WO2022001708A1 - 车辆控制方法、装置、车辆及存储介质 - Google Patents

车辆控制方法、装置、车辆及存储介质 Download PDF

Info

Publication number
WO2022001708A1
WO2022001708A1 PCT/CN2021/101036 CN2021101036W WO2022001708A1 WO 2022001708 A1 WO2022001708 A1 WO 2022001708A1 CN 2021101036 W CN2021101036 W CN 2021101036W WO 2022001708 A1 WO2022001708 A1 WO 2022001708A1
Authority
WO
WIPO (PCT)
Prior art keywords
path
vehicle
paths
preview point
smoothing
Prior art date
Application number
PCT/CN2021/101036
Other languages
English (en)
French (fr)
Inventor
沈峥
潘杨杰
张应鹏
陈超越
邱明喆
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2022001708A1 publication Critical patent/WO2022001708A1/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
    • B60W60/005—Handover processes
    • B60W60/0051—Handover processes from occupants to vehicle
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/10—Path keeping
    • 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions

Definitions

  • the present application relates to the field of driving, and in particular, to a vehicle control method, device, vehicle and storage medium.
  • the current automatic driving (automated driving/ADS) technology can be used for smart/intelligent car.
  • the automatic driving technology is to plan the path through the path planning module of the vehicle, and the vehicle controls itself to complete the driving process automatically based on the planned path.
  • the driving path of the vehicle may be different from the user's needs.
  • the user may take over the vehicle and drive it manually.
  • the vehicle exits the automatic driving mode and enters the manual driving mode.
  • the user may need the vehicle to continue to drive automatically after driving manually for a period of time, the user can only stop the vehicle at present, and manually turn on the automatic driving mode again, so that the vehicle can continue to drive automatically. Therefore, the current automatic driving efficiency is low.
  • the present application provides a vehicle control method, device, vehicle and storage medium to improve the efficiency of automatic driving.
  • the technical solution is as follows:
  • the present application provides a method for controlling a vehicle.
  • the smoothing errors of N paths are obtained, and the N paths are obtained when the vehicle enters the manual driving mode.
  • the previously planned path, N is an integer greater than 1
  • the smoothing error of the first path is used to indicate the smoothness of the transition of the vehicle from the first position to the first path
  • the first position is the current position of the vehicle
  • the first path is the any of the N paths.
  • one path is selected from the N paths as the second path; according to the second path, the vehicle is controlled to drive automatically.
  • the smoothing error of each of the N paths that have been planned before entering the manual driving mode is obtained, and one path is selected as the second path according to the smoothing error of each path.
  • the automatic driving of the vehicle is controlled according to the second path, so that the automatic driving mode does not need to be stopped and restarted, and the efficiency of automatic driving is improved.
  • the smoothing error of the path is used to indicate the smoothness of the transition of the vehicle from the first position to the first path, and because of the second path selected based on the smoothing error, the vehicle can be controlled to transition from the first position to the second relatively smoothly path, improving the comfort and safety of autonomous driving.
  • a preview point is determined according to the motion information of the vehicle, the preview point is a position to be reached by the vehicle within a specified time length, and the preview point is located on the first path; according to the preview point and the driving direction of the vehicle to obtain the smoothing error of the first path. Since the preview point is the position where the vehicle will arrive on the first path within a specified period of time, both the preview point and the driving direction of the vehicle can reflect the trajectory and rotation angle that the vehicle needs to travel from the first position to the preview point. , the trajectory and angle include the smoothness of the transition of the vehicle from the first position to the first path, so as to achieve the smooth error of accurately obtaining the first path.
  • the preview point is mapped to the vehicle coordinate system of the vehicle, and the lateral coordinate of the preview point in the vehicle coordinate system is obtained;
  • the angle between the lines is used to obtain the smoothing error of the first path, and the first tangent is the tangent of the first path at the preview point.
  • the lateral coordinate reflects the lateral offset of the vehicle from the first position to the preview point, and the included angle reflects the angle that the vehicle needs to turn when filtering to the preview point. Get the smoothing error for the first path.
  • an area including N paths is determined; when the first position is located in the area, the smoothing errors of the N paths are obtained.
  • This area is a safe area, and there may be no obstacles in this area. Therefore, when the first position is located in this area, the control vehicle may not collide with obstacles on the path from the first position to the preview point, thereby improving the driving safety.
  • At least one path to be driven is planned by a path planning module of the vehicle, and the vehicle is controlled to drive automatically according to the at least one path.
  • An obstacle may exist outside the area, and if the first position is outside the area, reaching any one of the N paths from the first position may collide with the obstacle. Therefore, when the first position is outside the area, the path is re-planned, the re-divided path avoids obstacles, and automatic driving is based on the re-divided path, which improves driving safety.
  • the at least one path is displayed; when the user's selection operation on the third path is detected, the third path is acquired, and the third path is one of the at least one paths; according to The third path controls the autonomous driving of the vehicle. In this way, human-computer interaction is realized, allowing users to choose the path they need or expect to meet the needs of users.
  • a path parameter of a fourth path is obtained, the fourth path is a path traveled by the vehicle in the time period when the manual driving mode is used, and the path parameter is used by the path planning module of the vehicle to plan the path based on the path parameter. At least one path that the vehicle is to travel after traveling the second path. Since the fourth path is a path manually driven by the user, the path parameters of the fourth path reflect the user's driving habits, and the vehicle's path planning module plans a path that conforms to the user's driving habits based on the path parameters.
  • the present application provides an apparatus for controlling a vehicle, for executing the method in the first aspect or any possible implementation manner of the first aspect.
  • the apparatus includes means for performing the method of the first aspect or any one of possible implementations of the first aspect.
  • the present application provides an apparatus for controlling a vehicle, the apparatus comprising: a processor, a memory and a transceiver.
  • the processor, the memory and the transceiver may be connected through a bus system.
  • the memory is used to store one or more programs, and the processor is used to execute the one or more programs in the memory to cause the apparatus to perform the method of the first aspect or any possible implementation of the first aspect.
  • the present application provides a computer-readable storage medium, where program codes are stored in the computer-readable storage medium, which, when run on a computer, enables the computer to execute the first aspect or any possible implementation of the first aspect method in method.
  • the present application provides a computer program product comprising program code, which, when run on a computer, causes the computer to execute the method of the first aspect or any possible implementation manner of the first aspect.
  • the present application provides a vehicle, comprising the device of the second aspect or the device of the third aspect.
  • FIG. 1 is a schematic structural diagram of a vehicle provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of a planned route provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of another planned route provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram of a driving path of a manually-driven vehicle provided by an embodiment of the present application.
  • FIG. 5 is a flowchart of a method for controlling a vehicle provided by an embodiment of the present application.
  • FIG. 6 is a schematic diagram of a preview point provided by an embodiment of the present application.
  • FIG. 7 is a schematic diagram of a vehicle coordinate system provided by an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a device for controlling a vehicle provided by an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a controller provided by an embodiment of the present application.
  • an embodiment of the present application provides a vehicle 1 , the vehicle 1 includes a controller 11 , a perception system 12 , a positioning system 13 and a path planning module 14 , the controller 11 , the perception system 12 , the positioning system 13 and the path planning
  • the modules 14 are all installed on the body of the vehicle 1 .
  • the controller 11 establishes communication connections with the positioning system 13 and the path planning module 14 respectively.
  • the path planning module 14 also establishes communication connections with the perception system 12 and the positioning system 13 .
  • the controller 11 , the perception system 12 , the positioning system 13 and the path planning module 14 may be connected to a controller area network (CAN) bus of the vehicle 1 .
  • the controller 11 establishes a communication connection with the positioning system 13 and the path planning module 14 respectively through the CAN bus, and the path planning module 14 also establishes a communication connection with the sensing system 12 and the positioning system 13 through the CAN bus.
  • CAN controller area network
  • the perception system 12 When the vehicle 1 needs to drive automatically, the perception system 12 is used to perceive the environmental information around the vehicle 1, and send the perceived environmental information to the path planning module 14; The module 14 transmits the motion information of the vehicle 1 .
  • the sensing system 12 can periodically sense environmental information around the vehicle 1 and send the sensed environmental information to the path planning module 14 .
  • the positioning system 13 can also periodically acquire the motion information of the vehicle 1 and send the motion information of the vehicle 1 to the path planning module 14 .
  • the path planning module 14 is used to receive the environmental information around the vehicle 1 sent by the perception system 12, and the movement information of the vehicle 1 sent by the positioning system 13. Based on the received environmental information and movement information of the vehicle 1, plan the first time period. At least one path to travel within. The first time period is located after the current time, the time length of the first time period is the specified first time length, the starting position of each path in the at least one path is the same, and the length of each path is based on the movement of the vehicle 1 information and the first length of time is determined. The controller 11 then selects one path from the at least one path, and controls the vehicle 1 to automatically drive for the first time period based on the selected one path.
  • the path planning module 14 is also used to continue to receive the environmental information around the vehicle 1 sent by the perception system 12, and to receive the motion information of the vehicle 1 sent by the positioning system 13, and continue to plan based on the received environmental information and motion information of the vehicle 1.
  • the second time period is located after the first time period, the time length of the second time period is the specified first time length, and the starting positions of each of the at least one route to be traveled in the second time period are the same,
  • the starting position may be the end position of a path selected by the controller 11 from at least one path to be traveled in the first time period, and the length of each path to be traveled in the second time period is based on the motion information of the vehicle 1 and the first time period. a certain length of time.
  • the controller 11 selects a route from at least one route to be driven in the second time period, and controls the vehicle 1 to drive automatically during the second time period based on the selected one route.
  • the path planning module 14 and the controller 11 repeat the above process to continuously control the automatic driving of the vehicle 1 .
  • the path planning module 14 plans 4 paths to be traveled in the first time period according to the received environmental information and motion information of the vehicle 1 , and the 4 paths are paths 1a, 1b, 1c and 1d, the starting positions of the 4 paths are the same.
  • the controller 11 selects the route 1a from the four routes, and controls the vehicle 1 to drive automatically within the first time period according to the selected route 1a.
  • the path planning module 14 continues to receive the environmental information and motion information of the vehicle 1, and continues to plan 3 paths to be traveled in the second time period, the 3 paths are paths 2a, 2b and 2c, respectively.
  • the starting positions of the paths are the same, which are the end positions of path 1a.
  • the controller 11 selects the route 2a from the three routes, and controls the vehicle 1 to drive automatically in the second time period according to the selected route 2a.
  • the controller 11 and the path planning module 14 repeat the above process to control the vehicle 1 to drive automatically.
  • the surroundings of the vehicle 1 may include obstacles, and the environment information around the vehicle 1 may include the type and motion information of the obstacles.
  • the movement information of the obstacle includes at least one of the position, movement speed, movement acceleration and movement direction of the obstacle. Among them, for an obstacle in a stationary state, the motion speed and motion acceleration are both 0.
  • the motion information of the vehicle 1 includes at least one of the position, the motion speed, the motion acceleration, and the motion direction of the vehicle 1 .
