WO2022095814A1 - 自动倒车控制方法、装置、车辆和存储介质 - Google Patents
自动倒车控制方法、装置、车辆和存储介质 Download PDFInfo
- Publication number
- WO2022095814A1 WO2022095814A1 PCT/CN2021/127853 CN2021127853W WO2022095814A1 WO 2022095814 A1 WO2022095814 A1 WO 2022095814A1 CN 2021127853 W CN2021127853 W CN 2021127853W WO 2022095814 A1 WO2022095814 A1 WO 2022095814A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- reversing
- vehicle
- target
- information
- point
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000001133 acceleration Effects 0.000 claims description 9
- 230000009466 transformation Effects 0.000 abstract description 7
- 238000009825 accumulation Methods 0.000 abstract description 4
- 230000001934 delay Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 13
- 230000008859 change Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 238000009795 derivation Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D15/00—Steering not otherwise provided for
- B62D15/02—Steering position indicators ; Steering position determination; Steering aids
- B62D15/027—Parking aids, e.g. instruction means
- B62D15/0285—Parking performed automatically
-
- 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
- B60W30/12—Lane 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D15/00—Steering not otherwise provided for
- B62D15/02—Steering position indicators ; Steering position determination; Steering aids
Definitions
- the present application relates to the technical field of automatic driving control, and in particular, to an automatic reversing control method, device, vehicle and storage medium.
- the automatic reversing of vehicles is an indispensable technology in automatic driving, especially as the technologies of assisted driving and some unmanned vehicles are becoming more and more mature, and the application scenarios are becoming more and more abundant, there is a demand for automatic reversing and storage, such as unmanned mining areas.
- An automatic reversing control method comprising:
- the vehicle's reversing target trajectory information in the reversing coordinate system generated according to the vehicle position and the reversing position position; wherein, the reversing coordinate system is established with the position of the center of mass of the vehicle as the center point and the reversed rear wheel speed direction as the positive direction;
- the curvature of the trajectory point in the reversing target trajectory range is calculated in real time, and the target driving trajectory point in the reversing coordinate system is obtained according to the curvature of the trajectory point in the reversing target trajectory range and the actual curvature of the vehicle;
- Reversing control is performed according to the error information.
- An automatic reversing control device includes:
- the target trajectory acquisition module is used to acquire the reversing target trajectory information of the vehicle in the reversing coordinate system generated according to the vehicle position and the reversing position position; wherein, the center of mass position of the vehicle is used as the center point, and the rear wheel speed direction of reversing is the positive direction to establish Reversing coordinate system;
- the target driving trajectory point determination module is used to calculate the curvature of the trajectory points in the target trajectory range of reversing in real time according to the target trajectory information of reversing, and obtain the coordinates of the reversing according to the curvature of the trajectory points in the target trajectory range of reversing and the actual curvature of the vehicle
- the target driving trajectory point under the system is used to calculate the curvature of the trajectory points in the target trajectory range of reversing in real time according to the target trajectory information of reversing, and obtain the coordinates of the reversing according to the curvature of the trajectory points in the target trajectory range of reversing and the actual curvature of the vehicle.
- an error calculation module configured to calculate the error information between the vehicle and the target driving trajectory point when reversing according to the target driving trajectory point in the reversing coordinate system
- the reversing control module is used for reversing control according to the error information.
- a vehicle comprising a vehicle controller, a lidar, a camera, a radar sensor and a lidar connected to the vehicle controller, the memory stores a computer program, and the vehicle controller implements the following steps when executing the computer program :
- the vehicle's reversing target trajectory information in the reversing coordinate system generated according to the vehicle position and the reversing position position; wherein, the reversing coordinate system is established with the position of the center of mass of the vehicle as the center point and the reversed rear wheel speed direction as the positive direction;
- the curvature of the trajectory point in the reversing target trajectory range is calculated in real time, and the target driving trajectory point in the reversing coordinate system is obtained according to the curvature of the trajectory point in the reversing target trajectory range and the actual curvature of the vehicle;
- Reversing control is performed according to the error information.
- the vehicle's reversing target trajectory information in the reversing coordinate system generated according to the vehicle position and the reversing position position; wherein, the reversing coordinate system is established with the position of the center of mass of the vehicle as the center point and the reversed rear wheel speed direction as the positive direction;
- the curvature of the trajectory point in the reversing target trajectory range is calculated in real time, and the target driving trajectory point in the reversing coordinate system is obtained according to the curvature of the trajectory point in the reversing target trajectory range and the actual curvature of the vehicle;
- Reversing control is performed according to the error information.
- the above-mentioned automatic reversing control method, device, vehicle and storage medium establish a reversing coordinate system with the direction of the rear wheel speed of reversing as the positive direction, and obtain the reversing target trajectory information of the vehicle in the reversing coordinate system, so as to avoid using the location information of the reversing drivable area.
- Carry out the error caused by coordinate conversion calculate the data point position of the maximum curvature change within a certain range in real time according to the target driving trajectory of reversing, and carry out the reversing control according to the error value between the target position and the vehicle, which can realize the advance control function of the control system and make up for the system. Delay and other reasons lead to the accumulation of errors, which improves the accuracy of reversing, especially the parking space control.
- the method improves the precision of automatic reversing control.
- Fig. 1 is the application environment diagram of the automatic reversing control method in one embodiment
- FIG. 2 is a schematic flowchart of an automatic reversing control method in one embodiment
- FIG. 3 is a schematic diagram of a reversing coordinate system and a vehicle reversing kinematics model in one embodiment
- FIG. 4 is a schematic flowchart of steps for generating target trajectory data in one embodiment
- Figure 5 is a schematic diagram of a front-wheel drive reversing dynamics model in one embodiment
- FIG. 6 is a schematic diagram of the relationship between the direction angle of rear wheel speed and the actual speed of the vehicle in one embodiment
- FIG. 7 is a schematic diagram of the articulation information of the truck with trailer in the reversing coordinate system in one embodiment
- FIG. 10 is a structural block diagram of an automatic reversing control device in one embodiment
- FIG. 11 is an internal structural diagram of a vehicle in one embodiment.
- the automatic reversing control method provided by the present application can be applied to the application environment shown in FIG. 1 .
- the application environment includes a vehicle 100 equipped with a lidar 101 , a camera 102 , a radar sensor 103 and a vehicle controller 104 .
- the lidar 101 , the camera 102 , and the radar sensor 103 are respectively connected to the controller 104 .
- the lidar 101 collects a three-dimensional map of the equipment environment, and the camera 102 collects images around the equipment in real time. Based on image recognition technology, it can assist in identifying obstacles of signal lights. Radar sensors determine the distance of obstacles.
- the controller 104 stores a high-precision map, and uses the data of the lidar 101 , the camera 102 , and the radar sensor 103 and the high-precision map to control the equipment to realize automatic driving.
- the vehicle 100 may be an autonomous vehicle such as a mining truck, a heavy truck, a bus, and a sedan in a mining area. It can be used in the actual application of autonomous vehicles that require autonomous reversing to complete parking space parking, unloading ore unloading, roadside parking and other scenarios. It can also be applied to assist the driver to automatically control the vehicle to reverse according to the planned path. .
- an autonomous vehicle such as a mining truck, a heavy truck, a bus, and a sedan in a mining area. It can be used in the actual application of autonomous vehicles that require autonomous reversing to complete parking space parking, unloading ore unloading, roadside parking and other scenarios. It can also be applied to assist the driver to automatically control the vehicle to reverse according to the planned path. .
- an automatic reversing control method is provided, which is described by taking the method applied to the vehicle controller in FIG. 1 as an example, including the following steps:
- Step 202 Acquire the reversing target trajectory information of the vehicle in the reversing coordinate system generated according to the vehicle position and the reversing space position; wherein, the reversing coordinate system is established with the position of the center of mass of the vehicle as the center point and the reversed rear wheel speed direction as the positive direction.
- the vehicle position refers to the current position of the vehicle.
- the reversing position refers to the target position for reversing. Taking the position of the vehicle as the starting point and the position of the reversing space as the end point, the reversing target estimation information of the vehicle from the vehicle position to the position of the reversing space is generated in the backward coordinate system.
- the movement direction of the rear wheels of the vehicle is the positive direction when reversing
- a vehicle model that defines the actual front-wheel drive of the vehicle body as the rear-wheel drive when reversing it can be understood as a model that the rear-wheel drive vehicle travels in the forward direction.
- the reversing driving direction is the positive direction
- use GPS global positioning or local positioning of the base station to establish a reversing coordinate system based on the position of the center of mass of the vehicle.
- the coordinate system and vehicle reversing kinematics model are shown in Figure 3 below.
- XOY is the established reversing coordinate system
- V X is the speed direction of reversing driving.
- the XOY reversing coordinate system can accurately describe the kinematics of the vehicle when reversing, and the direction of the reversing speed is used as the positive direction of the coordinate system.
- the lateral dynamics model and longitudinal dynamics model of reversing are derived, and the lateral error and longitudinal error under this coordinate system are substituted to calculate the control amount of the front wheel angle and the throttle brake control amount, so as to realize the reversing of the vehicle to the target point.
- the positive direction of the forward automatic driving coordinate system is the speed direction of the front wheels, and the planned forward driving trajectory x direction data during automatic driving is a positive value, but in general, the driving position of the vehicle needs to be considered due to automatic driving. Whether it meets the requirements, it is necessary to retain a piece of data with a negative value in the x direction (for example, when the vehicle position exceeds the planned target position, a negative value in the x direction of the planned target position tells the vehicle to exceed the target position). However, if the coordinate system continues to be used to generate the planned target position for reversing, and the planned vehicle travels in the backward direction, the generated trajectory position data is negative, which conflicts with the forward automatic driving scheme.
- the planning module generates a reversing trajectory in the forward automatic driving coordinate system when reversing, which requires special processing, such as the acceleration generated by the reversing trajectory, and the position data is negative.
- the control method uses the target data to calculate the control amount, coordinate transformation and position transformation are required.
