CN114834441B - Trajectory tracking control method, device and system for automatic parking and storage medium - Google Patents
Trajectory tracking control method, device and system for automatic parking and storage medium Download PDFInfo
- Publication number
- CN114834441B CN114834441B CN202210546846.XA CN202210546846A CN114834441B CN 114834441 B CN114834441 B CN 114834441B CN 202210546846 A CN202210546846 A CN 202210546846A CN 114834441 B CN114834441 B CN 114834441B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- steering wheel
- track
- wheel angle
- predicted
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/06—Automatic manoeuvring for parking
Abstract
The invention provides a track tracking control method, a device, a system and a storage medium for automatic parking, wherein a prediction model can predict a future advancing track according to the pose of a vehicle at the current moment, a steering wheel angle and the increment of the steering wheel angle, a loss function is designed according to the error of the corresponding segment of the future advancing track and a planning reference track, the increment value of the steering wheel angle when the error of the corresponding segment of the future advancing track and the planning reference track is minimum is solved through the loss function, the steering wheel angle is corrected according to the increment value of the steering wheel angle, and the vehicle is controlled to walk according to the corrected steering wheel angle.
Description
Technical Field
The invention relates to the field of path planning, in particular to a trajectory tracking control method, a trajectory tracking control device, a trajectory tracking control system and a storage medium for automatic parking.
Background
At present, in the technical field of automatic parking, a control module of a vehicle often controls the vehicle to run according to a specified track according to an expected path given by planning, and due to the particularity of a low-speed parking scene, requirements on precision and comfort are often put forward for the control of low-speed parking. The control precision ensures that the vehicle can be accurately stopped at a planned parking space, and the control precision within 10cm can meet the actual requirement; in addition to control accuracy, comfort during control is also important, and if the steering wheel swings back and forth at high frequency during control, discomfort is easily caused to the driver and passengers.
In order to improve the control accuracy and comfort during automatic parking, the vehicle needs to be controlled to track a planned path. At present, the method for tracking the planned path by the vehicle mainly comprises the following steps:
1. pure path tracking: the method is generally based on a constant speed working condition, but the pre-aiming distances under different working conditions need to be calibrated, curvatures of different paths can generate great influence on the pre-aiming distances, if the pre-aiming distances are too small, the paths are easy to vibrate during path tracking, and if the pre-aiming distances are too large, the tracked paths are not accurate enough. Therefore, the pure path tracking method is suitable for being used under the condition of low requirement on path tracking precision.
2. PID control tracking: the PID control algorithm is one of the commonly used control algorithms in low-speed parking, and the control is mainly realized according to the error between the current vehicle position and the planned track point. However, the PID control algorithm must perform a control function only when an error occurs, that is, when the vehicle tracks a path through the PID control algorithm, the vehicle already has a certain position deviation from a planned trajectory, and during low-speed parking, if the vehicle trajectory has a curvature change, the vehicle is easily controlled to oscillate or be controlled in a non-timely manner. In addition, under the low-speed parking scene, a high requirement is provided for the quick response of vehicle control, and if the advanced control cannot be realized, the path tracking effect is poor.
Disclosure of Invention
The present invention is directed to provide a method, an apparatus, a system and a storage medium for trajectory tracking control of automatic parking, which can improve the control accuracy and comfort during automatic parking of a vehicle.
In order to achieve the above object, the present invention provides a trajectory tracking control method for automatic parking, including:
collecting the pose and the steering wheel angle of the vehicle at the current moment;
predicting a future travel track of the vehicle by using a prediction model of the vehicle based on the pose of the vehicle at the current moment, the steering wheel angle and the increment of the steering wheel angle;
designing a loss function according to the future advancing track and the error of a segment of a planned reference track corresponding to the future advancing track, wherein the planned reference track is a driving track to a target parking space generated in advance when a vehicle parks;
solving an increment value of the steering wheel angle when the error of the corresponding segments of the future travel track and the planning reference track is minimum according to the loss function;
correcting the steering wheel angle according to the solved incremental value of the steering wheel angle;
and controlling the vehicle to walk at the corrected steering wheel angle.