  • the sensing system 12 includes at least one sensing sensor, and the at least one sensing sensor includes one or more of a camera, a radar, and the like.
  • the radar includes one or more of millimeter-wave radar, lidar, and ultrasonic radar.
  • the positioning system 13 is a global positioning system (global positioning system, GPS) or a Beidou navigation system or the like.
  • the selected path may be different from the needs of the user.
  • the user may directly use the steering wheel of the vehicle 1 for manual driving.
  • the user may stop using the steering wheel for manual driving, and again the controller 11 needs to continue to control the vehicle 1 to perform automatic driving from the current position.
  • the current position at this time is called the first position.
  • the controller 11 controls the vehicle 1 to drive automatically according to the selected path 2a
  • the user manually drives the vehicle 1 using the steering wheel, so that the vehicle 1 deviates from the path 2a and continues drive.
  • the controller 11 needs to continue to control the vehicle 1 from the first position 32 for automatic driving.
  • the above-mentioned mode in which the user manually drives the vehicle 1 using the steering wheel is referred to as a manual driving mode
  • the above-mentioned mode in which the controller 11 controls the driving of the vehicle 1 is referred to as an automatic driving mode.
  • the vehicle 1 exits the manual driving mode and enters the automatic driving mode the detailed implementation process of how to control the automatic driving of the vehicle 1 will be implemented by any of the following embodiments.
  • an embodiment of the present application provides a method for automatic driving.
  • the method is applied to the vehicle shown in FIG. 1 , and the method can be executed by a controller in the vehicle, including:
  • Step 501 When it is detected that the vehicle exits the manual driving mode and enters the automatic driving mode, obtain N paths, the N paths are the paths that the vehicle has planned before entering the manual driving mode, and N is an integer greater than 1.
  • the driving mode of the vehicle is the automatic driving mode
  • the path planning module of the vehicle plans N paths
  • the vehicle drives automatically based on one of the N paths.
  • the user can manually turn the steering wheel to perform manual driving.
  • the vehicle exits the automatic driving mode and enters the manual driving mode.
  • the user stops using the steering wheel for manual driving, at which time the vehicle exits the manual driving mode and enters the automatic driving mode.
  • the path planning module of the vehicle plans three paths, namely paths 2a, 2b and 2c, and the vehicle performs automatic driving based on path 2a among the three paths.
  • the vehicle is automatically driven to position 31, the user manually turns the steering wheel to perform manual driving, and the vehicle enters the manual driving mode.
  • the user manually drives to the position 32, he stops using the steering wheel for manual driving, and at this time, the vehicle exits the manual driving mode and enters the automatic driving mode.
  • this step the driving mode that the vehicle is in needs to be detected, and this step is performed when it is detected that the vehicle exits the manual driving mode and enters the automatic driving mode.
  • implementation instance can be:
  • the torque of the steering wheel of the vehicle is obtained in real time, and the torque of the steering wheel obtained each time is determined.
  • the torque of the steering wheel changes from less than the torque threshold to greater than the torque threshold.
  • the torque of the steering wheel of the vehicle is also obtained in real time, and the torque of the steering wheel obtained each time is determined.
  • the N paths are the paths last planned by the path planning module of the vehicle before the vehicle enters the manual driving mode from the automatic driving mode.
  • the vehicle enters the manual driving mode from the automatic driving mode when driving to the position 31
  • the most recent path planned by the path planning module of the vehicle includes paths 2 a , 2 b and 2 c .
  • the vehicle enters the automatic drive mode from the manual drive mode when the user manually drives to position 32 . Therefore, in this step, when it is detected that the vehicle exits the manual driving mode, the routes 2a, 2b and 2c are acquired.
  • Step 502 Obtain the preview point on each of the N paths, wherein the preview point on the first path is located on the first path and is the position to be reached by the vehicle within the specified second time length,
  • the first path is any one of the N paths.
  • the vehicle before the vehicle enters the manual driving mode, the vehicle performs automatic driving based on one of the N paths.
  • the vehicle When the vehicle is in the manual driving mode, the user drives the vehicle with the steering wheel of the vehicle, and the path that the user drives the vehicle manually will deviate from this path. Therefore, when the vehicle exits the manual driving mode, the current position of the vehicle may not be in the N paths. On any path, for the convenience of description, the current position when the vehicle exits the manual driving mode is referred to as the first position.
  • the vehicle before the vehicle enters the manual driving mode, the vehicle performs automatic driving based on the path 2a.
  • the path that the user drives the vehicle on deviates from the path 2a, so when the vehicle exits the manual driving mode, The first position 32 of the vehicle is not on the paths 2a, 2b and 2c.
  • the preview point of the path is the position where the vehicle is expected to transition from the first position to the access point on the path.
  • a preview point on the first path is determined according to the motion information of the vehicle.
  • the motion information of the vehicle and the first position that is, the current position of the vehicle
  • the distance is a radius, and a circle is determined; for the first path, one or more intersections where the first path intersects the circle are determined; if there is an intersection in the one or more intersections that are located in front of the vehicle, the intersection will be located in front of the vehicle. It is determined as a preview point on the first path; if none of the one or more intersection points is located in front of the vehicle, the end position of the first path is determined as a preview point on the first path.
  • the motion information of the vehicle is acquired through a positioning system of the vehicle, where the motion information includes the motion speed, acceleration, and motion direction of the vehicle. According to the moving speed and acceleration of the vehicle and the second time length, the distance traveled by the vehicle within the second time length is obtained.
  • the first position is the position in the world coordinate system.
  • the position of the intersection point in the world coordinate system is obtained, and the position of the intersection point can be determined according to the first position and the position of the intersection point. Whether the intersection is in front of the vehicle.
  • the first position 32 of the vehicle is acquired through the positioning system included in the vehicle 1 , and the motion information such as the motion speed, acceleration, and motion direction of the vehicle is acquired.
  • the motion information such as the motion speed, acceleration, and motion direction of the vehicle
  • the second time length the moving speed and acceleration of the vehicle
  • the distance traveled by the vehicle in the second time length is obtained.
  • a circle is determined.
  • the intersection point L of the path 2a and the circle is determined.
  • the intersection point L is not located in front of the vehicle, then the end point position K of the path 2a is determined Determined as the preview point on path 2a.
  • For the path 2b determine the intersection G and H where the path 2b intersects the circle, the intersection H is located in front of the vehicle, then the intersection H is determined as the preview point on the path 2b.
  • For the path 2c determine the intersection points E and F where the path 2c intersects the circle, and the intersection point F is located in front of the vehicle, then the intersection point F is determined as the preview point on the path 2c.
  • the area including the N paths is determined.
  • the area is the smallest area including the N paths. This step is performed when the first location is in the area. That is, when the first position is located in the area, a preview point on each of the N paths is obtained.
  • at least one path to be driven is planned by a path planning module of the vehicle, and the vehicle is controlled to drive automatically according to the at least one path.
  • one path is selected from the at least one path, and the vehicle is controlled to drive automatically based on the selected one path.
  • the N paths are planned by the path planning module based on the environmental information around the vehicle.
  • the paths planned by the path planning module are relatively safe, and the vehicle will not encounter obstacles around the vehicle when driving automatically based on any of the planned paths. Collision, the obstacle is other vehicles or pedestrians, etc.
  • This area is an area surrounded by the N paths, so there may be no obstacles in this area. Therefore, when the first position is located in this area, control the vehicle to transition to one of the N paths in this area. On the path, the vehicle will not collide with obstacles, which improves the safety of autonomous driving.
  • the path planning module directly senses the surrounding environment information of the vehicle according to the perception system and obtains the motion information of the vehicle from the positioning system, plans at least one path, and automatically drives based on the at least one path.
  • the minimum area including the paths 2a, 2b and 2c is the area NMJKN, wherein the first position 32 is located in the minimum area NMJKN, then the preview point K located on the path 2a and located on the path 2b is obtained through this step.
  • Step 503 Obtain the smoothing error of each path according to the preview point of each path and the driving direction of the vehicle.
  • the smoothing error of the first path is obtained according to the preview point on the first path and the driving direction of the vehicle, and the smoothing error of the first path is used to indicate the vehicle The smoothness of the transition from the first position to the first path.
  • the smoothing error of the first path can be obtained through the following 5031 to 5032, where the 5031 to 5032 are respectively:
  • the absolute value of the lateral coordinate of the preview point is equal to the lateral offset of the vehicle from the first position to the preview point.
  • the vehicle coordinate system is determined.
  • the vehicle coordinate system takes the position of the target point included in the vehicle as the coordinate origin, the heading direction of the vehicle as the x-axis, and the direction perpendicular to the vehicle's head orientation as the y-axis.
  • the conversion relationship between the vehicle coordinate system and the world coordinate system is determined, and based on the conversion relationship, the preview point is mapped to the vehicle coordinate system of the vehicle to obtain the first path.
  • the lateral coordinate of the preview point in the vehicle coordinate system is determined.
  • the target point is the center of the rear axle of the vehicle, the center of the vehicle, the center of the front axle of the vehicle, or the like.
  • the target point is the rear axle center 33 of the vehicle
  • the position of the target point 33 is used as the coordinate origin
  • the direction of the front of the vehicle is the x-axis
  • the direction perpendicular to the front of the vehicle is the y-axis.
  • the position of the target point 33 in the world coordinate system is acquired, and the conversion relationship between the vehicle coordinate system and the world coordinate system is determined based on the position of the target point 33 .
  • the preview point K of the path 2a based on the conversion relationship, the preview point K is mapped to the vehicle coordinate system of the vehicle to obtain the lateral coordinate xa of the preview point K on the path 2a in the vehicle coordinate system.
  • the preview point H of the path 2b based on the conversion relationship, the preview point H is mapped to the vehicle coordinate system of the vehicle to obtain the lateral coordinate xb of the preview point H on the path 2b in the vehicle coordinate system.
  • the preview point F of the path 2c based on the conversion relationship, the preview point F is mapped to the vehicle coordinate system of the vehicle to obtain the lateral coordinate xc of the preview point F on the path 2c in the vehicle coordinate system.
  • the first tangent line is the tangent line of the first path at the preview point, and obtain the angle between the driving direction of the vehicle and the first tangent line, according to The absolute value of the lateral coordinate and the angle between the traveling direction of the vehicle and the first tangent line obtain the smoothing error of the first path.
  • the included angle reflects the angle that the vehicle needs to rotate when transitioning to the preview point, and when the vehicle reaches the preview point, the traveling direction of the vehicle is parallel to the first tangent.
  • the curvature of the first path at its preview point can be obtained, and based on the curvature, the first all of the first path at the preview point can be determined.
  • direction of the line The driving direction of the vehicle can be obtained in real time through the vehicle's positioning system. Based on the direction of the first tangent and the traveling direction of the vehicle, an angle between the traveling direction of the vehicle and the first tangent can be obtained.
  • the smoothing error of the first path is obtained according to the following first formula.
  • err is the smoothing error of the first path
  • x is the lateral coordinate of the preview point
  • ⁇ is the included angle
  • a and b are two weights.
  • the preview point K on the path 2a determine the first tangent 34 of the path 2a at the preview point K, and obtain the angle between the traveling direction of the vehicle and the first tangent 34, according to The horizontal coordinate xa of the preview point and the angle between the traveling direction of the vehicle and the first tangent 34 are used to obtain the smoothing error of the path 2a.
  • the lateral coordinate xc, and the angle between the driving direction of the vehicle and the first tangent 36 obtain the smoothing error of the path 2c.