- the trajectory data generated based on the reversing coordinate system is similar to the trajectory generation method of forward automatic driving. The control method does not need to perform any processing on the target data, and the method of controlling the calculation error is consistent.
- the lateral dynamics model calculated by the forward automatic driving coordinate system considers the front-wheel drive, and there is an error when the steering wheel angle is calculated to control the vehicle to reverse according to the front-wheel drive.
- the reversing coordinate system calculate a target trajectory information that satisfies the reversing coordinate system.
- the starting point of the target trajectory starts from the driving wheel, and generates a trajectory with no less than 1 data point in the positive direction of the reversing coordinate system.
- the data points mainly include the coordinates, heading angle, curvature, and the length of the curve from the coordinate origin based on the reversing coordinate system. s, speed, acceleration and other data.
- the reversing target trajectory information of the parking space is created offline on the high-precision map.
- the production method uses the actual reversing to record the reversing positioning information points, and fits the continuous reversing curve offline.
- the reversing trajectory in and out of the warehouse is calculated according to the vehicle positioning information and the fitted curve. Because the current parking space information is fixed and standardized. The parking position in the same area, the reversing estimation fitting curve can be reused.
- the vehicle controller calculates the reversing trajectory in the global coordinate system according to the position information of the vehicle itself, and obtains the reversing trajectory information based on the reversing coordinate system after coordinate transformation.
- acquiring the reversing target trajectory information of the vehicle in the reversing coordinate system generated according to the vehicle position and the reversing space position includes: acquiring map information and vehicle location information, and acquiring the location information of the reversing space according to the map information; The position information of the reversing space is generated, and the target point position information of the reversing space is generated; the reversing trajectory information in the reversing coordinate system is fitted according to the vehicle position information and the target point position information of the reversing space.
- the vehicle position information refers to the position information of the vehicle itself, and the vehicle position information is obtained according to the high-precision positioning device of the vehicle, including the coordinates of the current position of the vehicle and the heading angle.
- the map information of the high-precision map is received, and the map information mainly includes the specific location information of the reversing space where the vehicle needs to reverse, including the coordinates of the four corners of the reversing space and the heading angle. According to the coordinates of the four corners of the reversing space, the position information of the target point of the reversing space is generated.
- the method of fitting the reversing trajectory information in the reversing coordinate system according to the vehicle position information and the target point position information of the reversing space may be to record the vehicle center position when the vehicle is driving in the forward direction.
- reversing perform coordinate conversion based on the reversing coordinate system, convert the recorded forward driving GPS coordinate points to the reversing coordinate system, and generate a forward reversing track in the reversing coordinate system, and the data of the track point is reversing Coordinate point in the coordinate system.
- the above scenario can be realized in which the vehicle reverses and returns according to the forward trajectory.
- the method of fitting the reversing trajectory information in the reversing coordinate system according to the vehicle position information and the target point position information of the reversing space can also be based on the high-precision map and the reversing target parking point, according to the center position of the vehicle when reversing.
- GPS coordinates, using two-point and curve fitting (such as quintic polynomial), calculate the reversing trajectory data from the origin of the reversing coordinate system to the target point, and the data of the trajectory points are also the coordinate points in the reversing coordinate system.
- the above can realize the scene of reversing into the garage and parking in the side direction of the vehicle.
- filtering algorithms such as a digital filter and an average value filter can also be used to perform signal noise reduction filtering processing on the signals fed back by the positioning device and the speed sensor to remove interference signals.
- Step 204 Calculate the curvature of the track points within the range of the target track for reversing in real time according to the target track information for reversing, and obtain the target driving track in the reversing coordinate system according to the curvature of the track points within the range of the target track for reversing and the actual curvature of the vehicle point.
- the preset trajectory is the experience value, and the experience value of different vehicles may be different. Taking a truck as an example, the experience value when reversing is 5m.
- the control is carried out in advance to reduce the problem of low control accuracy caused by system delay.
- the larger the curvature corresponds to the larger the curve the larger the required change in the target steering wheel control amount, and the steering wheel rotation to the target angle has a certain delay, so it needs to be controlled in advance.
- Step S206 according to the target driving trajectory point in the reversing coordinate system, calculate the error information between the vehicle and the target driving trajectory point when reversing.
- the error information may include lateral position error information and heading angle error information.
- the lateral position error may include the lateral position error and the rate of change of the lateral position error
- the heading angle error may include the heading angle error and the rate of change of the heading angle error.
- a front-wheel-drive reversing dynamic model is established; according to the front-wheel-drive reversing dynamic model, the lateral position error information and the heading angle between the vehicle and the target driving trajectory point when reversing are calculated. Error information; calculate the longitudinal position error and speed error between the vehicle and the target driving trajectory point when reversing.
- a is the distance from the rear axle to the center of mass
- b is the distance from the front axle to the center of mass
- V X is the longitudinal direction of reversing driving.
- V y is the lateral speed of reverse driving
- ⁇ is the front wheel angle
- angular velocity is the angular velocity
- m is the vehicle mass
- a is the acceleration at the center of mass of the Y-axis
- F f is the lateral force of the front wheel
- F r is the lateral force of the rear wheel.
- a is the motion acceleration and centripetal acceleration of the Y-axis
- I z is about the z-axis
- y is the lateral position error value in the reversing coordinate system, is the change rate of lateral position error in the reversing coordinate system
- ⁇ is the heading angle error in the reversing coordinate system
- ⁇ is the rate of change of the heading angle error in the reversing coordinate system.
- the above is the derivation process of the dynamic model considering the forward driving of rear-wheel drive to realize reversing in the reversing coordinate system.
- the structure of the model is the same as that of forward automatic driving, but the calculation method of the state matrix parameters of the model is different. Therefore, when switching between forward automatic driving and reverse automatic driving, it is only necessary to adjust the parameter calculation method of the model to realize the reverse function, and the controller selection and control method can be reused.
- Step 208 performing reverse control according to the error information.
- control command is calculated according to the error information to correct the error and realize reverse vehicle control.
- the lateral steering wheel control amount is calculated, and the lateral steering wheel control command is obtained;
- the state equation model tracking the above four error variables is obtained according to the lateral dynamics model.
- the error state feedback controller for reversing is designed.
- the control algorithm can use LQR, PID, etc. to generate the lateral steering wheel control amount.
- the PID control algorithm is used to calculate the acceleration and deceleration of the vehicle. Control the amount, control the vehicle to reverse and park.
- the controlled steering wheel angle is output to the steering wheel control system to control the vehicle to reverse.
- Reversing control is performed according to the lateral steering wheel control command and the longitudinal driving control command.
- the lateral steering wheel control command is converted into a steering wheel turning and rotation percentage recognizable by the vehicle chassis, that is, the vehicle electronic steering device can recognize the steering wheel rotation.
- the signal is used to control the lateral movement of the vehicle;
- the longitudinal running control command is converted into the throttle or brake information that can be recognized by the electronic pedal of the vehicle chassis, and the longitudinal movement of the vehicle is controlled.
- the input variables considered include the vehicle speed vx, the actual front wheel angle ⁇ , and the predicted target angle ⁇ 0. Considering the actual speed and the difference between the actual rotation angle of the front wheel and the predicted target rotation angle, the weight coefficient of the throttle valve output is calculated to realize the coordination of longitudinal control and lateral control.
- start the reverse start lateral control calculates the absolute value of the difference between the target steering wheel angle and the actual steering wheel angle; calculate the throttle weight system according to the ratio of the absolute value and the target steering wheel angle, the The weight coefficient is used to control the opening of the throttle valve and then the speed of the vehicle in reverse; when the vehicle speed reaches a certain value, or the steering wheel difference is less than a certain value, the reverse start control is exited.
- the calculation method of the valve weight coefficient is as follows:
- the distance between the actual position of the vehicle and the target position is calculated to reach a certain error range of the target position, and when the speed is 0, it is judged that the vehicle has completed the parking and reversing action, and the reversing process is completed.
- control the vehicle to pull up the handbrake to enter the parking state; control the gear to switch to neutral; control the steering wheel position to return to zero.
- a reversing coordinate system is established with the speed direction of the rear wheels of the reversing vehicle as the positive direction, and the reversing target trajectory information of the vehicle in the reversing coordinate system is obtained, which can avoid errors caused by coordinate conversion using the position information of the reversing drivable area.
- the data point position of the maximum curvature change within a certain range is calculated in real time, and the reversing control is performed according to the error value between the target position and the vehicle, which can realize the advance control function of the control system and make up for the accumulation of errors caused by system delay and other reasons.
- the method improves the precision of automatic reversing control.
- the present application also provides an application scenario in which the automatic reversing control method is applied to a truck with a trailer, so as to realize the function of reversing by installing a reversing track on the truck with a trailer.
- the automatic reversing control scheme it is only necessary to adjust the calculation method of the control model, add the angle measurement device of the front and the trailer to the whole system, and then add the data of the hinge angle of the trailer and the front to achieve.
- a reversing coordinate system is established based on the center of mass of the front of the vehicle, and the driving direction of the rear wheels of the front of the vehicle is taken as the positive direction.
- the method includes: calculating the lateral position error information and the heading angle error information of the vehicle and the target driving trajectory point when the vehicle is reversing, based on the reversing dynamics model of the front wheel drive and the articulation angle information.
- calculating the lateral position error information and heading angle error information between the vehicle and the target driving trajectory point when reversing including: Hinge angle information, the coordinates of the center of mass of the front of the current vehicle in the reversing coordinate system, the length from the center of mass of the front to the hinge point, and the length from the center of mass of the trailer to the hinge point, the coordinates of the center of mass of the trailer are calculated, and the arc established by the center of mass of the trailer based on the reversing dynamics model of the front-wheel drive, select the first reference target point of the center of mass of the head on the reversing trajectory, and calculate the coordinate value of the center of mass of the head and the first reference point in the reversing coordinate system
- the lateral position error and heading angle error of the vehicle head based on the reversing dynamics model of the front wheel drive, select the second reference target point of the trailer mass center point on the
- the initial condition of the current vehicle state in the reversing coordinate system is calculated.