Optionally, the obtaining manner of the prediction model includes:
obtaining a vehicle kinematic model;
and discretizing the difference of the vehicle kinematic model to obtain the prediction model.
Optionally, the prediction model is:
X(k+n)=A*X(k+n-1)
wherein the content of the first and second substances,
the collected pose of the vehicle at the current moment is X (k + n) is the predicted value of the abscissa of the nth predicted track point, y (k + n) is the predicted value of the ordinate of the nth predicted track point,predicted value of vehicle heading angle v for nth predicted track point r The central speed of a rear axle of the vehicle, the wheel base of the vehicle, the wheel rotation angle of the vehicle, delta (k) and T are respectively acquired according to the steering wheel angle and the increment of the steering wheel angle, and the T is sampling time.
Optionally, the error of the segment corresponding to the future travel trajectory and the planned reference trajectory is: the difference value of the pose of each predicted track point and the pose of the corresponding planning reference track point is obtained;
the loss function is:
wherein the content of the first and second substances,
and Q is the weight coefficient of the position of the vehicle and the heading angle of the vehicle.
Optionally, the loss function is used for solving the minimum value by a gradient descent method or a newton iteration method.
In order to achieve the above object, the present invention also provides a trajectory tracking control device for automatic parking, including:
the acquisition module is used for acquiring the pose and the steering wheel angle of the vehicle at the current moment;
the prediction module is used for predicting the future travel track of the vehicle by utilizing a prediction model of the vehicle based on the pose of the vehicle at the current moment, the steering wheel angle and the increment of the steering wheel angle;
the design module is used for designing a loss function according to the future advancing track and the error of a segment of a planned reference track corresponding to the future advancing track, wherein the planned reference track is a driving track to a target parking space generated in advance when a vehicle parks;
a solving module, configured to solve, according to the loss function, an incremental value of the steering wheel angle when an error of a corresponding segment of the future travel trajectory and the planned reference trajectory is minimum;
the correction module is used for controlling a steering wheel of a vehicle according to the solved increment value of the steering wheel angle so as to correct the steering wheel angle according to the increment value of the steering wheel angle;
and the control module is used for controlling the vehicle to walk at the corrected steering wheel angle.
In order to achieve the above object, the present invention also provides a trajectory tracking control system for automatic parking, including:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to execute the trajectory tracking control method of automatic parking as described above via execution of the executable instructions.
In order to achieve the above object, the present invention further provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the trajectory tracking control method for automatic parking as described above.
The invention also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the trajectory tracking control method for automatic parking as described above.
According to the track tracking control method for automatic parking, the future advancing track of the vehicle is predicted by using a prediction model based on the pose of the vehicle at the current moment, the steering wheel angle and the increment of the steering wheel angle, a loss function is designed according to the error of the corresponding segment of the future advancing track and the planning reference track, the increment value of the steering wheel angle when the error of the corresponding segment of the future advancing track and the planning reference track is minimum is solved through the loss function, the steering wheel angle is corrected according to the solved increment value of the steering wheel angle, and therefore the vehicle is controlled to walk at the corrected steering wheel angle. Because the solved incremental value of the steering wheel angle is the incremental value of the steering wheel angle when the error between the future advancing track and the planned reference track is minimum, the vehicle can be controlled in advance according to the solved incremental value of the steering wheel angle, so that the future advancing path of the vehicle is closer to the pre-planned driving track, the vehicle does not need to be controlled when the actual advancing track of the vehicle deviates from the planned reference track, the vehicle smoothly and stably parks along the pre-planned driving track, the good track tracking effect can be achieved, the vehicle control precision is improved, the stability of the steering wheel control is improved, and the comfort of the vehicle in the parking process is improved.
Drawings
Fig. 1 is a flowchart of a trajectory tracking control method for automatic parking according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of a future predicted trajectory and a segment of a planned reference trajectory corresponding to the future predicted trajectory in accordance with an embodiment of the present invention.
