目标车辆和障碍物发生碰撞，减少交通事故的发生，提高了自动驾驶车辆避障时的安全性和可靠性。
实施例三
作为上述实施例的一可选实施例，图3为本申请实施例三提供的一种避障方法的流程示意图。
如图3所示，本申请实施例三提供的一种避障方法可以通过获取目标车辆周围障碍物信息，根据车辆传感器的感知结果，获取障碍物的位置、长、宽、速度等信息。进而，根据障碍物速度小于一设定阈值、障碍物位置在目标车辆前方或者障碍物在与目标车辆相关联的预设区域范围内等条件，筛选目标车辆行驶路径周围的静止障碍物，根据预先设置的膨胀宽度的膨胀属性信息，膨胀宽度初次设定为初始值，一般地，膨胀宽度初始值横向膨胀宽度为0.6m，纵向膨胀宽度为4m，计算障碍物膨胀宽度，对筛选出的障碍物进行膨胀处理，获取目标障碍物信息相对应的目标膨胀检测框，规划目标车辆的避障路径和速度，为保障避障安全性，设置避障时目标车辆最高限速，一般地，在城市道路行驶中可设为10m/s。在膨胀宽度较低时，设置较低的目标车辆避障限速，一般地，在膨胀宽度的横向距离低于0.4m的情况下，目标车辆限速可设为3m/s。
可选的，判断膨胀后的障碍物能否本车道避让，可以通过计算障碍物膨胀后四个顶点距离规划的避障路径的距离是否大于目标车辆自身宽度，基于上述距离大于目标车辆自身宽度的判断结果，判断该障碍不会发生碰撞，即该障碍可以本车道避让，可以规划目标避障行驶路径；基于上述距离不大于目标车辆自身宽度的判断结果，判断当前膨胀宽度是否为最小设定阈值，基于当前膨胀宽度为最小设定阈值的判断结果，规划纵向避障路径，基于当前膨胀宽度不为最小设定阈值的判断结果，发出减少膨胀宽度的请求，则膨胀宽度减少一定值，一般地横向减少0.05m，纵向减少0.1m，进而重新更新膨胀属性信息，计算障碍物膨胀宽度，确定目标障碍物信息相对应的目标膨胀检测框，如此循环更新，直至满足膨胀后的障碍物可以本车道避让或者判断当前膨胀宽度为最小设定阈值，开始规划目标避障行驶路径和规划纵向避障路径，纵向避障路径为障碍物对应的目标膨胀检测框上的各个离散点与目标车辆当前位置的最小距离路径。
可选的，避障方法的内容如图4所示，目标车辆410正常行驶时检测到前方障碍物430，此时，根据预先设置的膨胀属性信息，对目标障碍物进行膨胀处理，得到与目标障碍物相对应的目标膨胀检测框，目标膨胀检测框参见框1，进而，根据目标膨胀检测框中所有顶点到车道边界线上的距离确定最小距离，并根据最小距离和最小距离对应的顶点，确定第一行驶离散点，该点为M点，然后，根据第一行驶离散点、车道边界线信息、目标车辆的预设速度信息和预设时长信息，确定第二行驶离散点，该点为N点，进而，根据目标车辆的当前位置信息、 第一行驶离散点信息和第二行驶离散点信息，确定出一条待使用避障行驶路径，路径为O-M-N，且避障行驶的目标车辆420可以根据避障行驶路径避开障碍物，其中，目标车辆的当前位置为O点。
可选的，避障方法的内容如图5所示，在目标膨胀检测框中所有顶点到车道边界线上的距离存在不大于目标车辆510自身宽度的情况下，可以发出更新膨胀宽度的膨胀属性信息的请求，将减少目标障碍物530的膨胀宽度，即减少横向膨胀和减少纵向膨胀，得到减少后的目标障碍物的目标膨胀检测框，目标膨胀检测框参见框2，重新计算第一行驶离散点M和第二行驶离散点O，根据目标车辆的当前位置信息、第一行驶离散点信息和第二行驶离散点信息，确定出一条待使用避障行驶路径，路径为O-M-N，且避障行驶的目标车辆520可以根据避障行驶路径避开障碍物。
可选的，避障方法的内容如图6所示，判断当前膨胀宽度是否为最小横向膨胀和最小纵向膨胀，基于当前膨胀宽度为最小横向膨胀和最小纵向膨胀的判断结果，规划纵向避障路径，纵向避障路径为障碍物620与目标车辆610最近距离处的车道中心线上的点Q到目标车辆当前位置O的路径，路径为O-Q，基于当前膨胀宽度不为最小横向膨胀和最小纵向膨胀的判断结果，发出减少膨胀宽度的请求，更新膨胀属性信息，重新规划避障路径。
本实施例通过获取目标车辆预设区域范围内的目标障碍物信息，通过预先设置的膨胀属性信息确定与目标障碍物信息相对应的目标膨胀检测框，通过计算使用避障行驶路径中的第一行驶离散点和第二行驶离散点，与目标车辆的当前位置信息确定与目标车辆相对应的至少一条待使用避障行驶路径，根据待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定出目标车辆在避障行驶过程中的目标避障行驶路径。解决相关技术中车辆在自动驾驶时无法自动避开路障，规划避障行驶路径，造成交通事故频发的问题，本实施例通过利用为目标障碍物设置膨胀宽度，确定目标障碍物信息相对应的目标膨胀检测框，检测待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，从而使目标车辆在自动避障行驶过程中，可以准确的规划出目标避障行驶路径，防止目标车辆和障碍物发生碰撞，减少交通事故的发生，提高了自动驾驶车辆避障时的安全性和可靠性。
实施例四
图7为本申请实施例四提供的一种避障装置的结构框图。该装置包括：障碍物信息获取模块710、膨胀检测框确定模块520、避障行驶路径确定模块730和目标避障行驶路径确定模块740。