- the initial conditions include: the coordinate A of the center of mass of the head, the coordinate B of the center of mass of the trailer, the radius R of the arc established by the center of mass of the head and the trailer, and the angle ⁇ between the head and the trailer.
- L1 is the length from the center of mass of the head to the hinge point
- L2 is the length from the center of mass of the trailer to the hinge point.
- the lateral error e 1 and the heading angle error e 2 are calculated according to the coordinate values of point A and point P1 in the reversing coordinate system.
- the lateral error e 3 and the heading angle error e 4 of point B and point P2 in the reversing coordinate system are obtained.
- the lateral steering wheel control algorithm PI is designed according to the above errors to calculate the steering wheel control amount, so that the above five errors converge to 0.
- the truck with a trailer changes from the attitude AB to P1P2, and tracks the reversing trajectory target.
- the design idea of PI control algorithm is as follows:
- calculating the lateral position error information and the heading angle error information between the vehicle and the target driving trajectory point when reversing including: in the reversing trajectory Select the first reference target point of the center of mass of the head, based on the reversing dynamics model of the front wheel drive, and calculate the lateral position error and the heading angle error according to the coordinate values of the center of mass of the head and the first reference point in the reversing coordinate system ; According to the hinge angle between the trailer and the front, the coordinates of the center of mass of the front of the current vehicle in the reversing coordinate system, the length of the center of mass of the front to the hinge point, and the length parameters from the center of mass of the trailer to the hinge point, calculate the coordinates of the center of mass of the trailer; The center of mass coordinates select the second reference target point of the center of mass of the trailer on the reversing trajectory, and calculate the target articulation angle information according
- a kind of truck with trailer attitude AB and target attitude P1P2 consider controlling the front wheel mass center point A to the reversing trajectory point P1, and consider the difference between the hinge angle between the trailer and the front and the heading angle of the reversing trajectory target point P1P2.
- the schematic diagram is shown in Figure 9.
- the front of the vehicle is well controlled to the target trajectory point. If the articulation angle error also satisfies 0, the trailer can be controlled to the target trajectory point P2.
- the lateral position error of the head AP1 is e 1 , the heading angle error e 2 , the articulation angle error e ⁇ ,
- the lateral steering wheel control algorithm PI is designed to calculate the steering wheel control amount, so that the above three errors converge to 0.
- the truck with a trailer changes from the attitude AB to P1P2, and tracks the reversing trajectory target.
- the design idea of PI control algorithm is as follows:
- an automatic reversing control device including:
- the target trajectory acquisition module 1002 is used to acquire the reversing target trajectory information of the vehicle in the reversing coordinate system generated according to the vehicle position and the reversing position position; wherein, the position of the center of mass of the vehicle is taken as the center point, and the direction of the speed of the rear wheels of the reversing vehicle is the positive direction Establish a reversing coordinate system.
- the target driving trajectory point determination module 1004 is used to calculate the curvature of the trajectory points in the reversing target trajectory range in real time according to the reversing target trajectory information, and obtain the reversing according to the curvature of the trajectory points in the reversing target trajectory range and the actual curvature of the vehicle
- An error calculation module 1006 configured to use the error information of the target driving track point under the reversing coordinate system
- the reversing control module 1008 is configured to perform reversing control according to the error information.
- the above automatic reversing control device establishes a reversing coordinate system with the direction of the rear wheel speed of reversing as a positive direction, and obtains the reversing target trajectory information of the vehicle in the reversing coordinate system, which can avoid errors caused by coordinate conversion using the position information of the reversing drivable area.
- the data point position of the maximum curvature change within a certain range is calculated in real time, and the reversing control is performed according to the error value between the target position and the vehicle, which can realize the advance control function of the control system and make up for the accumulation of errors caused by system delay and other reasons.
- the method improves the precision of automatic reversing control.
- a target trajectory acquisition module is used to acquire map information and vehicle location information; acquire location information of a reversing space according to the map information, and generate target point location information of the reversing space according to the location information of the reversing space; According to the vehicle location information and the location information of the reversing space target point, the reversing target trajectory information in the system of reversing coordinates is fitted.
- the target driving trajectory point determination module includes:
- the judgment module is used for judging whether the position of the center of mass of the vehicle body is greater than a preset distance from the end point of the reversing trajectory according to the information of the reversing target trajectory.
- the curvature obtaining module is used for traversing the curvature data of the track points within the range of the vehicle position to the preset distance length when the judgment result of the judgment module is yes, to obtain the curvature of the track points within the reversing target track range.
- the difference obtaining module is used to obtain the absolute difference between the curvature of the track point within the range of the reversing target track and the actual curvature of the vehicle.
- the selection module is used for selecting the trajectory data point with the largest absolute difference to obtain the target driving trajectory point in the reversing coordinate system.
- the error calculation module includes:
- a first error calculation module configured to calculate the lateral position error information and the heading angle error information of the vehicle and the target travel trajectory point when the vehicle is reversing according to the reversing dynamics model of the front-wheel drive;
- the second error calculation module is used to calculate the longitudinal position error and speed error between the vehicle and the target travel trajectory point when reversing.
- the reversing control module includes:
- a lateral control instruction acquisition module configured to calculate the lateral steering wheel control amount according to the lateral position error information and the heading angle error information to obtain the lateral steering wheel control instruction
- the longitudinal control instruction acquisition module is used to calculate the longitudinal driving control instruction for controlling the vehicle to reverse according to the longitudinal position error, speed error and acceleration data between the vehicle and the target driving track point when reversing;
- the reversing module is configured to perform reversing control according to the lateral steering wheel control instruction and the longitudinal driving control instruction, and complete reversing when the distance between the actual position of the vehicle and the target position is within the error range and the speed is 0.
- a reversing module is used to convert the lateral steering wheel control command into a steering wheel turning and rotation percentage identifiable by the vehicle chassis to control the lateral movement of the vehicle; convert the longitudinal travel control command into an electronic pedal of the vehicle chassis Recognizable throttle or brake information to control the longitudinal movement of the vehicle.
- the reversing module is further configured to start the reverse start lateral control when the vehicle is reversing and the vehicle is not started; calculate the absolute value of the difference between the target steering wheel angle and the actual steering wheel angle; according to the absolute value and the target steering wheel angle
- the weighting system of the throttle valve is calculated by the ratio of .
- the vehicle includes a truck with a trailer; the reversing coordinate system takes the center of mass of the front of the truck as a center, and takes the running direction of the rear wheels of the front as a positive direction.
- the automatic reversing control also includes:
- the articulation information acquisition module is used for acquiring the articulation angle information of the trailer with the trailer and the front of the vehicle.
- the first error calculation module is configured to calculate the lateral position error information and heading angle error information between the vehicle and the target travel trajectory point when the vehicle is in reverse based on the reversing dynamics model of the front wheel drive and the articulation angle information.
- the first error calculation module is configured to, according to the hinge angle information between the trailer and the front of the vehicle, the coordinates of the center of mass of the front of the current vehicle in the reversing coordinate system, the length from the center of mass of the front to the hinge point, and the length of the trailer.
- the length from the center of mass to the hinge point is calculated to obtain the coordinates of the center of mass of the trailer and the radius of the arc established by the center of mass of the trailer; based on the reversing dynamics model of the front-wheel drive, select the first reference target of the center of mass of the head on the reversing trajectory point, according to the center of mass of the head and the coordinate value of the first reference point in the reversing coordinate system, calculate the lateral position error and heading angle error of the head; The second reference target point of the center of mass point, according to the coordinate value of the center of mass point of the trailer and the second reference point in the reversing coordinate system, calculate the lateral position error and heading angle error of the trailer; according to the curvature information of the second reference point and the radius calculated from the initial state, calculate the curvature error.
- the lateral control instruction acquisition module is used to make the lateral position error, heading angle error, and curvature error of the head and the trailer to be zero, and the trailer truck changes from the initial position to the target position as the goal, calculate the lateral steering wheel Control quantity, get lateral steering wheel control command.
- the first error calculation module is configured to select a first reference target point of the center of mass of the head of the vehicle on the reversing trajectory, based on the reversing dynamics model of the front wheel drive, according to the center of mass of the head and the first reference target point.
- the coordinate value of the reference point in the reversing coordinate system is used to calculate the lateral position error and heading angle error; according to the hinge angle between the trailer and the front of the vehicle, the coordinates of the center of mass of the front of the current vehicle in the reversing coordinate system, and the length from the center of mass of the front to the hinge point,
- the length parameter from the center of mass of the trailer to the hinge point is calculated to obtain the coordinates of the center of mass of the trailer;
- the second reference target point of the center of mass of the trailer is selected on the reversing trajectory according to the coordinates of the center of mass of the trailer, and the heading angle of the first reference target point and the second reference target point is based on the
- the information calculates the target hinge angle information; according to the target hinge angle information and the actual hinge angle information, the hinge angle error is calculated.
- the lateral control instruction acquisition module is used to calculate the lateral steering wheel control quantity and obtain the lateral steering wheel control instruction with the articulation angle error, the lateral position error of the head mass center to the first target position and the heading angle error being zero as the target.
- All or part of the modules in the above automatic reversing control device can be implemented by software, hardware and combinations thereof.
- the above modules may be embedded in or independent of the processor in the vehicle in the form of hardware, or may be stored in the memory in the vehicle in the form of software, so that the processor can call and execute operations corresponding to the above modules.
- a vehicle in one embodiment, is provided, the internal structure of which may be as shown in FIG. 11 .
- the vehicle includes a vehicle controller, lidar, cameras, radar sensors and memory connected via a system bus. Among them, the vehicle controller is used to provide computing and control capabilities.
- the memory of the vehicle includes a non-volatile storage medium and an internal memory.
- the nonvolatile storage medium stores an operating system and a computer program.
- the internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium.
- the communication interface of the vehicle is used for wired or wireless communication with an external terminal, and the wireless communication can be realized by WIFI, operator network, NFC (Near Field Communication) or other technologies.