  • Step 504 According to the smoothing errors of the N paths, select one path from the N paths as the second path.
  • a path with the smallest smoothing error is selected from the N paths as the second path.
  • path 2b is selected from path 2a, path 2b, and path 2c based on the smoothing error of path 2a, the smoothing error of path 2b, and the smoothing error of path 2c.
  • the smoothing error of the second path is the smallest, and the smoothing error of the second path is used to indicate the smoothness of the transition of the vehicle from the first position to the second path, the transition of the control vehicle to the selected second path is the most stable, and it is necessary to turn the vehicle
  • the angle of the driving direction is the smallest.
  • the smoothing error of the selected path 2b is the smallest, and the angle required to turn the vehicle's traveling direction to control the transition of the vehicle from the first position 32 to the preview point H of the selected path 2b is the smallest. So the transition from the first position to path 2b is the smoothest and safest.
  • Step 505 Control the vehicle to drive automatically according to the second path.
  • the vehicle is controlled to automatically drive from the first position to the preview point of the second path, and the driving direction of the vehicle at the preview point of the second path is parallel to the first tangent, and the first tangent is the first tangent.
  • the tangent of the second path at the preview point. Controlling the second path controls the vehicle to continue autonomous driving from the preview point.
  • the vehicle is controlled to automatically drive from the first position 32 to the preview point H of the path 2b, and the driving direction of the vehicle at the preview point H is parallel to the tangent 35 of the path 2b at the preview point H.
  • the path parameters of the fourth path can also be obtained, and the fourth path is the path the vehicle travels during the time period when the manual driving mode is used, so that the path planning module of the vehicle can plan the vehicle to plan the vehicle after driving the first path based on the path parameters.
  • the path parameter of the fourth path includes at least one of curvature and smoothness of the fourth path.
  • the path parameters of the fourth path may also be obtained, so that the path planning module of the vehicle plans at least one path based on the path parameters, from One path is selected from the at least one path, and the vehicle is controlled to continue automatic driving based on the selected one path.
  • the fourth path is the path where the user manually drives the vehicle, so the path parameters of the fourth path are used to reflect the user's driving habits. Therefore, the path planning module introduces the path of the fourth path when planning the path based on the vehicle's environmental information and motion information. parameters, so that the path planning module can plan a path that conforms to the user's driving habits based on the environmental information and motion information of the vehicle and the path parameters of the fourth path.
  • the cost parameter of each path in the at least one path is obtained, and the cost parameter of the path is used to reflect at least one of the user's driving style and habits, etc., according to each path.
  • the cost parameter of each path select a path.
  • the at least one path can also be displayed, so that the user can choose a path that meets his needs.
  • the third path is acquired, and the third path is one of the at least one paths; the vehicle is controlled to drive automatically according to the third path.
  • N paths that have been planned before entering the manual driving mode are acquired, an area including the N paths is determined, and the current position of the vehicle is located in the area.
  • the smoothing error of each path in the N paths is obtained, and a path is selected as the second path according to the smoothing error of each path, so that the vehicle can be automatically driven according to the second path, so that it is not necessary to stop and restart the automatic driving mode, Improve the efficiency of autonomous driving.
  • the second route is selected only when the current position of the vehicle is within the area, driving safety can be improved.
  • the smoothing error of the path is used to indicate how smoothly the vehicle transitions from the first position to the first path, and because of the second path selected based on the smoothing error, the vehicle can be controlled to transition from the first position to the second path more smoothly, Improve the comfort and safety of autonomous driving.
  • an embodiment of the present application provides an apparatus 800 for controlling a vehicle.
  • the apparatus 800 may be deployed on the vehicle controller of the embodiment shown in FIG. 1 or FIG. 5 , including:
  • the processing unit 801 is configured to obtain smooth errors of N paths when it is detected that the vehicle exits the manual driving mode, where the N paths are the paths that the vehicle has planned before entering the manual driving mode, N is an integer greater than 1, and the first
  • the smoothing error of the path is used to indicate the smoothness of the transition of the vehicle from the first position to the first path, the first position is the current position of the vehicle, and the first path is any one of the N paths; according to the smoothness of the N paths error, select one path from the N paths as the second path.
  • the control unit 802 is configured to control the automatic driving of the vehicle according to the second path.
  • step 504 for the detailed implementation process of selecting the second path by the processing unit 801, reference may be made to the relevant content in step 504 in the embodiment shown in FIG. 5 , which will not be described in detail here.
  • control unit 802 controlling the automatic driving of the vehicle, reference may be made to the relevant content in steps 505 to 503 in the embodiment shown in FIG. 5 , which will not be described in detail here.
  • processing unit 801 is configured to:
  • the preview point is the position to be reached by the vehicle within the specified time length, and the preview point is located on the first path;
  • the smoothing error of the first path is obtained.
  • processing unit 801 is configured to:
  • the smoothing error of the first path is obtained according to the lateral coordinates and the angle between the traveling direction of the vehicle and the first tangent, where the first tangent is the tangent of the first path at the preview point.
  • the processing unit 801 is configured to determine an area including N paths; when the first position is located in the area, obtain the smoothing errors of the N paths.
  • processing unit 801 is further configured to:
  • At least one path to be driven is planned by a path planning module of the vehicle, and the vehicle is controlled to drive automatically according to the at least one path.
  • the apparatus 800 further includes: a display unit 803,
  • a display unit 803, configured to display the at least one path
  • Control unit 802 for:
  • the third path is acquired, and the third path is one of the at least one paths; the vehicle is controlled to drive automatically according to the third path.
  • processing unit 801 is further configured to:
  • the fourth path is the path the vehicle travels during the time period when the manual driving mode is used, and the path parameters are used by the path planning module of the vehicle to plan the vehicle after the second path is driven based on the path parameters. At least one path to travel.
  • the apparatus 800 in this embodiment of the present application may be implemented by an application-specific integrated circuit (ASIC), or a programmable logic device (PLD), and the PLD may be a complex program logic device (complex programmable logical device, CPLD), field-programmable gate array (field-programmable gate array, FPGA), general array logic (generic array logic, GAL) or any combination thereof.
  • ASIC application-specific integrated circuit
  • PLD programmable logic device
  • the PLD may be a complex program logic device (complex programmable logical device, CPLD), field-programmable gate array (field-programmable gate array, FPGA), general array logic (generic array logic, GAL) or any combination thereof.
  • CPLD complex programmable logical device
  • FPGA field-programmable gate array
  • GAL general array logic
  • the apparatus 800 may correspond to executing the methods described in the embodiments of the present application, and the above-mentioned and other operations and/or functions of the various units in the apparatus 800 are respectively for implementing the corresponding methods of the respective methods in FIG. 5 .
  • the process, for the sake of brevity, will not be repeated here.
  • the processing unit when entering the automatic driving mode from the manual driving mode, acquires the smoothing error of each of the N paths planned before entering the manual driving mode, and selects the smoothing error according to the smoothing error of each path.
  • One path is used as the second path, so that the control unit controls the automatic driving of the vehicle according to the second path, so that the automatic driving mode does not need to be stopped and restarted, and the efficiency of automatic driving is improved.
  • the control unit can control the vehicle to transition from the first position more smoothly Transitioning to the second path improves the comfort and safety of autonomous driving.
  • an embodiment of the present application provides a schematic diagram of a controller 900 for controlling a vehicle.
  • the controller 900 may be the controller in any of the foregoing embodiments, for example, the controller 900 is the controller in the embodiment shown in FIG. 1 or the embodiment shown in FIG. 5 .
  • the controller 900 includes at least a processor 901 , a memory unit 902 , a storage medium 903 , a communication interface 904 and a bus system 905 .
  • the processor 901 , the memory unit 902 , the storage medium 903 , and the communication interface 904 communicate through the bus system 905 .
  • the processor 901 may invoke computer-executed instructions (eg, program codes) stored in the memory unit 902 to implement the operation steps performed by the controller in the embodiment shown in FIG. 5 .
  • the smoothing errors of N paths are obtained, the N paths are the paths that the vehicle has planned before entering the manual driving mode, N is an integer greater than 1, and the smoothing error of the first path is It is used to indicate the smoothness of the transition of the vehicle from the first position to the first path, the first position is the current position of the vehicle, and the first path is any one of the N paths; according to the smoothing errors of the N paths, from the N paths One path is selected as the second path; according to the second path, the vehicle is controlled to drive automatically.
  • computer-executed instructions eg, program codes
  • the computer-executable instructions and the operating system are stored in the storage medium 903, and when the apparatus 900 starts running, the processor 901 can load the computer-executable instructions and the operating system stored in the storage medium 903 into the memory unit 902, and The computer-executed instructions in the memory unit 902 are invoked and executed in the operating environment provided by the operating system.
  • the above-mentioned processor 901 may be a CPU, a microprocessor, an application-specific integrated circuit (application-specific integrated circuit, ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.
  • the processor 901 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 9 .
  • the processor 901 can also be other general-purpose processors, digital signal processing (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistors Logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or any conventional processor or the like.
  • bus system 905 in the controller 900 may also include a power bus, a control bus, a status signal bus, and the like. However, for clarity of illustration, the various buses are labeled as bus system 905 in the figure.
  • the above-mentioned communication interface 904 is used to communicate with other devices.
  • the processor 901 communicates with the sensing system and the positioning system through the communication interface 904, and the processor 901 communicates with the sensing system and the positioning system through the communication interface 904 to obtain the position and motion attribute information of obstacles around the moving object.
  • the storage medium 903 may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory.
  • the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM random access memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • Double data rate synchronous dynamic random access memory double data date SDRAM, DDR SDRAM
  • enhanced synchronous dynamic random access memory enhanced SDRAM, ESDRAM
  • synchronous link dynamic random access memory direct rambus RAM, DR RAM
  • bus 905 may also include a power bus, a control bus, a status signal bus, an in-vehicle bus (such as a controller area network (CAN) bus), and the like.
  • CAN controller area network
  • bus 305 the various buses are labeled as bus 305 in the figure.
  • controller 900 may correspond to the apparatus 800 in the embodiment of the present application, and may correspond to executing the corresponding subject in FIG. 5 according to the embodiment of the present application, and the various modules in the controller 900
  • the above and other operations and/or functions are respectively to implement the corresponding flow of each method in FIG. 5 , and are not repeated here for brevity.
  • the present application also provides a vehicle, which includes the controller 900 shown in FIG. 9 , and the controller 900 is configured to execute the operation steps of the corresponding subject in each method in the above-mentioned FIG. 5 , which will not be repeated here for brevity.
  • the above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination.
  • the above-described embodiments may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated.
  • the computer may be a general purpose computer, special purpose computer, computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server or data center Transmission to another website site, computer, server, or data center is by wire (eg, coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (eg, infrared, wireless, microwave, etc.).
  • the computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, or the like that contains one or more sets of available media.
  • the usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media.
  • the semiconductor medium may be a solid state drive (SSD).