其中，障碍物信息获取模块710，被设置为获取目标车辆预设区域范围内的目标障碍物信息；
膨胀检测框确定模块720，被设置为确定与目标障碍物信息相对应的目标膨胀检测框；
避障行驶路径确定模块730，被设置为根据所述目标膨胀检测框、所述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径；
目标避障行驶路径确定模块740，被设置为根据所述待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定目标避障行驶路径。
本实施例通过获取目标车辆预设区域范围内的目标障碍物信息，通过预先设置的膨胀属性信息确定与目标障碍物信息相对应的目标膨胀检测框，通过计算使用避障行驶路径中的第一行驶离散点和第二行驶离散点，与目标车辆的当前位置信息确定与目标车辆相对应的至少一条待使用避障行驶路径，根据待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定出目标车辆在避障行驶过程中的目标避障行驶路径。解决相关技术中车辆在自动驾驶时无法自动避开路障，规划避障行驶路径，造成交通事故频发的问题，本实施例通过利用为目标障碍物设置膨胀宽度，确定目标障碍物信息相对应的目标膨胀检测框，检测待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，从而使目标车辆在自动避障行驶过程中，可以准确的规划出目标避障行驶路径，防止目标车辆和障碍物发生碰撞，减少交通事故的发生，提高了自动驾驶车辆避障时的安全性和可靠性。
上述装置中，可选的是，所述障碍物信息获取模块710，包括：
待处理障碍物确定单元，被设置为根据所述目标车辆的当前位置信息和预先设置的检测区域范围，确定与所述目标车辆相关联的预设区域范围内的待处理障碍物；
目标障碍物信息确定单元，被设置为根据所述待处理障碍物的属性信息，从待处理障碍物中确定目标障碍物信息。
上述装置中，可选的是，所述膨胀检测框确定模块720，包括：
目标膨胀检测框确定单元，被设置为根据预先设置的膨胀属性信息，对所述目标障碍物信息进行膨胀处理，得到与目标障碍物信息相对应的目标膨胀检测框。
目标膨胀检测框确定单元还被设置为，在接收到膨胀属性信息更新请求的情况下，确定与所述更新请求相对应的待更新膨胀属性信息，并根据所述待更新膨胀属性信息更新与目标障碍物信息相对应的目标膨胀检测框。
上述装置中，可选的是，所述避障行驶路径确定模块730，包括：
顶点确定单元，被设置为根据所述目标膨胀检测框确定所述目标膨胀检测框中所有顶点；
第一行驶离散点确定单元，被设置为根据所述目标膨胀检测框中所有顶点到所述车道边界线信息中第一边界线上的距离确定最小距离，并根据所述最小距离和所述最小距离对应的顶点，确定第一行驶离散点；
第二行驶离散点确定单元，被设置为根据所述第一行驶离散点、车道边界线信息、目标车辆的预设速度信息和预设时长信息，确定第二行驶离散点；
待使用避障行驶路径确定单元，被设置为根据所述目标车辆的当前位置信息、第一行驶离散点信息和第二行驶离散点信息，确定至少一条待使用避障行驶路径。
上述装置中，可选的是，所述目标避障行驶路径确定模块740，包括：
距离信息确定单元，被设置为针对所述目标膨胀检测框，确定当前目标膨胀检测框中所有顶点到当前待使用避障行驶路径中各个离散点的距离信息；
目标避障行驶路径确定单元，被设置为基于所有所述距离信息大于所述目标车辆在垂直方向上的宽度信息的判断结果，确定所述当前待使用避障行驶路径为所述目标避障行驶路径。
目标避障行驶路径确定单元还被设置为，基于所有所述距离信息中存在距离信息不大于所述目标车辆在垂直方向上的宽度信息的判断结果，确定所述当前待使用避障行驶路径不为所述目标避障路径；基于所有待使用避障行驶路径均不为所述目标避障行驶路径的判断结果，更新与目标障碍物信息相对应的膨胀属性信息，以基于更新后的膨胀属性信息，重新确定与所述目标车辆相对应的目标避障行驶路径。
实施例五
图8为本申请实施例五提供的一种电子设备的结构示意图。图8示出了适于用来实现本申请实施例实施方式的示例性电子设备80的框图。图8显示的电子设备80仅仅是一个示例。
如图8所示，电子设备80以通用计算设备的形式表现。电子设备80的组件可以包括：至少一个处理器或者处理单元801，系统存储器802，连接不同系统组件(包括系统存储器802和处理单元801)的总线803。
总线803表示几类总线结构中的至少一种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括工业标准体系结构(Industry Standard Architecture，ISA)总线，微通道体系结构(Micro Channel Architecture，MCA)总线，增强型ISA总线、视频电子标准协会(Video Electronics Standards Association，VESA)局域总线以及外围组件互连(Peripheral Component Interconnect，PCI)总线。