- WIFI WIFI
- operator network operator network
- NFC Near Field Communication
- FIG. 11 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the vehicle to which the solution of the present application is applied. More or fewer components are shown in the figures, either in combination or with different arrangements of components.
- a vehicle including a vehicle controller, and a lidar, a camera, a radar sensor, and a memory connected to the vehicle controller, the memory having a computer program stored therein, the vehicle controller executing a computer In the program, the steps of the methods of the above-mentioned embodiments are implemented.
- a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of the methods of the foregoing embodiments.
- Non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, or optical memory, and the like.
- Volatile memory may include random access memory (RAM) or external cache memory.
- the RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
Landscapes
- Engineering & Computer Science (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
一种自动倒车控制方法，该方法以倒车的后轮速度方向为正方向建立倒车坐标系，获取车辆在倒车坐标系下的倒车目标轨迹信息，能够避免使用倒车可行驶区域位置信息进行坐标转换带来的误差，根据倒车目标行驶轨迹实时计算一定范围内最大曲率变化的数据点位置，根据该目标位置与车辆的误差值进行倒车控制，可实现控制系统的提前控制功能，弥补系统延迟等原因导致误差的累积，提升倒车尤其是泊车位控制精准度。该方法提高了自动倒车控制的精度。还涉及一种自动倒车控制装置、一种车辆和一种计算机可读存储介质。
Description
本申请涉及自动驾驶控制技术领域，特别是涉及一种自动倒车控制方法、装置、车辆和存储介质。
随着汽车智能化、网联化技术发展，我国的智能驾驶技术也在飞速发展当中，并且在特定园区物流及港口等特定区域自动驾驶已经陆续实现。
车辆的自动倒车属于自动驾驶中不可或缺的技术，尤其在辅助驾驶和部分无人车技术日渐成熟，应用场景越来越丰富去前提下，对自主倒车入库提出了需求，比如无人矿区矿卡的自主装/卸矿、带挂卡车的辅助倒车、轿车的自主泊车等。由于汽车转向系统普遍采用前轮驱动，这使得车辆在前向自动驾驶时能良好的跟随规划轨迹进行控制。而对于轴距较长的车辆采用前轮驱动进行倒车控制时，尤其如带挂卡车的倒车控制时，往往由于控制模型的不准确、传感器信号的误差、前轮驱动执行机构的响应延迟等原因，导致大型车辆的倒车控制效果不理想，倒车精度无法满足要求。
发明内容
基于此，有必要针对上述技术问题，提供一种能够提高倒车精度的自动倒车控制方法、装置、车辆和存储介质。
一种自动倒车控制方法，所述方法包括：
获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息；其中，以车辆质心位置为中心点，以倒车的后轮速度方向为正方向建立倒车坐标系；
根据所述倒车目标轨迹信息实时计算倒车目标轨迹范围内轨迹点的曲率，根据所述倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率，得到所述倒车坐标系下的目标行驶轨迹点；
根据所述倒车坐标系下的所述目标行驶轨迹点，计算倒车时车辆与目标行驶轨迹点的误差信息；
根据所述误差信息进行倒车控制。
一种自动倒车控制装置，所述装置包括：
目标轨迹获取模块，用于获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息；其中，以车辆质心位置为中心点，以倒车的后轮速度方向为正方向建立倒车坐标系；
目标行驶轨迹点确定模块，用于根据所述倒车目标轨迹信息实时计算倒车目标轨迹范围内轨迹点的曲率，根据所述倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率，得到所述倒车坐标系下的目标行驶轨迹点；
误差计算模块，用于根据所述倒车坐标系下的所述目标行驶轨迹点，计算倒车时车辆与目标行驶轨迹点的误差信息；
倒车控制模块，用于根据所述误差信息进行倒车控制。
一种车辆，包括车辆控制器，以及与所述车辆控制器连接的激光雷达、摄像头、雷达感应器和，所述存储器存储有计算机程序，所述车辆控制器执行所述计算机程序时实现以下步骤：
获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息；其中，以车辆质心位置为中心点，以倒车的后轮速度方向为正方向建立倒车坐标系；
根据所述倒车目标轨迹信息实时计算倒车目标轨迹范围内轨迹点的曲率，根据所述倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率，得到所述倒车坐标系下的目标行驶轨迹点；
根据所述倒车坐标系下的所述目标行驶轨迹点，计算倒车时车辆与目标行驶轨迹点的误差信息；
根据所述误差信息进行倒车控制。
一种计算机可读存储介质，其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以下步骤：
获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息；其中，以车辆质心位置为中心点，以倒车的后轮速度方向为正方向建立倒车坐标系；
根据所述倒车目标轨迹信息实时计算倒车目标轨迹范围内轨迹点的曲率，根据所述倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率，得到所述倒车坐标系下的目标行驶轨迹点；
根据所述倒车坐标系下的所述目标行驶轨迹点，计算倒车时车辆与目标行驶轨迹点的误差信息；
根据所述误差信息进行倒车控制。
上述自动倒车控制方法、装置、车辆和存储介质，以倒车的后轮速度方向为正方向建立倒车坐标系，获取车辆在倒车坐标系下的倒车目标轨迹信息，能够避免使用倒车可行驶区域位置信息进行坐标转换带来的误差，根据倒车目标行驶轨迹实时计算一定范围内最大曲率变化的数据点位置，根据该目标位置与车辆的误差值进行倒车控制，可实现控制系统的提前控制功能，弥补系统延迟等原因导致误差的累积，提升倒车尤其是泊车位控制精准度。该方法提高了自动倒车控制的精度。
图1为一个实施例中自动倒车控制方法的应用环境图；
图2为一个实施例中自动倒车控制方法的流程示意图；
图3为一个实施例中倒车坐标系和车辆倒车运动学模型的示意图；
图4为一个实施例中生成目标轨迹数据的步骤流程示意图；
图5为一个实施例中前轮驱动的倒车动力学模型的示意图；
图6为一个实施例中后轮速度方向角和车辆实际速度的关系示意图；
图7为一个实施例中带挂卡车的铰接信息在倒车坐标系的示意；
图8为一个实施例中误差信息的示意图；
图9为另一个实施例中误差信息的示意图；
图10为一个实施例中自动倒车控制装置的结构框图；
图11为一个实施例中车辆的内部结构图。
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请提供的自动倒车控制方法，可以应用于如图1所示的应用环境中。
该应用环境包括车辆100，车辆配置有激光雷达101、摄像头102、雷达感应器103以及车辆控制器104。其中，激光雷达101、摄像头102、雷达感应器103分别与控制器104连接。激光雷达101采集设备环境的三维地图，摄像头102实时采集设备周围图像。基于图像识别技术可辅助识别信号灯各障碍物。雷达感应器可确定障碍物的距离。控制器104存储有高精度地图，利用发激光雷达101、摄像头102以及雷达感应器103的数据以及高精度地图进行设备控制实现自动行驶。车辆100可以为矿区的矿卡、重卡、公交车、轿车等自动驾驶汽车。可用于自动驾驶车辆实际应用中需要进行自主倒车才能完成车位泊车、卸矿点卸矿、路边侧方位停车等场景，同样可应用于辅助驾驶员自动控制车辆按照规划路径进行倒车行驶的场景。
在一个实施例中，如图2所示，提供了一种自动倒车控制方法，以该方法应用于图1中的车辆控制器为例进行说明，包括以下步骤：
步骤202，获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息；其中，以车辆质心位置为中心点，以倒车的后轮速度方向为正方向建立倒车坐标系。
其中，车辆位置是指车辆当前所处的位置。倒车位位置是指倒车的目标位置。以车辆位置为起点，以倒车位位置为终点，生成车辆在倒从坐标系下从车辆位置至到倒车位位置的倒车目标估计信息。
具体地，考虑倒车时车辆后轮运动方向为正方向，采用将车身实际前轮驱动 定义为倒车时后轮驱动的车辆模型，即可理解为后轮驱动车辆正方向行驶的模型。倒车时，考虑倒车行驶方向为正方向，采用GPS全局定位或者基站的局部定位方式，建立基于车辆质心位置的倒车坐标系。坐标系和车辆倒车运动学模型如下如所图3所示。
图中，XOY为建立的倒车坐标系，V
X为倒车行驶的速度方向。XOY倒车坐标系可以准确描述倒车时车辆的运动学特性，采用倒车的行驶速度方向作为坐标系的正方向。基于该坐标系推导倒车的侧向动力学模型和纵向动力学模型，并代入该坐标系下的横向误差和纵向误差计算前轮转角控制量和气节门刹车控制量，实现车辆倒车到目标点的功能。
建立XOY倒车坐标系，相对于前向自动驾驶的采用的坐标系，存在以下几个优势：
(1)、前向自动驾驶坐标系的正方向为前轮行驶的速度方向，自动驾驶时规划的前向行驶轨迹x方向数据为正值，但是一般情况下由于自动驾驶需考虑车辆的行驶位置是否满足要求，需保留一段x方向为负值的数据(例如车辆位置超过规划的目标位置时，通过规划目标位置x方向为负值告诉车辆超过了目标位置)。而如果继续采用该坐标系生成倒车的规划目标位置，规划车辆向后方向行驶，生成的轨迹位置数据为负值，与前向自动驾驶的方案产生冲突。