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

一种车辆控制方法、装置、车辆及存储介质，属于驾驶领域。方法包括：在检测到车辆退出手动驾驶模式时，获取N条路径的平滑误差，N条路径是车辆在进入手动驾驶模式前已规划的路径，N为大于1的整数，第一路径的平滑误差用于指示车辆从第一位置过渡到第一路径的平稳程度，第一位置是车辆当前的位置，第一路径是N条路径中的任一条；根据N条路径的平滑误差，从N条路径中选择一条路径作为第二路径；根据第二路径，控制车辆自动驾驶。该方法能够提高自动驾驶的效率。

Description

车辆控制方法、装置、车辆及存储介质
本申请要求于2020年6月28日提交的申请号为202010598526.X、发明名称为“车辆控制方法、装置及车辆”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及驾驶领域，特别涉及一种车辆控制方法、装置、车辆及存储介质。
背景技术
目前的自动驾驶(automated driving/ADS)技术可用于智能车(smart/intelligent car)，自动驾驶技术是通过车辆的路径规划模块进行路径的规划，车辆基于规划的路径控制自身自动完成驾驶的过程。
车辆在基于规划的路径进行驾驶的过程，车辆行驶的路径可能与用户的需求不同，此时用户可能接管车辆，自己手动驾驶，车辆退出自动驾驶模式，进入手动驾驶模式。用户在手动驾驶一段时间后可能需要车辆继续自动驾驶时，目前只能停车，重新手动开启自动驾驶模式，使车辆继续自动驾驶。所以目前的自动驾驶效率较低。
发明内容
本申请提供了一种车辆控制方法、装置、车辆及存储介质，以提高自动驾驶的效率。所述技术方案如下：
第一方面，本申请提供了一种控制车辆的方法，在所述方法中：在检测到车辆退出手动驾驶模式时，获取N条路径的平滑误差，该N条路径是车辆在进入手动驾驶模式前已规划的路径，N为大于1的整数，第一路径的平滑误差用于指示车辆从第一位置过渡到第一路径的平稳程度，第一位置是车辆当前的位置，第一路径是该N条路径中的任一条。根据该N条路径的平滑误差，从该N条路径中选择一条路径作为第二路径；根据第二路径，控制车辆自动驾驶。
在从手动驾驶模式进入自动驾驶模式时，获取在进入手动驾驶模式之前已规划的N条路径中的每条路径的平滑误差，根据每条路径的平滑误差选择一条路径作为第二路径，这样便根据第二路径控制车辆自动驾驶，从而不需要停车重启自动驾驶模式，提高了自动驾驶的效率。另外，由于路径的平滑误差用于指示车辆从第一位置过渡到第一路径的平稳程度，又由于基于平滑误差选择的第二路径，所以能够控制车辆较平滑地从第一位置过渡到第二路径，提高了自动驾驶的舒适性和安全性。
在一种可能的实现方式中，根据车辆的运动信息确定预瞄点，该预瞄点是车辆在指定时间长度内待到达的位置，该预瞄点位于第一路径上；根据该预瞄点和车辆的行驶方向，获取第一路径的平滑误差。由于预瞄点是车辆在指定时间长度内待到达第一路径上的位置，所以预瞄点和车辆的行驶方向都能反映车辆从第一位置到预瞄点所需要行驶的轨迹和转动的角 度，该轨迹和角度包括车辆从第一位置过渡到第一路径的平稳程度，从而实现了准确获取第一路径的平滑误差。
在另一种可能的实现方式中，将预瞄点映射到车辆的车辆坐标系中，得到预瞄点在车辆坐标系中的横向坐标；根据该横向坐标，以及车辆的行驶方向与第一切线之间的夹角，获取第一路径的平滑误差，第一切线为第一路径在预瞄点处的切线。其中，横向坐标反映了车辆从第一位置到达预瞄点的横向偏移，该夹角反映了车辆在过滤到预瞄点所需要转动的角度，从而基于该横向坐标和该夹角可以准确地获取第一路径的平滑误差。
在另一种可能的实现方式中，确定包括N条路径的区域；在第一位置位于该区域中，获取N条路径的平滑误差。该区域是一个安全区域，该区域可能不存在障碍物等，所以当第一位置位于该区域内，控制车辆从第一位置过渡到预瞄点的路径上可能不会障碍物发生碰撞，从而提高了驾驶安全性。
在另一种可能的实现方式中，在第一位置位于该区域外，通过车辆的路径规划模块规划待行驶的至少一条路径，根据至少一条路径控制车辆自动驾驶。位于该区域外可能存在障碍物，在第一位置位于该区域外，从第一位置到达该N条路径中的任一条路径，可能会与障碍物发生碰撞。所以在第一位置位于该区域外，重新规划路径，重新划分的路径避开了障碍物，基于重新划分的路径自动驾驶，提高了驾驶安全性。
在另一种可能的实现方式中，显示所述至少一条路径；在检测到用户对第三路径的选择操作时，获取第三路径，第三路径是所述至少一条路径中的一条路径；根据第三路径控制车辆自动驾驶。从而实现了人机交互，可以让用户选择了自己需要或期望的路径，满足用户的需求。
在另一种可能的实现方式中，获取第四路径的路径参数，第四路径是在使用手动驾驶模式的时间段内车辆行驶的路径，路径参数用于车辆的路径规划模块基于路径参数，规划车辆在行驶完第二路径之后待行驶的至少一条路径。由于第四路径是用户手动驾驶的路径，所以第四路径的路径参数反映用户的驾驶习惯，车辆的路径规划模块基于路径参数，规划出符合用户驾驶习惯的路径。
第二方面，本申请提供了一种控制车辆的装置，用于执行第一方面或第一方面的任意一种可能实现方式中的方法。具体地，所述装置包括用于执行第一方面或第一方面的任意一种可能实现方式的方法的单元。
第三方面，本申请提供了一种控制车辆的装置，所述装置包括：处理器、存储器和收发器。其中，所述处理器、所述存储器和所述收发器之间可以通过总线系统相连。所述存储器用于存储一个或多个程序，所述处理器用于执行所述存储器中的一个或多个程序，使得所述装置完成第一方面或第一方面的任意可能实现方式中的方法。
第四方面，本申请提供了一种计算机可读存储介质，计算机可读存储介质中存储有程序代码，当其在计算机上运行时，使得计算机执行上述第一方面或第一方面的任意可能实现方式中的方法。
第五方面，本申请提供了一种包含程序代码的计算机程序产品，当其在计算机上运行时，使得计算机执行上述第一方面或第一方面的任意可能实现方式中的方法。
第六方面，本申请提供了一种车辆，包括第二方面所述的装置或第三方面所述的装置。
附图说明
图1是本申请实施例提供的一种车辆结构示意图；
图2是本申请实施例提供的一种规划的路径示意图；
图3是本申请实施例提供的另一种规划的路径示意图；
图4是本申请实施例提供的一种手动驾驶车辆行驶路径的示意图；
图5是本申请实施列提供的一种控制车辆的方法流程图；
图6是本申请实施例提供的预瞄点的示意图；
图7是本申请实施例提供的车辆坐标系的示意图；
图8是本申请实施例提供的一种控制车辆的装置结构示意图；
图9是本申请实施例提供的一种控制器的结构示意图。
具体实施方式
下面将结合附图对本申请实施方式作进一步地详细描述。
参见图1，本申请实施例提供了一种车辆1，该车辆1包括控制器11、感知系统12、定位系统13和路径规划模块14，控制器11、感知系统12、定位系统13和路径规划模块14均安装在车辆1的本体上，控制器11分别与定位系统13和路径规划模块14之间建立有通信连接，路径规划模块14还与感知系统12和定位系统13建立有通信连接。
可选的，控制器11、感知系统12、定位系统13和路径规划模块14可连接到车辆1的控制器局域网络(controller area network，CAN)总线上。控制器11通过CAN总线分别与定位系统13和路径规划模块14之间建立有通信连接，路径规划模块14通过CAN总线还与感知系统12和定位系统13建立有通信连接。
车辆1需要进行自动驾驶时，感知系统12用于感知车辆1周围的环境信息，向路径规划模块14发送感知到的环境信息；以及，定位系统13用于获取车辆1的运动信息，向路径规划模块14发送车辆1的运动信息。
可选的，感知系统12能够周期性地感知车辆1周围的环境信息，并向路径规划模块14发送感知的环境信息。同样，定位系统13也能够周期性地获取车辆1的运动信息，并向路径规划模块14发送车辆1的运动信息。
路径规划模块14用于接收感知系统12发送的车辆1周围的环境信息，以及接收定位系 统13发送的车辆1的运动信息，基于接收的车辆1的环境信息和运动信息，规划在第一时间段内待行驶的至少一条路径。第一时间段位于当前时间之后，第一时间段的时间长度为指定的第一时间长度，该至少一条路径中的每条路径的起始位置相同，每条路径的长度是基于车辆1的运动信息和第一时间长度确定的。然后控制器11从该至少一条路径中选择一条路径，基于选择的一条路径，在第一时间段内控制车辆1自动驾驶。
路径规划模块14还用于继续接收感知系统12发送的车辆1周围的环境信息，以及接收定位系统13发送的车辆1的运动信息，继续基于接收的车辆1的环境信息和运动信息，规划在第二时间段内待行驶的至少一条路径。第二时间段位于第一时间段之后，第二时间段的时间长度为指定的第一时间长度，第二时间段内待行驶的至少一条路径中的每条路径的起始位置相同，该起始位置可能是控制器11从第一时间段内待行驶的至少一条路径中选择的一条路径的终点位置，第二时间段内待行驶的每条路径的长度是基于车辆1的运动信息和第一时间长度确定的。然后控制器11从第二时间段内待行驶的至少一条路径中选择一条路径，基于选择的一条路径，在第二时间段控制车辆1自动驾驶。路径规划模块14和控制器11重复上述过程，不断地控制车辆1自动驾驶。
例如，参见图2，假设，路径规划模块14根据接收的车辆1的环境信息和运动信息，规划出在第一时间段内待行驶的4条路径，该4条路径分别为路径1a、1b、1c和1d，该4条路径的起始位置相同。控制器11从该4条路径中选择了路径1a，根据选择的路径1a，在第一时间段内控制车辆1自动驾驶。
参见图3，路径规划模块14继续接收车辆1的环境信息和运动信息，并继续规划出在第二时间段待行驶的3条路径，该3条路径分别为路径2a、2b和2c，该3条路径的起始位置相同，均为路径1a的终点位置。控制器11从该3条路径中选择了路径2a，根据选择的路径2a，在第二时间段内控制车辆1自动驾驶。控制器11和路径规划模块14重复上述过程，实现控制车辆1自动驾驶。
可选的，车辆1周围可能包括障碍物，车辆1周围的环境信息可能包括该障碍物的类型和运动信息等。障碍物的运动信息包括障碍物的位置、运动速度、运动加速度和运动方向等中的至少一个。其中，对于处于静止状态的障碍物，该运动速度和运动加速度均为0。
车辆1的运动信息包括车辆1的位置、运动速度、运动加速度和运动方向等中的至少一个。
可选的，感知系统12包括至少一个感知传感器，该至少一个感知传感器包括摄像头和雷达等中的一个或多个。该雷达包括毫米波雷达、激光雷达和超声波雷达等中的一个或多个。
可选的，定位系统13为全球定位系统(global positioning system，GPS)或北斗导航系统等。
其中，需要说明的是：在控制器11按照选择的路径控制车辆1自动驾驶的过程中，选择的路径可能与用户的需求不同，此时用户可能直接使用车辆1的方向盘进行手动驾驶，在用户进行手动驾驶一段时间后，用户可能停止使用方向盘进行手动驾驶，再次需要控制器11从当前位置继续控制车辆1进行自动驾驶，为了便于说明称此时的当前位置为第一位置。
例如，参见图4，在控制器11按照选择的路径2a控制车辆1自动驾驶时，在行驶到路径2a上的位置31时，用户使用方向盘手动驾驶车辆1，使得车辆1偏离了路径2a并继续行驶。在行驶到位置32时，此时用户停止使用方向盘进行手动驾驶，位置32为第一位置，需 要控制器11从第一位置32处继续控制车辆1进行自动驾驶。