电子设备80例如可以包括多种计算机系统可读介质。这些介质可以是任何能够被电子设备80访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
系统存储器802可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(Random Access Memory，RAM)804和/或高速缓存存储器805。 电子设备80可以包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统806可以用于读写不可移动的、非易失性磁介质(通常称为“硬盘驱动器”)。可选的，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘(例如便携式紧凑磁盘只读存储器(Compact Disc-Read Only Memory，CD-ROM)，数字通用光盘只读存储器(Digital Video Disc-Read Only Memory，DVD-ROM)或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过至少一个数据介质接口与总线803相连。存储器802可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本申请上述实施例的功能。
具有一组(至少一个)程序模块807的程序/实用工具808，可以存储在例如存储器802中，这样的程序模块807包括操作系统、至少一个应用程序、其它程序模块以及程序数据，这些示例中的每一个或一组合中可能包括网络环境的实现。程序模块807通常执行本申请所描述的实施例中的功能和/或方法。
电子设备80也可以与至少一个外部设备809(例如键盘、指向设备、显示器810等)通信，还可与至少一个使得用户能与该电子设备80交互的设备通信，和/或与使得该电子设备80能与至少一个其它计算设备进行通信的设备(例如网卡，调制解调器等)通信。这种通信可以通过输入/输出(Input/Output，I/O)接口811进行。并且，电子设备80还可以通过网络适配器812与至少一个网络(例如局域网(Local Area Network，LAN)，广域网(Wide Area Network，WAN)和/或公共网络，例如因特网)通信。如图所示，网络适配器812通过总线803与电子设备80的其它模块通信。应当明白，可以结合电子设备80使用其它硬件和/或软件模块，包括：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、独立冗余磁盘阵列(Redundant Array of Independent Disks，RAID)系统、磁带驱动器以及数据备份存储系统等。
处理单元801通过运行存储在系统存储器802中的程序，从而执行各种功能应用以及数据处理，例如实现本申请实施例所提供的避障方法。
实施例六
本申请实施例六还提供一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行一种避障方法。
本申请实施例的计算机存储介质，可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者以上的组合。计算机可读存储介质的示例(非穷举的列表)包括：具有至少一个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(Read Only Memory，ROM)、可擦式可编程只读存储器(如电子可编程只读存储器(Electronic Programable Read Only  Memory，EPROM)或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的合适的组合。在本文件中，计算机可读存储介质可以是包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括电磁信号、光信号或上述的合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的其他计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用适当的介质传输，包括无线、电线、光缆、射频(Radio Frequency，RF)等，或者上述的合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请实施例操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言如Java、Smalltalk、C++，还包括常规的过程式程序设计语言如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络包括局域网(LAN)或广域网(WAN)连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。