(2)、规划模块倒车时生成前向自动驾驶坐标系下倒车轨迹，需进行特殊处理，例如倒车轨迹生成的加速度，位置数据为负，实际是要求倒车时加速行驶，不符合车辆运动学，控制方法使用目标数据计算控制量时需进行坐标转换和位置转换。基于倒车坐标系生成轨迹数据近似于前向自动驾驶的轨迹生成方式，控制方法上不用对目标数据进行任何处理，控制计算误差量的方式保持一致。
(3)、同样的，倒车时，感知障碍物的位置信息在前向自动驾驶坐标系下需进行坐标转换和位置信息转换。感知倒车的可行驶区域的位置信息同样需要进行坐标转换，而坐标转换受航向角影响很大，转换时容易产生误差。
(4)、采用前向自动驾驶坐标系计算的侧向动力学模型考虑的是前轮驱动，计算方向盘转角控制车辆按照前轮驱动进行倒车时，存在误差。
(5)、调整坐标系为倒车坐标系后，仅需要重新推导后轮驱动的倒车侧向动 力学模型，而同一款车型的侧向动力学模型是不变的。且以上所述的所有模块坐标转换和位置信息转换，控制模块的特殊处理方式都不需要。
根据倒车坐标系，计算一条满足倒车坐标系的目标轨迹信息。目标轨迹的起始点从驱动轮出发，以倒车坐标系正方向生成一条不少于1个数据点的轨迹，数据点主要包括基于倒车坐标系下的坐标、航向角、曲率、距坐标原点曲线长度s、速度、加速度等数据。
一种方式中，基于高精度地图建立目标区域所有的停车位，停车位的位置信息在地图上已经明确。根据明确的停车位置信息，在高精度地图上离线制作停车位的倒车目标轨迹信息。制作方式采用实际倒车录制倒车的定位信息点，离线拟合出连续倒车曲线。车辆倒车时，根据车辆定位信息和拟合曲线计算出入库的倒车轨迹。因为目前的车位信息固定，且规范。同一区域下的泊车位置，倒车估计拟合曲线可以复用。
若采用离线拟合的连续倒车曲线，车辆控制器根据车辆自身位置信息计算出全局坐标系下的倒车轨迹，经过坐标转换后得到基于倒车坐标系下的倒车轨迹信息。
一种实施方式中，获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息，包括：获取地图信息和车辆位置信息，根据地图信息获取倒车位的位置信息；根据倒车位的位置信息，生成倒车位的目标点位置信息；根据所述车辆位置信息和所述倒车位的目标点位置信息拟合出在倒车坐标系下的倒车轨迹信息。
其中，车辆位置信息指的是车辆自身的位置信息，根据车辆的高精度定位装置获取车辆位置信息，包括车辆当前位置所在坐标以及航向角。
其中，接收高精度地图的地图信息，地图信息信息主要包括车辆需要倒车的倒车位的具体位置信息，包括倒车位的四个角的坐标，航向角。根据倒车位的四个角的坐标，生成倒车位的目标点位置信息。
具体地，根据所述车辆位置信息和所述倒车位的目标点位置信息拟合出在倒车坐标系下的倒车轨迹信息的方法，可以为采用前向行驶时记录车辆前向行驶时车辆中心位置的GPS坐标点，倒车时，基于倒车坐标系进行坐标转换，将记 录的前向行驶GPS坐标点转换到倒车坐标系，在倒车坐标系下生成一条正方向的倒车轨迹，轨迹点的数据为倒车坐标系下的坐标点。以上可实现车辆按前向行驶的轨迹倒车返回的场景。
根据所述车辆位置信息和所述倒车位的目标点位置信息拟合出在倒车坐标系下的倒车轨迹信息的方法，还可以基于高精度地图和倒车目标停车点，根据倒车时车辆中心位置的GPS坐标，采用两点和曲线拟合的方式(如五次多项式)，计算出倒车坐标系原点到目标点的倒车轨迹数据，轨迹点的数据同样为倒车坐标系下的坐标点。以上可实现车辆侧方位倒车入库停车的场景。
其中，还可采用数字滤波器、均值滤波器等滤波算法对对定位装置和速度传感器反馈的信号进行信号降噪滤波处理，去除干扰信号。
步骤204，根据所述倒车目标轨迹信息实时计算倒车目标轨迹范围内轨迹点的曲率，根据所述倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率，得到所述倒车坐标系下的目标行驶轨迹点。
预设轨迹为经验值，不同车辆的经验值可能不同，以卡车为例，倒车时的经验值5m。通过预测一段时距内横向控制的最大目标变化值，提前控制，减小系统延时导致的控制精度低问题。一般情况下，曲率越大对应的弯道越大，需要的目标方向盘控制量变化越大，而方向盘的转动到目标角度是有一定延时的，因此需要提前控制。
具体地，如图4所示，包括以下步骤：
S402，根据所述倒车目标轨迹信息，判断车身质心位置距离倒车轨迹终点是否大于预设距离；
若是，则执行S404，若否，则执行S405。
S404，遍历车辆位置到预设距离长度范围内的轨迹点的曲率数据，得到倒车目标轨迹范围内轨迹点的曲率。
S405，遍历车辆位置到轨迹终点范围内的轨迹点的曲率数据，得到倒车目标轨迹范围内轨迹点的曲率。
在步骤S404和S405之后，执行：
S406，获取倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率的绝对差值；
S408，选择绝对差值最大的轨迹数据点，得到所述倒车坐标系下的目标行驶轨迹点。
在步骤S204之后，执行：
步骤S206，根据倒车坐标系下的所述目标行驶轨迹点，计算倒车时车辆与目标行驶轨迹点的误差信息。
其中，误差信息可包括横向位置误差信息和航向角误差信息。横向位置误差可以包括横向位置误差、横向位置误差变化率，航向角误差可以包括航向角误差、航向角误差变化率。
具体地，根据倒车动力学模型和倒车坐标系，建立前轮驱动的倒车动力学模型；根据前轮驱动的倒车动力学模型，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息；计算倒车时车辆与目标行驶轨迹点的纵向位置误差和速度误差。
基于倒车坐标系和倒车时前轮转向驱动的车辆模型，建立前轮驱动的倒车侧向动力学模型。模型示意图简化如下图5所示。
图中，a为后轴到质心的距离，b为前轴到质心的距离，V
X为倒车行驶的纵
向速度，V
y为倒车行驶的横向速度，δ为前轮转角，
为方向角速度。
根据倒车侧向动力学模型推导侧向动力学的过程如下：
根据牛顿第二定律，上述模型中的侧向动力学描述为：
ma＝F
f+F
r
绕z轴转矩的动力学方程为：
式中m为车质量，a为Y轴质心处的加速度，F
f为前轮的侧向力，F
r为后轮的侧向力。a为Y轴的运动加速度和向心加速度，I
z为绕z轴的
转动惯量。即
根据车辆动力学基本原理，即轮胎侧向力与侧偏角存在一定比例关系，F
f＝-C
fθ
f，F
r＝-C
rθ
r。θ
f为前轮的速度方向角，θ
r为后轮的速度方向角，δ为上文提到的前轮转角。C
f和C
r为前轮和后轮的轮胎刚度。
倒车时，对于后轮驱动的速度在倒车坐标系XOY下的车辆速度与速度方向角的关系图如下：
后轮速度方向角和车辆实际速度的关系图6所示。
利用小角度近似法，得：
同理可得：
根据以上解析，得出运动学模型表示如下：
得出
形式的倒车侧向动力学状态方程如下：
上式中，y为倒车坐标系下横向位置误差值，
为倒车坐标系下横向位置误差变化率，ψ为倒车坐标系下航向角误差，
为倒车坐标系下航向角误差变化率。
同时，还得考虑倒车时倒车轨迹曲率的力学模型，确保车辆在一定曲率下倒车时良好跟踪轨迹曲率变化，不产生较大的横向位置误差。因倒车时的轨迹曲率力学模型与前向自动驾驶的模型一致，已经有大量文献推导证明，本专利技术方案仅仅引用。
以上为倒车坐标系下考虑后轮驱动正向行驶实现倒车的动力学模型推导过程，模型结构形式与前向自动驾驶一致，但模型的状态矩阵参数计算方式不同。因此在前向自动驾驶和倒车自动驾驶切换时，仅需调整模型的参数计算方式即 可实现倒车功能，控制器选择和控制方式都可复用。
步骤208，根据所述误差信息进行倒车控制。
具体地，根据误差信息计算控制指令，以修正误差，实现倒车控制。
具体地，根据所述横向位置误差信息和航向角误差信息，计算横向方向盘控制量，得到横向方向盘控制指令；根据倒车时车辆与所述目标行驶轨迹点的纵向位置误差、速度误差以及加速度数据，计算控制车辆倒车的纵向行驶控制指令；根据所述横向方向盘控制指令和所述纵向行驶控制指令进行倒车控制；当车辆实际位置与目标位置的距离在误差范围内，且速度为0时，完成倒车。
其中，根据侧向动力学模型得到跟踪上述四个误差变量的状态方程模型，根据状态方程模型，设计倒车的误差状态反馈控制器，控制算法可采用LQR、PID等，生成横向方向盘控制量。
其中，根据倒车时车辆与目标行驶轨迹点的纵向位置误差、速度误差，倒车坐标系下的倒车轨迹目标点的速度信息，包括时间、速度、加速度等信息，采用PID控制算法计算车辆加减速的控制量，控制车辆倒车行驶和停车。
根据误差状态反馈控制器计算的方向盘角度，考虑状态方程中轨迹曲率产生稳态误差的曲率补偿和路面坡度角影响的补偿，得到控制的方向盘角度输出到方向盘控制系统控制车辆倒车。
根据所述横向方向盘控制指令和所述纵向行驶控制指令进行倒车控制，具体地，将所述横向方向盘控制指令转换为车辆底盘可识别的方向盘转向和转动百分比，即车辆电子转向器可识别方向盘转动信号，控制车辆横向动作；将所述纵向行驶控制指令转换为车辆底盘电子踏板可识别的气节门或刹车信息，控制车辆纵向动作。
考虑司机实际倒车入库时，先将方向盘达到一个预测的角度，再让车辆起步。主要原因是倒车的纵向行驶距离短，如要在短时距内精准入位，需提前控制。因此技术方案加入倒车起步横向控制。考虑的输入变量包括车辆速度vx、前轮实际转角δ、预测目标转角δ0。考虑实际速度以及前轮实际转角与预测目标转角的差值情况下，计算气节门输出的权重系数，实现纵向控制和横向控制协同配合。
具体地，当倒车且车辆未启动时，启动倒车起步横向控制；计算目标方向盘 角度与实际方向盘角度差值的绝对值；根据所述绝对值与目标方向盘角度的比值计算气节门权重系统，所述权重系数用于控制气节门的开度进而控制倒时车车辆速度；当所述车辆速度达到一定值，或方向盘差值小于一定值时，退出倒车起步控制。
气节门权重系数计算方式如下：
Δδ＝|δ-δ
0|
进入倒车时，计算的气节门控制量T
out＝K
throttle*T
throttle。
在倒车过程中，计算车辆实际位置与目标位置的距离，达到目标位置一定误差范围，且速度为0时，判断车辆完成泊车倒车动作，倒车处理完成。倒车处理完成后，控制车辆拉起手刹进入驻车状态；控制挡位切换为空挡；控制方向盘位置归零。
上述自动倒车控制方法，以倒车的后轮速度方向为正方向建立倒车坐标系，获取车辆在倒车坐标系下的倒车目标轨迹信息，能够避免使用倒车可行驶区域位置信息进行坐标转换带来的误差，根据倒车目标行驶轨迹实时计算一定范围内最大曲率变化的数据点位置，根据该目标位置与车辆的误差值进行倒车控制，可实现控制系统的提前控制功能，弥补系统延迟等原因导致误差的累积，提升倒车尤其是泊车位控制精准度。该方法提高了自动倒车控制的精度。
进一步的，本申请还提供一种将该自动倒车控制方法应用于带挂卡车的应用场景，用于实现带挂卡车安装倒车轨迹实现倒车功能。在普通自动倒车控制方案的基础上，仅需要调整控制模型计算方法，整个系统中增加车头与挂车角度测量装置，然后在增加挂车与车头铰接角度的数据即可实现。
具体地：基于车头质心建立倒车坐标系，以车头后轮行驶方向为正方向。