其中，上述用户手动使用方向盘驾驶车辆1的模式称为手动驾驶模式，以及上述控制器11控制车辆1驾驶的模式称为自动驾驶模式。在车辆1退出手动驾驶模式并进入自动驾驶模式时，如何控制车辆1自动驾驶的详细实现过程，将通过如下任一实施例来实现。
参见图5，本申请实施例提供了一种自动驾驶的方法，该方法应用于图1所示的车辆，该方法可以由车辆中的控制器来执行，包括：
步骤501：在检测到车辆退出手动驾驶模式并进入自动驾驶模式时，获取N条路径，该N条路径是车辆在进入手动驾驶模式前已规划的路径，N为大于1的整数。
车辆在进入手动驾驶模式之前，车辆的驾驶模式为自动驾驶模式，车辆的路径规划模块规划出N条路径，车辆基于该N条路径中的一条路径进行自动驾驶。在自动驾驶的过程中，如果车辆行驶的路径与用户的需求不同，用户可以手动转动方向盘进行手动驾驶，此时车辆退出自动驾驶模式并进入手动驾驶模式。用户在手动驾驶一段时间后，停止使用方向盘进行手动驾驶，此时车辆退出手动驾驶模式并进入自动驾驶模式。
例如，参见图4，在车辆处于自动驾驶模式时，车辆的路径规划模块规划出3条路径，分别为路径2a、2b和2c，车辆基于该三条路径中的路径2a进行自动驾驶。在车辆自动驾驶到位置31时，用户手动转动方向盘进行手动驾驶，车辆进入手动驾驶模式。用户在手动驾驶到位置32时，停止使用方向盘进行手动驾驶，此时车辆退出手动驾驶模式并进入自动驾驶模式。
在本步骤中，需要检测车辆处于的驾驶模式，在检测到车辆退出手动驾驶模式并进入自动驾驶模式时执行本步骤。
其中，需要说明是：在车辆处于手动驾驶模式时，用户手动转动方向盘来驾驶车辆。用户在手动转动方向盘时，会改变方向盘的扭矩，使该方向盘的扭矩大小超过扭矩阈值；在车辆处于自动驾驶模式的情况下，用户不会转动方向盘，此时方向盘的扭矩大小为0或小于该扭矩阈值。因此，在步骤中列举了一种检测车辆的驾驶模式的实现实例，在实现实例中通过获取车辆的方向盘的扭矩大小，基于该扭矩大小检测车辆的驾驶模式。
可选的，该实现实例可以为：
在车辆处于自动驾驶模式的情况下，实时获取车辆的方向盘的扭矩大小，并对每次获取的方向盘的扭矩大小进行确定，在确定出方向盘的扭矩大小从小于扭矩阈值变为大于扭矩阈值时，确定车辆从自动驾驶模式进入手动驾驶模式。在车辆处于手动驾驶模式的情况下，也实时获取车辆的方向盘的扭矩大小，并对每次获取的方向盘的扭矩大小进行确定，在确定出方向盘的扭矩大小从大于扭矩阈值变为小于扭矩阈值时，确定车辆从手动驾驶模式进入自动驾驶模式。
该N条路径是车辆从自动驾驶模式进入手动驾驶模式之前，车辆的路径规划模块最近一次规划的路径。例如，参见图4，车辆在行驶到位置31时由自动驾驶模式进入手动驾驶模式，车辆的路径规划模块最近一次规划的路径包括路径2a、2b和2c。在用户手动驾驶到位置32时车辆由手动驾驶模式进入自动驾驶模式。因此，在本步骤中，在检测出车辆退出手动驾驶模式时，获取路径2a、2b和2c。
步骤502：获取该N条路径中的每条路径上的预瞄点，其中，第一路径上的预瞄点位于 第一路径上，且是车辆在指定第二时间长度内待到达的位置，第一路径是该N条路径中的任一条路径。
其中，需要说明的是：在车辆进入手动驾驶模式之前，车辆基于该N条路径中的一条路径进行自动驾驶。在车辆处于手动驾驶模式时，用户使用车辆的方向盘驾驶车辆，用户手动驾驶车辆行驶的路径会偏离该条路径，所以车辆在退出手动驾驶模式时，车辆的当前位置可能不在该N条路径中的任一条路径上，为了便于说明称车辆退出手动驾驶模式时的当前位置为第一位置。
例如，参见图4，在车辆进入手动驾驶模式之前，车辆基于路径2a进行自动驾驶，在车辆处于手动驾驶模式时，用户驾驶车辆行驶的路径偏离了路径2a，所以车辆在退出手动驾驶模式时，车辆的第一位置32不在路径2a、2b和2c上。
由于第一位置不在该N条路径上，所以在车辆退出手动驾驶模式时，需要为车辆从该N条路径中选择一条路径，将车辆过渡到选择路径上，使车辆基于该选择的路径进行自动驾驶。而路径的预瞄点，就是期望车辆从第一位置过渡到该路径上的接入点位置。
其中，需要说明的是：如果第一位置在该N条路径中的某条路径上，则在车辆进入自动驾驶模式时，直接根据该条路径控制车辆进行自动驾驶。
在本步骤中，对于该N条路径中的任一条路径，即对于第一路径，根据车辆的运动信息确定第一路径上的预瞄点。在实现时，
获取车辆的运动信息和第一位置(即车辆的当前位置)，根据车辆的运动信息和第二时间长度，获取车辆在第二时间长度内行驶的距离；以第一位置为圆点并以该距离为半径，确定一个圆；对于第一路径，确定第一路径与该圆相交的一个或多个交点；如果该一个或多个交点中存在交点位于车辆的前方，则将位于车辆前方的交点确定为第一路径上的预瞄点；如果该一个或多个交点中没有交点位于车辆的前方，则将第一路径的终点位置确定为第一路径上的预瞄点。
可选的，通过车辆的定位系统获取车辆的运动信息，该运动信息包括车辆的运动速度、加速度和运动方向等。根据该车辆的运动速度和加速度，以及第二时间长度，获取车辆在第二时间长度内行驶的距离。
可选的，第一位置是在世界坐标系中的位置，在得到第一路径上的交点时，获取该交点在世界坐标系中的位置，根据第一位置和该交点的位置，可以确定该交点是否位于车辆的前方。
例如，参见图6，通过车辆1包括的定位系统获取车辆的第一位置32，以及获取车辆的运动速度、加速度和运动方向等运动信息。根据第二时间长度、车辆的运动速度和加速度，获取车辆在第二时间长度内行驶的距离。以第一位置32为圆点以该距离为半径，确定一个圆，对于路径2a，确定路径2a与该圆相交的交点L，该交点L没有位于车辆的前方，则将路径2a的终点位置K确定为路径2a上的预瞄点。对于路径2b，确定路径2b与该圆相交的交点G和H，该交点H位于车辆的前方，则将交点H确定为路径2b上的预瞄点。对于路径2c，确定路径2c与该圆相交的交点E和F，该交点F位于车辆的前方，则将交点F确定为路径2c上的预瞄点。
可选的，在执行本步骤之前，确定包括该N条路径的区域。可选的，该区域为包括该N条路径的最小区域。在第一位置位于该区域中，执行本步骤。即在第一位置位于该区域中， 获取N个路径中的每条路径上的预瞄点。在第一位置位于该区域外，通过车辆的路径规划模块规划待行驶的至少一条路径，根据至少一条路径控制车辆自动驾驶。
可选的，从该至少一条路径选择一条路径，基于选择的一条路径控制车辆自动驾驶。
其中，该N条路径是路径规划模块基于车辆周围的环境信息规划的，路径规划模块规划的路径都是比较安全的，车辆基于规划的任一条路径自动驾驶时不会与车辆周围的障碍物发生碰撞，该障碍物为其他车辆或行人等。该区域为该N条路径共同包围的区域，所以在该区域内可能不会有障碍物存在，因此当第一位置位于该区域内，在该区域内控制车辆过渡到该N条路径的某条路径上，车辆不会与障碍物碰撞，提高了自动驾驶的安全性。
而当第一位置位于该区域外，即车辆位于该区域外，如此需要控制车辆从该区域外过渡到该N条路径中的某条路径上，位于该区域外可能有障碍物，这样车辆从第一位置过渡到该N条路径中的某条路径时，可能与障碍物发生碰撞。所以为了避免此情况发生，以提高自动驾驶的安全性。在第一位置位于该区域外，直接通过路径规划模块根据感知系统感知车辆周围的环境信息和定位系统获取车辆的运动信息，规划至少一条路径，基于该至少一条路径自动驾驶。
例如，参见图6，确定包括路径2a、2b和2c的最小区域为区域NMJKN，其中第一位置32位于该最小区域NMJKN，则通过本步骤获取位于路径2a上的预瞄点K，位于路径2b上的预瞄点H和位于路径2c上的预瞄点F。
步骤503：根据每条路径的预瞄点和车辆的行驶方向，分别获取每条路径的平滑误差。
对于该N条路径中的任一条路径，即对于第一路径，根据第一路径上的预瞄点和车辆的行驶方向，获取第一路径的平滑误差，第一路径的平滑误差用于指示车辆从第一位置过渡到第一路径的平稳程度。
在本步骤中，可以通过如下5031至5032获取第一路径的平滑误差，该5031至5032分别为：
5031：对于第一路径上的预瞄点，将该预瞄点映射到车辆的车辆坐标系中，得到该预瞄点在车辆坐标系中的横向坐标。
可选的，预瞄点的横向坐标的绝对值等于车辆从第一位置到达预瞄点的横向偏移。
在本操作中，确定车辆坐标系，车辆坐标系以车辆包括的目标点的位置作为坐标原点，以车头的朝向方向为x轴，以与车头朝向垂直的方向为y轴。根据目标点在世界坐标系中的位置，确定车辆坐标系与世界坐标系之间的转换关系，基于该转换关系，将该预瞄点映射到车辆的车辆坐标系中，得到第一路径上的预瞄点在车辆坐标系中的横向坐标。
可选的，目标点为车辆的后轴中心、车辆的中心或车辆的前轴中心等。
例如，参见图7，假设目标点为车辆的后轴中心33，以目标点33的位置作为坐标原点，以车头的朝向方向为x轴，以与车头朝向垂直的方向为y轴。获取目标点33在世界坐标系中的位置，基于目标点33的位置确定车辆坐标系与世界坐标系之间的转换关系。对于路径2a的预瞄点K，基于该转换关系，将该预瞄点K映射到车辆的车辆坐标系中，得到路径2a上的预瞄点K在车辆坐标系中的横向坐标xa。对于路径2b的预瞄点H，基于该转换关系，将该预瞄点H映射到车辆的车辆坐标系中，得到路径2b上的预瞄点H在车辆坐标系中的横向坐标xb。对于路径2c的预瞄点F，基于该转换关系，将该预瞄点F映射到车辆的车辆坐标系中，得到路径2c上的预瞄点F在车辆坐标系中的横向坐标xc。
5032：根据该横向坐标，以及车辆的行驶方向与第一切线之间的夹角，获取第一路径的平滑误差，第一切线为第一路径在该预瞄点处的切线。
对于第一路径上的预瞄点，确定第一切线，第一切线为第一路径在该预瞄点处的切线，获取车辆的行驶方向与第一切线之间的夹角，根据该横向坐标的绝对值，以及车辆的行驶方向与第一切线之间的夹角，获取第一路径的平滑误差。
可选的，该夹角反映了车辆在过渡到该预瞄点所需要转动的角度，且车辆到达该预瞄点时，车辆的行驶方向与第一切线平行。
可选的，由于第一路径是路径规划模块规划出的路径，所以可以获取第一路径在其预瞄点处的曲率，基于该曲率可以确定第一路径在该预瞄点处的第一切线的方向。而车辆的行驶方向，可以通过车辆的定位系统实时获取到。基于第一切线的方向和车辆的行驶方向，可以获取车辆的行驶方向与第一切线之间的夹角。
可选的，按如下第一公式，获取第一路径的平滑误差。
第一公式为：err＝a*|x|+b*θ
在第一公式中，err为第一路径的平滑误差，x为预瞄点的横向坐标，θ为该夹角，a和b为两个权重。
例如，参见图7，对于路径2a上的预瞄点K，确定路径2a在预瞄点K处的第一切线34，获取车辆的行驶方向与第一切线34之间的夹角，根据该预瞄点的横向坐标xa，以及车辆的行驶方向与第一切线34之间的夹角，获取路径2a的平滑误差。对于路径2b上的预瞄点H，确定路径2b在预瞄点H处的第一切线35，获取车辆的行驶方向与第一切线35之间的夹角，根据该预瞄点的横向坐标xb，以及车辆的行驶方向与第一切线35之间的夹角，获取路径2b的平滑误差。对于路径2c上的预瞄点F，确定路径2c在预瞄点F处的第一切线36，获取车辆的行驶方向与第一切线36之间的夹角，根据该预瞄点F的横向坐标xc，以及车辆的行驶方向与第一切线36之间的夹角，获取路径2c的平滑误差。
步骤504：根据该N个路径的平滑误差，从N个路径中选择一个路径作为第二路径。
可选的，根据该N个路径的平滑误差，从N个路径中选择平滑误差最小的一个路径作为第二路径。
例如，根据路径2a的平滑误差，路径2b的平滑误差和路径2c的平滑误差，从路径2a、路径2b和路径2c中选择路径2b。