Claims (10)

  1. 一种避障方法，应用于车辆，包括：
    获取目标车辆预设区域范围内的目标障碍物信息；
    确定与目标障碍物信息相对应的目标膨胀检测框；
    根据所述目标膨胀检测框、所述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径；
    根据所述待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定目标避障行驶路径。
  2. 根据权利要求1所述的方法，其中，所述获取目标车辆预设区域范围内的目标障碍物信息，包括：
    根据所述目标车辆的当前位置信息和预先设置的检测区域范围，确定与所述目标车辆相关联的预设区域范围内的待处理障碍物；
    根据所述待处理障碍物的属性信息，从所述待处理障碍物中确定目标障碍物信息。
  3. 根据权利要求1所述的方法，其中，所述确定与目标障碍物信息相对应的目标膨胀检测框，包括：
    根据预先设置的膨胀属性信息，对所述目标障碍物信息进行膨胀处理，得到与所述目标障碍物信息相对应的目标膨胀检测框。
  4. 根据权利要求3所述的方法，所述方法还包括：
    在接收到膨胀属性信息更新请求的情况下，确定与所述更新请求相对应的待更新膨胀属性信息，并根据所述待更新膨胀属性信息更新与所述目标障碍物信息相对应的目标膨胀检测框。
  5. 根据权利要求1所述的方法，其中，所述根据所述目标膨胀检测框、所 述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径，包括：
    根据所述目标膨胀检测框确定所述目标膨胀检测框中所有顶点；
    根据所述目标膨胀检测框中所有顶点到所述车道边界线信息中第一边界线上的距离确定最小距离，并根据所述最小距离和所述最小距离对应的顶点，确定第一行驶离散点；
    根据所述第一行驶离散点、所述车道边界线信息、所述目标车辆的预设速度信息和预设时长信息，确定第二行驶离散点；
    根据所述目标车辆的当前位置信息、所述第一行驶离散点信息和所述第二行驶离散点信息，确定至少一条待使用避障行驶路径。
  6. 根据权利要求1所述的方法，其中，所述根据所述待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定目标避障行驶路径，包括：
    针对所述目标膨胀检测框，确定当前目标膨胀检测框中所有顶点到当前待使用避障行驶路径中各个离散点的距离信息；
    基于所有所述距离信息大于所述目标车辆在垂直方向上的宽度信息的判断结果，确定所述当前待使用避障行驶路径为所述目标避障行驶路径。
  7. 根据权利要求6所述的方法，所述方法还包括：
    基于所有所述距离信息中存在距离信息不大于所述目标车辆在垂直方向上的宽度信息的判断结果，确定所述当前待使用避障行驶路径不为所述目标避障路径；
    基于所有所述待使用避障行驶路径均不为所述目标避障行驶路径的判断结果，更新与目标障碍物信息相对应的膨胀属性信息，以基于更新后的膨胀属性 信息，重新确定与所述目标车辆相对应的目标避障行驶路径。
  8. 一种避障装置，应用于车辆，包括：
    障碍物信息获取模块，被设置为获取目标车辆预设区域范围内的目标障碍物信息；
    膨胀检测框确定模块，被设置为确定与目标障碍物信息相对应的目标膨胀检测框；
    避障行驶路径确定模块，被设置为根据所述目标膨胀检测框、所述目标车辆的当前位置信息以及所述目标车辆所属行驶道路的车道边界线信息，确定与所述目标车辆相对应的至少一条待使用避障行驶路径；
    目标避障行驶路径确定模块，被设置为根据所述待使用避障行驶路径中离散点与目标膨胀检测框之间的相对位置信息，确定目标避障行驶路径。
  9. 一种电子设备，所述电子设备包括：
    处理器；
    存储装置，被设置为存储程序，
    在所述程序被所述处理器执行时，所述处理器实现如权利要求1-7中任一所述的避障方法。
  10. 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程序，所述计算机程序被处理器执行时实现如权利要求1-7中任一所述的避障方法。
PCT/CN2022/126903 2021-10-26 2022-10-24 避障方法、装置、电子设备和存储介质 WO2023071959A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111247962.3 2021-10-26
CN202111247962.3A CN113928340B (zh) 2021-10-26 应用于车辆中的避障方法、装置、电子设备和存储介质