获取所述带挂卡车的挂车与车头的铰接角度信息，进一步地，根据所述前轮驱动的倒车动力学模型，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息，包括：基于所述前轮驱动的倒车动力学模型和所述铰接角 度信息，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息。
具体地，基于所述前轮驱动的倒车动力学模型和所述铰接角度信息，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息，包括：根据所述挂车与车头的铰接角度信息，当前车辆在倒车坐标系下的车头质心的坐标、车头的质心到铰接点处的长度、挂车质心到铰接点处长度，计算得到挂车质心的坐标，以及以挂车质心建立的圆弧的半径；基于所述前轮驱动的倒车动力学模型，在倒车轨迹上选择车头质心点的第一参考目标点，根据所述车头质心和第一参考点在倒车坐标系下的坐标值，计算车头的横向位置误差和航向角误差；基于所述前轮驱动的倒车动力学模型，在倒车轨迹上选择挂车质心点的第二参考目标点，根据所述挂车质心点和第二参考点在倒车坐标系下的坐标值，计算挂车的横向位置误差和航向角误差。
具体地，根据车头与挂车的铰接角度，计算当前车辆状态在倒车坐标系下的初始条件。初始条件包括：车头质心的坐标A、挂车质心的坐标B、以车头和挂车质心建立的圆弧的半径R，车头和挂车的夹角θ。L1为车头的质心到铰接点处的长度，L2为挂车质心到铰接点处长度。示意图描述如图7所示，.
推导过程如下：
在倒车轨迹上选择车头质心点A的参考目标点P1，以及挂车质心点B的参考目标点P2。根据A点和P1点在倒车坐标系下的坐标值计算横向误差e
1、航向角误差e
2。同理得到B点和P2点在倒车坐标系下的横向误差e
3、航向角误差e
4。根据P2点的曲率信息和初始状态计算的半径R计算曲率误差e
ρ，e
ρ＝ρ
P2-1/R。示意图如图8所示：
根据所述第二参考点的曲率信息和初始状态计算的半径，计算曲率误差；根据所述横向位置误差信息和航向角误差信息，计算横向方向盘控制量，得到横向方向盘控制指令，包括：以使所述车头和挂车的横向位置误差、航向角误差、和 所述曲率误差为零，所述带挂卡车从初始位置变化到目标位置为目标，计算横向方向盘控制量，得到横向方向盘控制指令。
具体地，根据以上误差设计横向方向盘控制算法PI计算方向盘控制量，使得以上五个误差收敛到0。带挂卡车从姿态AB倒车变化到P1P2，跟踪倒车轨迹目标。PI控制算法设计思路如下：
式中
控制系统的稳定性分析，已有很成熟的方法，本文不做阐述。
在另一个实施例中，基于所述前轮驱动的倒车动力学模型和所述铰接角度信息，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息，包括：在倒车轨迹上选择车头质心点的第一参考目标点，基于所述前轮驱动的倒车动力学模型，根据所述车头质心和第一参考点在倒车坐标系下的坐标值计算横向位置误差和航向角误差；根据所述挂车与车头铰接角度，当前车辆在倒车坐标系下的车头质心坐标，车头的质心到铰接点处的长度，挂车质心到铰接点处长度参数，计算得到挂车质心的坐标；根据挂车质心坐标在倒车轨迹上选择挂车质心点的第二参考目标点，根据第一参考目标点和第二参考目标点的航向角信息计算目标铰接角度信息；根据所述目标铰接角度信息和实际铰接角度信息，计算铰接角误差。一种的带挂卡车姿态AB和目标姿态P1P2，考虑将前轮质心点A控制到倒车轨迹点P1，同时考虑挂车与车头铰接角度和倒车轨迹目标点P1P2的航向角度差。示意图图9所示。
当A点和P1点的横向位置误差和航向角误差等于0，实现车头良好控制到目标轨迹点。若铰接角误差同样满足为0，即可实现挂车控制到目标轨迹点P2。车头AP1的横向位置误差为e
1、航向角误差e
2，铰接角误差e
θ，
根据所述横向位置误差信息和航向角误差信息，计算横向方向盘控制量，得 到横向方向盘控制指令，包括：以所述铰接角误差、车头质心到第一目标位置的横向位置误差和航向角误差为零为目标，计算横向方向盘控制量，得到横向方向盘控制指令。
根据以上误差设计横向方向盘控制算法PI计算方向盘控制量，使得以上三个误差收敛到0。带挂卡车从姿态AB倒车变化到P1P2，跟踪倒车轨迹目标。PI控制算法设计思路如下：
式中
应该理解的是，虽然图2的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图2中的至少一部分步骤可以包括多个步骤或者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。
在一个实施例中，如图10所示，提供了一种自动倒车控制装置，包括：
目标轨迹获取模块1002，用于获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息；其中，以车辆质心位置为中心点，以倒车的后轮速度方向为正方向建立倒车坐标系。
目标行驶轨迹点确定模块1004，用于根据所述倒车目标轨迹信息实时计算倒车目标轨迹范围内轨迹点的曲率，根据所述倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率，得到所述倒车坐标系下的目标行驶轨迹点；
误差计算模块1006，用于根据所述倒车坐标系下的所述目标行驶轨迹点的误差信息；
倒车控制模块1008，用于根据所述误差信息进行倒车控制。
上述自动倒车控制装置，以倒车的后轮速度方向为正方向建立倒车坐标系，获取车辆在倒车坐标系下的倒车目标轨迹信息，能够避免使用倒车可行驶区域位置信息进行坐标转换带来的误差，根据倒车目标行驶轨迹实时计算一定范围内最大曲率变化的数据点位置，根据该目标位置与车辆的误差值进行倒车控制，可实现控制系统的提前控制功能，弥补系统延迟等原因导致误差的累积，提升倒车尤其是泊车位控制精准度。该方法提高了自动倒车控制的精度。
在另一个实施例中，目标轨迹获取模块，用于获取地图信息和车辆位置信息；根据地图信息获取倒车位的位置信息，根据所述倒车位的位置信息，生成倒车位的目标点位置信息；根据所述车辆位置信息和所述倒车位目标点位置信息，拟合出倒车坐标下系下的倒车目标轨迹信息。
在另一个实施例中，目标行驶轨迹点确定模块，包括：
判断模块，用于根据所述倒车目标轨迹信息，判断车身质心位置距离倒车轨迹终点是否大于预设距离。
曲率获取模块，用于在所述判断模块的判断结果为是时，遍历车辆位置到预设距离长度范围内的轨迹点的曲率数据，得到倒车目标轨迹范围内轨迹点的曲率。
差值获取模块，用于获取倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率的绝对差值。
选择模块，用于选择绝对差值最大的轨迹数据点，得到所述倒车坐标系下的目标行驶轨迹点。
在另一个实施例中，误差计算模块，包括：
动力学模型，用于基于所述倒车坐标系和倒车时前轮转向驱动的车辆模型，建立前轮驱动的倒车动力学模型；
第一误差计算模块，用于根据所述前轮驱动的倒车动力学模型，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息；
第二误差计算模块，用于计算倒车时车辆与目标行驶轨迹点的纵向位置误差和速度误差。
在另一个实施例中，倒车控制模块，包括：
横向控制指令获取模块，用于根据所述横向位置误差信息和航向角误差信息，计算横向方向盘控制量，得到横向方向盘控制指令；
纵向控制指令获取模块，用于根据倒车时车辆与所述目标行驶轨迹点的纵向位置误差、速度误差以及加速度数据，计算控制车辆倒车的纵向行驶控制指令；
倒车模块，用于根据所述横向方向盘控制指令和所述纵向行驶控制指令进行倒车控制，当车辆实际位置与目标位置的距离在误差范围内，且速度为0时，完成倒车。
在另一个实施例中，倒车模块，用于将所述横向方向盘控制指令转换为车辆底盘可识别的方向盘转向和转动百分比，控制车辆横向动作；将所述纵向行驶控制指令转换为车辆底盘电子踏板可识别的气节门或刹车信息，控制车辆纵向动作。
在另一个实施例中，倒车模块，还用于当倒车且车辆未启动时，启动倒车起步横向控制；计算目标方向盘角度与实际方向盘角度差值的绝对值；根据所述绝对值与目标方向盘角度的比值计算气节门权重系统，所述权重系数用于控制气节门的开度进而控制倒时车车辆速度；当所述车辆速度达到一定值，或方向盘差值小于一定值时，退出倒车起步控制。
在另一个实施例中，所述车辆包括带挂卡车；所述倒车坐标系以所述带挂卡车车头质心为中心，以车头后轮行驶方向为正方向。
自动倒车控制装置还包括：
铰接信息获取模块，用于获取所述带挂卡车的挂车与车头的铰接角度信息。
第一误差计算模块，用于基于所述前轮驱动的倒车动力学模型和所述铰接角度信息，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息。
在另一个实施例中，第一误差计算模块，用于根据所述挂车与车头的铰接角度信息，当前车辆在倒车坐标系下的车头质心的坐标、车头的质心到铰接点处的长度、挂车质心到铰接点处长度，计算得到挂车质心的坐标，以及以挂车质心建立的圆弧的半径；基于所述前轮驱动的倒车动力学模型，在倒车轨迹上选择车头 质心点的第一参考目标点，根据所述车头质心和第一参考点在倒车坐标系下的坐标值，计算车头的横向位置误差和航向角误差；基于所述前轮驱动的倒车动力学模型，在倒车轨迹上选择挂车质心点的第二参考目标点，根据所述挂车质心点和第二参考点在倒车坐标系下的坐标值，计算挂车的横向位置误差和航向角误差；根据所述第二参考点的曲率信息和初始状态计算的半径，计算曲率误差。
横向控制指令获取模块，用于以使所述车头和挂车的横向位置误差、航向角误差、和所述曲率误差为零，所述带挂卡车从初始位置变化到目标位置为目标，计算横向方向盘控制量，得到横向方向盘控制指令。
在另一个实施例中，第一误差计算模块，用于在倒车轨迹上选择车头质心点的第一参考目标点，基于所述前轮驱动的倒车动力学模型，根据所述车头质心和第一参考点在倒车坐标系下的坐标值计算横向位置误差和航向角误差；根据所述挂车与车头铰接角度，当前车辆在倒车坐标系下的车头质心坐标，车头的质心到铰接点处的长度，挂车质心到铰接点处长度参数，计算得到挂车质心的坐标；根据挂车质心坐标在倒车轨迹上选择挂车质心点的第二参考目标点，根据第一参考目标点和第二参考目标点的航向角信息计算目标铰接角度信息；根据所述目标铰接角度信息和实际铰接角度信息，计算铰接角误差。
横向控制指令获取模块，用于以所述铰接角误差、车头质心到第一目标位置的横向位置误差和航向角误差为零为目标，计算横向方向盘控制量，得到横向方向盘控制指令。