由于第二路径的平滑误差最小，而第二路径的平滑误差用于指示车辆从第一位置过渡到第二路径的平稳程度，所以控制车辆过渡到选择的第二路径最平稳，所需要转动车辆的行驶方向的角度最小。例如，参见图7，选择路径2b的平滑误差最小，控制车辆从第一位置32过渡到选择路径2b的预瞄点H所需要的转动车辆的行驶方向的角度最小。所以从第一位置过渡到路径2b最平稳，最安全。
步骤505：根据第二路径，控制车辆自动驾驶。
在本步骤中，控制车辆从第一位置自动驾驶至第二路径的预瞄点上，且第二路径的预瞄点处车辆的行驶方向与第一切线平行，该第一切线为第二路径在该预瞄点处的切线。控制第二路径控制车辆从该预瞄点继续自动驾驶。
例如，控制车辆从第一位置32自动驾驶至路径2b的预瞄点H，且在预瞄点H处车辆的行驶方向与路径2b在预瞄点H的切线35平行。
可选的，还能够获取第四路径的路径参数，第四路径是在使用手动驾驶模式的时间段内车辆行驶的路径，这样使车辆的路径规划模块基于该路径参数，规划车辆在行驶完第二路径之后待行驶的至少一条路径。从该至少一条路径中选择一条路径，在行驶完第二路径后，基于选择一条路径控制车辆继续自动驾驶。
可选的，该第四路径的路径参数包括第四路径的曲率和平滑程度等至少一个。
可选的，在步骤502中，在第一位置不在包括N条路径的区域内时，也可以获取第四路径的路径参数，使车辆的路径规划模块基于该路径参数，规划至少一条路径，从该至少一条路径中选择一条路径，基于选择一条路径控制车辆继续自动驾驶。
第四路径是用户手动驾驶车辆行驶的路径，所以第四路径的路径参数用于反映用户的驾驶习惯，因此路径规划模块在基于车辆的环境信息和运动信息规划路径时，引入第四路径的路径参数，这样路径规划模块基于车辆的环境信息和运动信息，以及第四路径的路径参数，能够规划出符合用户驾驶习惯的路径。
可选的，在路径规划模块规划出至少一条路径后，获取该至少一条路径中的每条路径的代价参数，路径的代价参数用于反映用户的驾驶风格和习惯等中的至少一个，根据每条路径的代价参数，选择一条路径。
可选的，在路径规划模块规划出至少一条路径后，还可显示该至少一条路径；以让用户选择满足自己需求的路径。
相应的，在检测到用户对第三路径的选择操作时，获取第三路径，第三路径是至少一条路径中的一条路径；根据第三路径控制所述车辆自动驾驶。
在本申请实施例中，在从手动驾驶模式进入自动驾驶模式时，获取在进入手动驾驶模式之前已规划的N条路径，确定包括该N条路径的区域，在车辆的当前位置位于该区域内才获取该N条路径中的每条路径的平滑误差，根据每条路径的平滑误差选择一条路径作为第二路径，这样便根据第二路径控制车辆自动驾驶，从而不需要停车重启自动驾驶模式，提高了自动驾驶的效率。另外，由于在车辆的当前位置位于该区域内才选择第二路径，这样可以提高了驾驶安全性。由于路径的平滑误差用于指示车辆从第一位置过渡到第一路径的平稳程度，又由于基于平滑误差选择的第二路径，所以能够控制车辆较平滑地从第一位置过渡到第二路径，提高了自动驾驶的舒适性和安全性。
参见图8，本申请实施例提供了一种控制车辆的装置800，所述装置800可部署在上述图1或图5所示实施例的车辆控制器上，包括：
处理单元801，用于在检测到车辆退出手动驾驶模式时，获取N条路径的平滑误差，该N条路径是车辆在进入手动驾驶模式前已规划的路径，N为大于1的整数，第一路径的平滑误差用于指示车辆从第一位置过渡到第一路径的平稳程度，第一位置是车辆当前的位置，第一路径是该N条路径中的任一条；根据该N条路径的平滑误差，从该N条路径中选择一条路径作为第二路径。
控制单元802，用于根据第二路径，控制车辆自动驾驶。
可选的，处理单元801获取N条路径的平滑误差的详细实现过程，可以参见图5所示实施例中的步骤501至503中的相关内容，在此不再详细说明。
可选的，处理单元801选择第二路径的详细实现过程，，可以参见图5所示实施例中的步 骤504中的相关内容，在此不再详细说明。
控制单元802控制车辆自动驾驶的详细实现过程，可以参见图5所示实施例中的步骤505至503中的相关内容，在此不再详细说明。
可选的，处理单元801，用于：
根据车辆的运动信息确定预瞄点，预瞄点是车辆在指定时间长度内待到达的位置，预瞄点位于第一路径上；
根据预瞄点和车辆的行驶方向，获取第一路径的平滑误差。
可选的，处理单元801获取第一路径的平滑误差的详细实现过程，可以参见图5所示实施例中的步骤5031至5032中的相关内容，在此不再详细说明。
可选的，处理单元801，用于：
将预瞄点映射到车辆的车辆坐标系中，得到预瞄点在车辆坐标系中的横向坐标；
根据横向坐标，以及车辆的行驶方向与第一切线之间的夹角，获取第一路径的平滑误差，第一切线为第一路径在预瞄点处的切线。
可选的，处理单元801，用于确定包括N条路径的区域；在第一位置位于该区域中，获取N条路径的平滑误差。
可选的，处理单元801，还用于：
在第一位置位于该区域外，通过车辆的路径规划模块规划待行驶的至少一条路径，根据至少一条路径控制车辆自动驾驶。
可选的，所述装置800还包括：显示单元803，
显示单元803，用于显示该至少一条路径；
控制单元802，用于：
在检测到用户对第三路径的选择操作时，获取第三路径，第三路径是该至少一条路径中的一条路径；根据第三路径控制车辆自动驾驶。
可选的，处理单元801，还用于：
获取第四路径的路径参数，第四路径是在使用手动驾驶模式的时间段内车辆行驶的路径，该路径参数用于车辆的路径规划模块基于该路径参数，规划车辆在行驶完第二路径之后待行驶的至少一条路径。
应理解的是，本申请实施例的装置800可以通过专用集成电路(application-specific integrated circuit，ASIC)实现，或可编程逻辑器件(programmable logic device，PLD)实现，上述PLD可以是复杂程序逻辑器件(complex programmable logical device，CPLD)，现场可编程门阵列(field-programmable gate array，FPGA)，通用阵列逻辑(generic array logic，GAL)或其任意组合。也可以通过软件实现图5所示的控制车辆的方法时，所述装置800及其各个模块也可以为软件模块。
根据本申请实施例的装置800可对应于执行本申请实施例中描述的方法，并且所述装置800中的各个单元的上述和其它操作和/或功能分别为了实现图5中的各个方法的相应流程，为了简洁，在此不再赘述。
在本申请实施例中，处理单元在从手动驾驶模式进入自动驾驶模式时，获取在进入手动驾驶模式之前已规划的N条路径中的每条路径的平滑误差，根据每条路径的平滑误差选择一条路径作为第二路径，这样便控制单元根据第二路径控制车辆自动驾驶，从而不需要停车重 启自动驾驶模式，提高了自动驾驶的效率。另外，由于路径的平滑误差用于指示车辆从第一位置过渡到第一路径的平稳程度，又由于处理单元基于平滑误差选择的第二路径，所以控制单元能够控制车辆较平滑地从第一位置过渡到第二路径，提高了自动驾驶的舒适性和安全性。
参见图9，本申请实施例提供了一种控制车辆的控制器900示意图。该控制器900可以是上述任一实施例中的控制器，例如该控制器900为图1所示实施例或图5所示实施例中的控制器。该控制器900包括至少一个处理器901，内存单元902，存储介质903、通信接口904和总线系统905。其中，处理器901、内存单元902、存储介质903、通信接口904通过总线系统905进行通信。
处理器901可以调用内存单元902中存储的计算机执行指令(例如，程序代码)实现图5所示实施例中控制器执行的操作步骤。例如，在检测到车辆退出手动驾驶模式时，获取N条路径的平滑误差，该N条路径是车辆在进入手动驾驶模式前已规划的路径，N为大于1的整数，第一路径的平滑误差用于指示车辆从第一位置过渡到第一路径的平稳程度，第一位置是车辆当前的位置，第一路径是N条路径中的任一条；根据N条路径的平滑误差，从N条路径中选择一条路径作为第二路径；根据第二路径，控制车辆自动驾驶。
可选的，存储介质903中存储该计算机执行指令和操作系统，在该装置900启动运行时，处理器901可以将存储介质903存储的该计算机执行指令和操作系统加载到内存单元902中，并在操作系统提供的运行环境中调用并运行内存单元902中的该计算机执行指令。
可选的，上述处理器901可以是一个CPU，微处理器，特定应用集成电路(application-specific integrated circuit，ASIC)，或一个或多个用于控制本申请方案程序执行的集成电路。作为一种实施例，处理器901可以包括一个或多个CPU，例如图9中的CPU0和CPU1。该处理器901还可以是其他通用处理器、数字信号处理器(digital signal processing，DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者是任何常规的处理器等。
该控制器900中总线系统905除包括数据总线之外，还可以包括电源总线、控制总线和状态信号总线等。但是为了清楚说明起见，在图中将各种总线都标为总线系统905。
上述通信接口904，用于与其他设备通信。例如，处理器901通过通信接口904与感知系统和定位系统进行通信，处理器901通过通信接口904与感知系统和定位系统进行通信，以获取到移动物体周围的障碍物的位置和运动属性信息。
该存储介质903可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data date SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器 (synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。
该总线905除包括数据总线之外，还可以包括电源总线、控制总线、状态信号总线、车内总线(例如控制器局域网络(controller area network，CAN)总线)等。但是为了清楚说明起见，在图中将各种总线都标为总线305。
应理解，根据本申请实施例的控制器900可对应于本申请实施例中的装置800，并可以对应于执行根据本申请实施例图5中的相应主体，并且控制器900中的各个模块的上述和其它操作和/或功能分别为了实现图5中的各个方法的相应流程，为了简洁，在此不再赘述。
本申请还提供一种车辆，该车辆包括图9所示的控制器900，该控制器900用于执行上述图5中各个方法中相应主体的操作步骤，为了简洁，在此不再赘述。
上述实施例，可以全部或部分地通过软件、硬件、固件或其他任意组合来实现。当使用软件实现时，上述实施例可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载或执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以为通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集合的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质。半导体介质可以是固态硬盘(solid state drive，SSD)。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
以上所述仅为本申请的可选实施例，并不用以限制本申请，凡在本申请的原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (17)