Publications (1)

Publication Number Publication Date
WO2023071959A1 true WO2023071959A1 (zh) 2023-05-04

Family

ID=79284252

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/126903 WO2023071959A1 (zh) 2021-10-26 2022-10-24 避障方法、装置、电子设备和存储介质

Country Status (1)

Country Link
WO (1) WO2023071959A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116974286A (zh) * 2023-08-25 2023-10-31 上海木蚁机器人科技有限公司 调整无人车跟随控制点的避障方法、装置、设备和介质
CN117021094A (zh) * 2023-08-20 2023-11-10 哈尔滨理工大学 一种适用于狭窄空间的盾构机换刀机器人路径规划方法
CN117021094B (zh) * 2023-08-20 2024-04-26 哈尔滨理工大学 一种适用于狭窄空间的盾构机换刀机器人路径规划方法

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170236422A1 (en) * 2014-09-29 2017-08-17 Hitachi Construction Machinery Co., Ltd. Obstacle avoidance system
CN110550029A (zh) * 2019-08-12 2019-12-10 华为技术有限公司 障碍物避让方法及装置
CN110614992A (zh) * 2018-12-29 2019-12-27 长城汽车股份有限公司 车辆自动驾驶时避障的方法、系统及车辆
CN111332285A (zh) * 2018-12-19 2020-06-26 长沙智能驾驶研究院有限公司 车辆避开障碍物的方法及装置、电子设备和存储介质
JP2020163975A (ja) * 2019-03-29 2020-10-08 マツダ株式会社 車両運転支援システム
CN112015181A (zh) * 2020-08-28 2020-12-01 上海高仙自动化科技发展有限公司 一种避障方法、装置、设备及计算机可读存储介质
CN112230634A (zh) * 2019-06-26 2021-01-15 北京海益同展信息科技有限公司 一种机器人避障方法和装置
JP2021041754A (ja) * 2019-09-09 2021-03-18 日産自動車株式会社 運転制御方法及び運転制御装置
CN113104033A (zh) * 2021-05-11 2021-07-13 东风柳州汽车有限公司 低速自动驾驶方法、装置、设备及存储介质
CN113928340A (zh) * 2021-10-26 2022-01-14 中国第一汽车股份有限公司 应用于车辆中的避障方法、装置、电子设备和存储介质