关于自动倒车控制装置的具体限定可以参见上文中对于自动倒车控制方法的限定，在此不再赘述。上述自动倒车控制装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于车辆中的处理器中，也可以以软件形式存储于车辆中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，提供了一种车辆，其内部结构图可以如图11所示。该车辆包括通过系统总线连接的车辆控制器、激光雷达、摄像头、雷达感应器和存储器。其中，该车辆控制器用于提供计算和控制能力。该车辆的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统和计算机程序。该 内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该车辆的通信接口用于与外部的终端进行有线或无线方式的通信，无线方式可通过WIFI、运营商网络、NFC(近场通信)或其他技术实现。该计算机程序被处理器执行时以实现一种自动倒车控制方法。
本领域技术人员可以理解，图11中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的车辆的限定，具体的车辆可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一个实施例中，提供了一种车辆，包括车辆控制器，以及与所述车辆控制器连接的激光雷达、摄像头、雷达感应器和存储器，存储器中存储有计算机程序，该车辆控制器执行计算机程序时实现上述各实施例方法的步骤。
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现上述各实施例方法的步骤。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和易失性存储器中的至少一种。非易失性存储器可包括只读存储器(Read-Only Memory，ROM)、磁带、软盘、闪存或光存储器等。易失性存储器可包括随机存取存储器(Random Access Memory，RAM)或外部高速缓冲存储器。作为说明而非局限，RAM可以是多种形式，比如静态随机存取存储器(Static Random Access Memory，SRAM)或动态随机存取存储器(Dynamic Random Access Memory，DRAM)等。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。
Claims (13)
- 一种自动倒车控制方法，所述方法包括：获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息；其中，以车辆质心位置为中心点，以倒车的后轮速度方向为正方向建立倒车坐标系；根据所述倒车目标轨迹信息实时计算倒车目标轨迹范围内轨迹点的曲率，根据所述倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率，得到所述倒车坐标系下的目标行驶轨迹点；根据所述倒车坐标系下的所述目标行驶轨迹点，计算倒车时车辆与目标行驶轨迹点的误差信息；根据所述误差信息进行倒车控制。
- 根据权利要求1所述的方法，其特征在于，所述获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息，包括：获取地图信息和车辆位置信息；根据地图信息获取倒车位的位置信息，根据所述倒车位的位置信息，生成倒车位的目标点位置信息；根据所述车辆位置信息和所述倒车位目标点位置信息，拟合出倒车坐标下系下的倒车目标轨迹信息。
- 根据权利要求1所述的方法，其特征在于，根据所述倒车目标轨迹信息实时计算倒车目标轨迹范围内轨迹点的曲率，根据所述倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率，得到所述倒车坐标系下的目标行驶轨迹点根据所述倒车目标轨迹信息，判断车身质心位置距离倒车轨迹终点是否大于预设距离；若是，则遍历车辆位置到预设距离长度范围内的轨迹点的曲率数据，得到倒车目标轨迹范围内轨迹点的曲率；获取倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率的绝对差值；选择绝对差值最大的轨迹数据点，得到所述倒车坐标系下的目标行驶轨迹点。
- 根据权利要求1所述的方法，其特征在于，根据所述倒车坐标系下的所述目标行驶轨迹点，计算倒车时车辆与目标行驶轨迹点的误差信息，包括：基于所述倒车坐标系和倒车时前轮转向驱动的车辆模型，建立前轮驱动的倒车动力学模型；根据所述前轮驱动的倒车动力学模型，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息；计算倒车时车辆与目标行驶轨迹点的纵向位置误差和速度误差。
- 根据权利要求4所述的方法，其特征在于，所述根据所述误差信息进行倒车控制，包括：根据所述横向位置误差信息和航向角误差信息，计算横向方向盘控制量，得到横向方向盘控制指令；根据倒车时车辆与所述目标行驶轨迹点的纵向位置误差、速度误差以及加速度数据，计算控制车辆倒车的纵向行驶控制指令；根据所述横向方向盘控制指令和所述纵向行驶控制指令进行倒车控制；当车辆实际位置与目标位置的距离在误差范围内，且速度为0时，完成倒车。
- 根据权利要求5所述的方法，其特征在于，根据所述横向方向盘控制指令和所述纵向行驶控制指令进行倒车控制，包括：将所述横向方向盘控制指令转换为车辆底盘可识别的方向盘转向和转动百分比，控制车辆横向动作；将所述纵向行驶控制指令转换为车辆底盘电子踏板可识别的气节门或刹车信息，控制车辆纵向动作。
- 根据权利要求6所述的方法，其特征在于，将所述纵向行驶控制指令转换为车辆底盘电子踏板可识别的气节门或刹车信息，控制车辆纵向动作之前，包括：当倒车且车辆未启动时，启动倒车起步横向控制；计算目标方向盘角度与实际方向盘角度差值的绝对值；根据所述绝对值与目标方向盘角度的比值计算气节门权重系统，所述权重 系数用于控制气节门的开度进而控制倒时车车辆速度；当所述车辆速度达到一定值，或方向盘差值小于一定值时，退出倒车起步控制。
- 根据权利要求5所述的方法，其特征在于，所述车辆包括带挂卡车；所述倒车坐标系以所述带挂卡车车头质心为中心，以车头后轮行驶方向为正方向；所述方法还包括：获取所述带挂卡车的挂车与车头的铰接角度信息；根据所述前轮驱动的倒车动力学模型，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息，包括：基于所述前轮驱动的倒车动力学模型和所述铰接角度信息，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息。
- 根据权利要求8所述的方法，其特征在于，基于所述前轮驱动的倒车动力学模型和所述铰接角度信息，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息，包括：根据所述挂车与车头的铰接角度信息，当前车辆在倒车坐标系下的车头质心的坐标、车头的质心到铰接点处的长度、挂车质心到铰接点处长度，计算得到挂车质心的坐标，以及以挂车质心建立的圆弧的半径；基于所述前轮驱动的倒车动力学模型，在倒车轨迹上选择车头质心点的第一参考目标点，根据所述车头质心和第一参考点在倒车坐标系下的坐标值，计算车头的横向位置误差和航向角误差；基于所述前轮驱动的倒车动力学模型，在倒车轨迹上选择挂车质心点的第二参考目标点，根据所述挂车质心点和第二参考点在倒车坐标系下的坐标值，计算挂车的横向位置误差和航向角误差；根据所述第二参考点的曲率信息和初始状态计算的半径，计算曲率误差；根据所述横向位置误差信息和航向角误差信息，计算横向方向盘控制量，得到横向方向盘控制指令，包括：以使所述车头和挂车的横向位置误差、航向角误差、和所述曲率误差为零，所述带挂卡车从初始位置变化到目标位置为目标，计算横向方向盘控制量，得到 横向方向盘控制指令。
- 根据权利要求8所述的方法，其特征在于，基于所述前轮驱动的倒车动力学模型和所述铰接角度信息，计算倒车时车辆与目标行驶轨迹点的横向位置误差信息和航向角误差信息，包括：在倒车轨迹上选择车头质心点的第一参考目标点，基于所述前轮驱动的倒车动力学模型，根据所述车头质心和第一参考点在倒车坐标系下的坐标值计算横向位置误差和航向角误差；根据所述挂车与车头铰接角度，当前车辆在倒车坐标系下的车头质心坐标，车头的质心到铰接点处的长度，挂车质心到铰接点处长度参数，计算得到挂车质心的坐标；根据挂车质心坐标在倒车轨迹上选择挂车质心点的第二参考目标点，根据第一参考目标点和第二参考目标点的航向角信息计算目标铰接角度信息；根据所述目标铰接角度信息和实际铰接角度信息，计算铰接角误差；根据所述横向位置误差信息和航向角误差信息，计算横向方向盘控制量，得到横向方向盘控制指令，包括：以所述铰接角误差、车头质心到第一目标位置的横向位置误差和航向角误差为零为目标，计算横向方向盘控制量，得到横向方向盘控制指令。
- 一种自动倒车控制装置，其特征在于，所述装置包括：目标轨迹获取模块，用于获取根据车辆位置和倒车位位置生成的车辆在倒车坐标系下的倒车目标轨迹信息；其中，以车辆质心位置为中心点，以倒车的后轮速度方向为正方向建立倒车坐标系；目标行驶轨迹点确定模块，用于根据所述倒车目标轨迹信息实时计算倒车目标轨迹范围内轨迹点的曲率，根据所述倒车目标轨迹范围内轨迹点的曲率与车辆实际曲率，得到所述倒车坐标系下的目标行驶轨迹点；误差计算模块，用于根据所述倒车坐标系下的所述目标行驶轨迹点，计算倒车时车辆与目标行驶轨迹点的误差信息；倒车控制模块，用于根据所述误差信息进行倒车控制。
- 一种车辆，包括车辆控制器，以及与所述车辆控制器连接的激光雷达、摄像头、雷达感应器和存储器，所述存储器存储有计算机程序，其特征在于，所述车辆控制器执行所述计算机程序时实现权利要求1至10中任一项所述方法的步骤。
- 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，所述计算机程序被处理器执行时实现权利要求1至10中任一项所述方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011223872.6 | 2020-11-05 | ||
| CN202011223872.6A CN114435470B (zh) | 2020-11-05 | 2020-11-05 | 自动倒车控制方法、装置、车辆和存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022095814A1 true WO2022095814A1 (zh) | 2022-05-12 |
Family
ID=81362131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/127853 WO2022095814A1 (zh) | 2020-11-05 | 2021-11-01 | 自动倒车控制方法、装置、车辆和存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114435470B (zh) |