  1. 一种控制车辆的方法，其特征在于，所述方法包括：
    在检测到车辆退出手动驾驶模式时，获取N条路径的平滑误差，所述N条路径是所述车辆在进入所述手动驾驶模式前已规划的路径，N为大于1的整数，第一路径的平滑误差用于指示所述车辆从第一位置过渡到所述第一路径的平稳程度，所述第一位置是所述车辆当前的位置，所述第一路径是所述N条路径中的任一条；
    根据所述N条路径的平滑误差，从所述N条路径中选择一条路径作为第二路径；
    根据所述第二路径，控制所述车辆自动驾驶。
  2. 如权利要求1所述的方法，其特征在于，获取所述第一路径的平滑误差，包括：
    根据所述车辆的运动信息确定预瞄点，所述预瞄点是所述车辆在指定时间长度内待到达的位置，所述预瞄点位于所述第一路径上；
    根据所述预瞄点和所述车辆的行驶方向，获取所述第一路径的平滑误差。
  3. 如权利要求2所述的方法，其特征在于，所述根据所述预瞄点和所述车辆的行驶方向，获取所述第一路径的平滑误差，包括：
    将所述预瞄点映射到所述车辆的车辆坐标系中，得到所述预瞄点在所述车辆坐标系中的横向坐标；
    根据所述横向坐标，以及所述车辆的行驶方向与第一切线之间的夹角，获取所述第一路径的平滑误差，所述第一切线为所述第一路径在所述预瞄点处的切线。
  4. 如权利要求1至3任一项所述的方法，其特征在于，所述获取N条路径的平滑误差之前，还包括：
    确定包括所述N条路径的区域；
    所述获取N条路径的平滑误差，包括：
    在所述第一位置位于所述区域中，获取N条路径的平滑误差。
  5. 如权利要求4所述的方法，其特征在于，所述方法还包括：
    在所述第一位置位于所述区域外，通过所述车辆的路径规划模块规划待行驶的至少一条路径，根据所述至少一条路径控制所述车辆自动驾驶。
  6. 如权利要求5所述的方法，其特征在于，所述方法还包括：
    显示所述至少一条路径；
    所述根据所述至少一条路径控制所述车辆自动驾驶，包括：
    在检测到用户对第三路径的选择操作时，获取所述第三路径，所述第三路径是所述至少一条路径中的一条路径；
    根据所述第三路径控制所述车辆自动驾驶。
  7. 如权利要求1至6任一项所述的方法，其特征在于，所述方法还包括：
    获取第四路径的路径参数，所述第四路径是在使用手动驾驶模式的时间段内所述车辆行驶的路径，所述路径参数用于所述车辆的路径规划模块基于所述路径参数，规划所述车辆在行驶完所述第二路径之后待行驶的至少一条路径。
  8. 一种控制车辆的装置，其特征在于，所述装置包括：
    处理单元，用于在检测到车辆退出手动驾驶模式时，获取N条路径的平滑误差，所述N条路径是所述车辆在进入所述手动驾驶模式前已规划的路径，N为大于1的整数，第一路径的平滑误差用于指示所述车辆从第一位置过渡到所述第一路径的平稳程度，所述第一位置是所述车辆当前的位置，所述第一路径是所述N条路径中的任一条；根据所述N条路径的平滑误差，从所述N条路径中选择一条路径作为第二路径；
    控制单元，用于根据所述第二路径，控制所述车辆自动驾驶。
  9. 如权利要求8所述的装置，其特征在于，所述处理单元，用于：
    根据所述车辆的运动信息确定预瞄点，所述预瞄点是所述车辆在指定时间长度内待到达的位置，所述预瞄点位于所述第一路径上；
    根据所述预瞄点和所述车辆的行驶方向，获取所述第一路径的平滑误差。
  10. 如权利要求9所述的装置，其特征在于，所述处理单元，用于：
    将所述预瞄点映射到所述车辆的车辆坐标系中，得到所述预瞄点在所述车辆坐标系中的横向坐标；
    根据所述横向坐标，以及所述车辆的行驶方向与第一切线之间的夹角，获取所述第一路径的平滑误差，所述第一切线为所述第一路径在所述预瞄点处的切线。
  11. 如权利要求8至10任一项所述的装置，其特征在于，所述处理单元，用于确定包括所述N条路径的区域；在所述第一位置位于所述区域中，获取N条路径的平滑误差。
  12. 如权利要求11所述的装置，其特征在于，所述处理单元，还用于：
    在所述第一位置位于所述区域外，通过所述车辆的路径规划模块规划待行驶的至少一条路径，根据所述至少一条路径控制所述车辆自动驾驶。
  13. 如权利要求12所述的装置，其特征在于，所述装置还包括：显示单元，
    所述显示单元，用于显示所述至少一条路径；
    所述控制单元，用于：
    在检测到用户对第三路径的选择操作时，获取所述第三路径，所述第三路径是所述至少一条路径中的一条路径；
    根据所述第三路径控制所述车辆自动驾驶。
  14. 如权利要求8至13任一项所述的装置，其特征在于，所述处理单元，还用于：
    获取第四路径的路径参数，所述第四路径是在使用手动驾驶模式的时间段内所述车辆行驶的路径，所述路径参数用于所述车辆的路径规划模块基于所述路径参数，规划所述车辆在行驶完所述第二路径之后待行驶的至少一条路径。
  15. 一种车辆，其特征在于，所述车辆包括如权利要求8至14任一项所述的装置。
  16. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被计算机执行时，实现如权利要求1-7任一项所述的方法。
  17. 一种计算机程序产品，其特征在于，所述计算机程序产品包括在计算机可读存储介质中存储的计算机程序，并且所述计算程序通过处理器进行加载来实现如权利要求1-7任一项所述的方法。
PCT/CN2021/101036 2020-06-28 2021-06-18 车辆控制方法、装置、车辆及存储介质 WO2022001708A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010598526.XA CN113844460B (zh) 2020-06-28 2020-06-28 车辆控制方法、装置及车辆
CN202010598526.X 2020-06-28