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170236422A1 (en) * 2014-09-29 2017-08-17 Hitachi Construction Machinery Co., Ltd. Obstacle avoidance system
CN111332285A (zh) * 2018-12-19 2020-06-26 长沙智能驾驶研究院有限公司 车辆避开障碍物的方法及装置、电子设备和存储介质
CN110614992A (zh) * 2018-12-29 2019-12-27 长城汽车股份有限公司 车辆自动驾驶时避障的方法、系统及车辆
JP2020163975A (ja) * 2019-03-29 2020-10-08 マツダ株式会社 車両運転支援システム
CN112230634A (zh) * 2019-06-26 2021-01-15 北京海益同展信息科技有限公司 一种机器人避障方法和装置
CN110550029A (zh) * 2019-08-12 2019-12-10 华为技术有限公司 障碍物避让方法及装置
JP2021041754A (ja) * 2019-09-09 2021-03-18 日産自動車株式会社 運転制御方法及び運転制御装置
CN112015181A (zh) * 2020-08-28 2020-12-01 上海高仙自动化科技发展有限公司 一种避障方法、装置、设备及计算机可读存储介质
CN113104033A (zh) * 2021-05-11 2021-07-13 东风柳州汽车有限公司 低速自动驾驶方法、装置、设备及存储介质
CN113928340A (zh) * 2021-10-26 2022-01-14 中国第一汽车股份有限公司 应用于车辆中的避障方法、装置、电子设备和存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117021094A (zh) * 2023-08-20 2023-11-10 哈尔滨理工大学 一种适用于狭窄空间的盾构机换刀机器人路径规划方法
CN117021094B (zh) * 2023-08-20 2024-04-26 哈尔滨理工大学 一种适用于狭窄空间的盾构机换刀机器人路径规划方法
CN116974286A (zh) * 2023-08-25 2023-10-31 上海木蚁机器人科技有限公司 调整无人车跟随控制点的避障方法、装置、设备和介质

Also Published As

Publication number Publication date
CN113928340A (zh) 2022-01-14

Similar Documents

Publication Publication Date Title
EP3321757B1 (en) Planning feedback based decision improvement system for autonomous driving vehicle
CN111750886B (zh) 局部路径规划方法及装置
US10943485B2 (en) Perception assistant for autonomous driving vehicles (ADVs)
JP6667686B2 (ja) 自動運転車両のための走行軌跡生成方法、システム及び機械可読媒体
US20190382031A1 (en) Methods for handling sensor failures in autonomous driving vehicles
US11520335B2 (en) Determining driving paths for autonomous driving vehicles based on map data
US9889847B2 (en) Method and system for driver assistance for a vehicle
JP6975775B2 (ja) 自動運転車両の高速道路における自動運転に用いる、地図及びポジショニングなしで車線に沿う走行方法
US20180307234A1 (en) Lane curb assisted off-lane checking and lane keeping system for autonomous driving vehicles
US10983522B2 (en) Emergency stop speed profile for autonomous vehicles
US10549752B2 (en) Deceleration curb-based direction checking and lane keeping system for autonomous driving vehicles
KR102309496B1 (ko) 자율 주행 차량을 위한 자기 위치 측정 방법, 시스템 및 기계 판독 가능한 매체
CN113335276A (zh) 障碍物的轨迹预测方法、装置、电子设备及存储介质
US11180160B2 (en) Spiral curve based vertical parking planner system for autonomous driving vehicles
CN111797780A (zh) 一种跟车轨迹规划方法、装置、服务器及存储介质
CN111006681B (zh) 一种辅助导航方法、装置、设备和介质
CN111380546A (zh) 基于平行道路的车辆定位方法、装置、电子设备和介质
WO2023025007A1 (zh) 车辆避让方法、装置、车载设备及存储介质
WO2023071959A1 (zh) 避障方法、装置、电子设备和存储介质
JP2010140265A (ja) 走行支援装置、方法およびプログラム
CN113928340B (zh) 应用于车辆中的避障方法、装置、电子设备和存储介质
WO2019127076A1 (en) Automated driving vehicle control by collision risk map
CN110497906B (zh) 车辆控制方法、装置、设备和介质
WO2022254535A1 (ja) 走行領域判定装置および走行領域判定方法
CN115900645B (zh) 一种车辆高程计算方法、装置、电子设备及存储介质

Legal Events

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

Ref document number: 22885836

Country of ref document: EP

Kind code of ref document: A1