| WO (1) | WO2022095814A1 (zh) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115320709A (zh) * | 2022-08-29 | 2022-11-11 | 东风悦享科技有限公司 | 一种基于四轮转向的自动驾驶混合控制方法 |
| CN116466382A (zh) * | 2023-04-24 | 2023-07-21 | 贵州一招信息技术有限公司 | 一种基于gps的高精度实时定位系统 |
| CN116968743A (zh) * | 2023-08-30 | 2023-10-31 | 梁山华鲁专用汽车制造有限公司 | 自卸车及倒车辅助装置 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116443013B (zh) * | 2023-06-16 | 2023-08-15 | 北京易控智驾科技有限公司 | 无人驾驶车辆的倒车控制系统、方法、设备及介质 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103183028A (zh) * | 2012-01-02 | 2013-07-03 | 福特全球技术公司 | 用于机动车辆的车道保持方法 |
| WO2016113504A1 (fr) * | 2015-01-16 | 2016-07-21 | Renault S.A.S. | Procede et dispositif d'aide a la manoeuvre en marche arriere d'un vehicule automobile |
| CN109823348A (zh) * | 2019-02-19 | 2019-05-31 | 百度在线网络技术（北京）有限公司 | 无人车倒车模型控制方法、装置、设备及计算机可读介质 |
| CN110825095A (zh) * | 2019-12-06 | 2020-02-21 | 苏州智加科技有限公司 | 一种自动驾驶车辆横向控制方法 |
| CN111767507A (zh) * | 2020-06-30 | 2020-10-13 | 北京百度网讯科技有限公司 | 一种倒车轨迹追踪方法、装置、电子设备及存储介质 |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3707379B2 (ja) * | 2000-03-23 | 2005-10-19 | 日産自動車株式会社 | 車両の前後輪舵角制御装置 |
| JP3818653B2 (ja) * | 2003-06-26 | 2006-09-06 | トヨタ自動車株式会社 | 車両用走行支援装置 |
| CN1987357B (zh) * | 2006-12-26 | 2010-05-19 | 浙江工业大学 | 基于全方位计算机视觉的智能停车辅助装置 |
| WO2017130397A1 (ja) * | 2016-01-29 | 2017-08-03 | 富士通株式会社 | 位置推定装置、位置推定方法および位置推定プログラム |
| JP6859239B2 (ja) * | 2017-09-19 | 2021-04-14 | 本田技研工業株式会社 | 車両制御装置、車両制御方法、およびプログラム |
| CN108437981B (zh) * | 2018-03-01 | 2020-02-21 | 东软集团股份有限公司 | 一种自动倒车方法及装置 |
| JP2019156217A (ja) * | 2018-03-14 | 2019-09-19 | 本田技研工業株式会社 | 車両制御装置、車両制御方法、及びプログラム |
| CN109375632B (zh) * | 2018-12-17 | 2020-03-20 | 清华大学 | 自动驾驶车辆实时轨迹规划方法 |
| CN111338342B (zh) * | 2020-02-28 | 2022-11-25 | 江苏徐工工程机械研究院有限公司 | 一种轮式工程机械自动循迹行驶控制系统及方法 |
-
2020
- 2020-11-05 CN CN202011223872.6A patent/CN114435470B/zh active Active
-
2021
- 2021-11-01 WO PCT/CN2021/127853 patent/WO2022095814A1/zh active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103183028A (zh) * | 2012-01-02 | 2013-07-03 | 福特全球技术公司 | 用于机动车辆的车道保持方法 |
| WO2016113504A1 (fr) * | 2015-01-16 | 2016-07-21 | Renault S.A.S. | Procede et dispositif d'aide a la manoeuvre en marche arriere d'un vehicule automobile |
| CN109823348A (zh) * | 2019-02-19 | 2019-05-31 | 百度在线网络技术（北京）有限公司 | 无人车倒车模型控制方法、装置、设备及计算机可读介质 |
| CN110825095A (zh) * | 2019-12-06 | 2020-02-21 | 苏州智加科技有限公司 | 一种自动驾驶车辆横向控制方法 |
| CN111767507A (zh) * | 2020-06-30 | 2020-10-13 | 北京百度网讯科技有限公司 | 一种倒车轨迹追踪方法、装置、电子设备及存储介质 |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115320709A (zh) * | 2022-08-29 | 2022-11-11 | 东风悦享科技有限公司 | 一种基于四轮转向的自动驾驶混合控制方法 |
| CN115320709B (zh) * | 2022-08-29 | 2023-04-18 | 东风悦享科技有限公司 | 一种基于四轮转向的自动驾驶混合控制方法 |
| CN116466382A (zh) * | 2023-04-24 | 2023-07-21 | 贵州一招信息技术有限公司 | 一种基于gps的高精度实时定位系统 |
| CN116968743A (zh) * | 2023-08-30 | 2023-10-31 | 梁山华鲁专用汽车制造有限公司 | 自卸车及倒车辅助装置 |
| CN116968743B (zh) * | 2023-08-30 | 2024-03-19 | 梁山华鲁专用汽车制造有限公司 | 自卸车及倒车辅助装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114435470A (zh) | 2022-05-06 |
| CN114435470B (zh) | 2022-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022095814A1 (zh) | 自动倒车控制方法、装置、车辆和存储介质 | |
| CN112477849B (zh) | 自动驾驶卡车的泊车控制方法、装置及自动驾驶卡车 | |
| CN112896147B (zh) | 用于矿用车辆的双向定位泊车控制方法及装置 | |
| CN111696339A (zh) | 一种自动驾驶车队的跟车控制方法、系统及车辆 | |
| CN113721606A (zh) | 引导式自动驾驶物流车辆控制系统及方法 | |
| US20230131835A1 (en) | Apparatus for controlling autonomous driving of independent driving electric vehicle and method thereof | |
| CN116080754B (zh) | 一种车辆自主驾驶横向控制方法 | |
| CN111959506A (zh) | 车辆及车辆编队行驶的控制方法、装置 | |
| KR20220070467A (ko) | 자동차의 폭방향 및 길이방향 안내 동안 데드타임 보상 기술 | |
| JP2019105568A (ja) | 物体認識装置、物体認識方法及び車両 | |
| CN110077462B (zh) | 一种无人车行驶过程中的转向保护方法及终端 | |
| US11529948B2 (en) | Architecture and methodology of limit handling intended driver command interpreter to achieve maximum lateral grip | |
| CN113928308B (zh) | 半挂卡车的倒车控制方法、装置及半挂卡车 | |
| CN114291071B (zh) | 一种车辆稳定性控制主动介入时机的判定方法、系统、可读存储介质及车辆 | |
| CN115525054A (zh) | 大型工业园区无人清扫车沿边路径跟踪控制方法及系统 | |
| CN111857112B (zh) | 一种汽车局部路径规划方法及电子设备 | |
| CN114620033A (zh) | 一种基于前轮反馈控制的泊车入库控制方法 | |
| CN112477861B (zh) | 自动驾驶卡车的行驶控制方法、装置及自动驾驶卡车 | |
| CN115243951A (zh) | 用于控制车辆的方法 | |
| CN113276834B (zh) | 使用感知横摆中心进行车辆综合稳定性控制的系统和方法 | |
| US11932308B1 (en) | Four wheel steering angle constraints | |
| CN113311834B (zh) | 自动驾驶轨迹追踪方法、系统及存储介质 | |
| CN114326728B (zh) | 高安全裕度的单agv智能车库路径跟踪控制系统及方法 | |
| US20240182019A1 (en) | Vehicle control based on dynamically configured longitudinal wheel slip limits | |
| CN112428981B (zh) | 一种自动驾驶卡车的控制方法、装置及自动驾驶卡车 |
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: 21888511 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: 21888511 Country of ref document: EP Kind code of ref document: A1 |