Publications (1)

Publication Number Publication Date
WO2022001708A1 true WO2022001708A1 (zh) 2022-01-06

Family

ID=78972122

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/101036 WO2022001708A1 (zh) 2020-06-28 2021-06-18 车辆控制方法、装置、车辆及存储介质

Country Status (2)

Country Link
CN (1) CN113844460B (zh)
WO (1) WO2022001708A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117572875A (zh) * 2024-01-15 2024-02-20 上海友道智途科技有限公司 一种基于热启动的实时速度规划方法、系统、设备及介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114475574A (zh) * 2022-03-02 2022-05-13 广东皓行科技有限公司 预瞄点确定方法、车辆控制方法以及车辆控制系统

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104837705A (zh) * 2012-11-30 2015-08-12 谷歌公司 启用和停用自动驾驶
CN104960520A (zh) * 2015-07-16 2015-10-07 北京工业大学 基于Pure Pursuit算法的预瞄点确定方法
JP2016050901A (ja) * 2014-09-02 2016-04-11 アイシン・エィ・ダブリュ株式会社 自動運転支援システム、自動運転支援方法及びコンピュータプログラム
CN106256643A (zh) * 2015-06-15 2016-12-28 丰田自动车株式会社 自动驾驶装置和车辆控制装置
CN107444405A (zh) * 2016-05-10 2017-12-08 本田技研工业株式会社 车辆控制系统、车辆控制方法和车辆控制程序
CN107835932A (zh) * 2015-07-08 2018-03-23 本田技研工业株式会社 自动驾驶控制装置
WO2019043776A1 (ja) * 2017-08-29 2019-03-07 株式会社日立製作所 車両制御装置
CN109843682A (zh) * 2016-10-18 2019-06-04 本田技研工业株式会社 车辆控制装置
KR102004141B1 (ko) * 2018-03-14 2019-10-01 송주희 졸음운전시 운전모드 전환 안내 시스템

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3240997B1 (en) * 2014-12-30 2020-08-19 Robert Bosch GmbH Route selection based on automatic-manual driving preference ratio
US9555807B2 (en) * 2015-05-01 2017-01-31 Delphi Technologies, Inc. Automated vehicle parameter modification based on operator override
US10353393B2 (en) * 2016-12-29 2019-07-16 Baidu Usa Llc Method and system for improving stability of autonomous driving vehicles
JP6565988B2 (ja) * 2017-08-25 2019-08-28 トヨタ自動車株式会社 自動運転装置
US10591926B2 (en) * 2017-09-18 2020-03-17 Baidu Usa Llc Smooth road reference for autonomous driving vehicles based on 2D constrained smoothing spline
CN107992050B (zh) * 2017-12-20 2021-05-11 广州汽车集团股份有限公司 无人驾驶汽车局部路径运动规划方法和装置
JP2019138637A (ja) * 2018-02-06 2019-08-22 株式会社デンソーテン 経路探索装置および経路探索方法
CN108519094B (zh) * 2018-02-11 2022-03-25 华为技术有限公司 局部路径规划方法及云处理端
CN110673593B (zh) * 2018-07-03 2022-11-15 杭州海康威视数字技术股份有限公司 车辆控制方法和装置
CN110516880B (zh) * 2019-08-29 2022-05-13 广州小鹏汽车科技有限公司 一种路径处理方法、系统、车辆及计算机可读存储介质

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104837705A (zh) * 2012-11-30 2015-08-12 谷歌公司 启用和停用自动驾驶
JP2016050901A (ja) * 2014-09-02 2016-04-11 アイシン・エィ・ダブリュ株式会社 自動運転支援システム、自動運転支援方法及びコンピュータプログラム
CN106256643A (zh) * 2015-06-15 2016-12-28 丰田自动车株式会社 自动驾驶装置和车辆控制装置
CN107835932A (zh) * 2015-07-08 2018-03-23 本田技研工业株式会社 自动驾驶控制装置
CN104960520A (zh) * 2015-07-16 2015-10-07 北京工业大学 基于Pure Pursuit算法的预瞄点确定方法
CN107444405A (zh) * 2016-05-10 2017-12-08 本田技研工业株式会社 车辆控制系统、车辆控制方法和车辆控制程序
CN109843682A (zh) * 2016-10-18 2019-06-04 本田技研工业株式会社 车辆控制装置
WO2019043776A1 (ja) * 2017-08-29 2019-03-07 株式会社日立製作所 車両制御装置
KR102004141B1 (ko) * 2018-03-14 2019-10-01 송주희 졸음운전시 운전모드 전환 안내 시스템

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117572875A (zh) * 2024-01-15 2024-02-20 上海友道智途科技有限公司 一种基于热启动的实时速度规划方法、系统、设备及介质
CN117572875B (zh) * 2024-01-15 2024-04-12 上海友道智途科技有限公司 一种基于热启动的实时速度规划方法、系统、设备及介质

Also Published As

Publication number Publication date
CN113844460B (zh) 2024-04-12
CN113844460A (zh) 2021-12-28

Similar Documents

Publication Publication Date Title
JP6861238B2 (ja) 自動運転車の車線変更軌跡を確定するための方法
JP6865244B2 (ja) 自動運転車両の軌道の生成方法
JP6845874B2 (ja) 自動運転車のための経路及び速度の最適化フォールバックメカニズム
JP7001642B2 (ja) 自動運転車両のためのオブジェクト移動を予測するための方法およびシステム
JP6975512B2 (ja) 自動運転車両の周辺車両の挙動に基づくリアルタイム感知調整と運転調整
JP7001628B2 (ja) 自動運転車両の駐車軌跡の計画
US10823575B2 (en) Reference line smoothing method using piecewise spiral curves with weighted geometry costs
JP6567617B2 (ja) 自律走行車の安定性を向上させるための方法、媒体、及びシステム
US10459441B2 (en) Method and system for operating autonomous driving vehicles based on motion plans
JP6878493B2 (ja) 自動運転車両（ａｄｖ）に用いるピッチ角の補正方法
JP6784794B2 (ja) 自動運転車の経路計画用のドリフト補正の方法
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
US10429849B2 (en) Non-linear reference line optimization method using piecewise quintic polynomial spiral paths for operating autonomous driving vehicles
JP2019182414A (ja) 自動運転車に対して障害物の予測軌跡を生成するための方法
JP6779326B2 (ja) 複数のスレッドを使用して自動運転車両に用いられる基準線を生成するための方法及びシステム
WO2022001708A1 (zh) 车辆控制方法、装置、车辆及存储介质
JP7149288B2 (ja) 自動運転車両のための螺旋曲線に基づく垂直駐車計画システム
JP7009490B2 (ja) 自動運転車両のための制御主導型の３ポイントターン計画
JP6932196B2 (ja) 自動運転車両のための螺旋経路に基づく３ポイントターン計画
JP6908675B2 (ja) Ｌ２自動運転用の所定のキャリブレーションテーブルに基づく車両アクセル／ブレーキアシストシステム
JP2021511995A (ja) 自動運転車の高速計画のための多項式フィッティングベースの基準線平滑化方法
US10732632B2 (en) Method for generating a reference line by stitching multiple reference lines together using multiple threads
JP2021518822A (ja) 自律走行車中の非回避計画システムにおける障害物フィルタリングの方法
JP6935507B2 (ja) 自動運転のための自己反転線の相互回避アルゴリズム
JP2021502915A (ja) 列挙に基づく自動運転車両の３ポイントターン計画

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: 21833281

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21833281

Country of ref document: EP

Kind code of ref document: A1