Fig. 3 is a block diagram of an automatic parking path planning apparatus according to an embodiment of the present invention.
Fig. 4 is a block diagram of an automatic parking path planning system according to an embodiment of the present invention.
Detailed Description
In order to explain technical contents, structural features, and effects of the present invention in detail, the following detailed description is given with reference to the embodiments and the accompanying drawings.
Referring to fig. 1, an embodiment of the present invention discloses a trajectory tracking control method for automatic parking, including:
100. and acquiring the pose and the steering wheel angle of the vehicle at the current moment.
The pose of the vehicle at the current moment can be collected through a positioning module of the vehicle, and the angle of the steering wheel can be collected through a control module of the vehicle or a steering wheel corner sensor and the like.
200. And predicting the future travel track of the vehicle by using the prediction model of the vehicle based on the pose of the vehicle at the current moment, the steering wheel angle and the increment of the steering wheel angle.
Since the vehicle is in low-speed operation during automatic parking, the speed of the wheels and the direction of the wheels are basically kept unchanged, so that the travel track of the vehicle in the future period can be predicted according to the current position of the vehicle, the steering wheel angle and the increment of the steering wheel angle.
In a specific example, the obtaining manner of the prediction model may include:
obtaining a vehicle kinematics model;
and carrying out differential discretization on the vehicle kinematic model to obtain a prediction model.
Specifically, the vehicle kinematic model is:
wherein x is a transverse coordinate value of the vehicle, y is a longitudinal left value of the vehicle,is the vehicle heading angle, v r Is the vehicle rear axle center speed, δ is the vehicle wheel steering angle, l is the vehicle wheelbase, δ is obtained from the steering wheel angle. And discretizing the difference of the vehicle kinematic model according to the forward difference to obtain a prediction model:
wherein, the first and the second end of the pipe are connected with each other,
the prediction model can be simplified as:
X(k+n)=A*X(k+n-1)
the collected pose of the vehicle at the current moment isX (k + n) represents the pose matrix of the nth predicted trajectory point, and/or>For the pose of the nth predicted track point, x (k + n) represents the predicted value of the abscissa of the nth predicted track point, y (k + n) is the predicted value of the ordinate of the nth predicted track point, and the position of the nth predicted track point is based on the coordinate of the nth predicted track point>And d, obtaining a predicted value of the vehicle heading angle of the nth predicted track point, wherein delta (k) is a wheel rotation angle of the vehicle, delta (k) is obtained according to the collected steering wheel angle and the increment of the steering wheel angle, and T is sampling time. It can be understood that X (k + n-1) is the pose matrix of the nth-1 predicted locus point, and is used for judging whether the pose matrix is located on the receiver or not>Predicting the pose of the track point for the (n-1) th track point; further, since the wheel rotation angle of the vehicle is obtained from the steering wheel angle, the wheel rotation angle of the vehicle does not change even when the steering wheel angle and the increment of the steering wheel angle are not changed during the prediction, and therefore the wheel rotation angle in the one-time prediction process is always δ (k).
It should be noted that the prediction model predicts the future travel track according to the time node, for example, the prediction model predicts the vehicle pose as the first predicted track point of the vehicle according to the first preset time duration at the current time, the prediction model predicts the vehicle pose as the second predicted track point of the vehicle according to the first preset time duration at the time when the first predicted track point is located, and by analogy, n predicted track points of the vehicle in a future period of time can be predicted. The first preset time period may be set according to an actual requirement, such as 2ms, 4ms, and the like.
It can be understood that the pose matrix is set for convenience of operation, and the pose of each predicted track point can be directly calculated one by one to obtain the pose of the next predicted track point corresponding to the pose matrix, so that the future travel track can be predicted.
The prediction model is obtained by carrying out differential discretization on the vehicle kinematic model, the prediction model can be simplified and the amount of calculation of the future travel locus prediction by the vehicle can be reduced.
It should be noted that the process of performing differential discretization on the vehicle kinematic model can be processed in various differential discretization manners known to those skilled in the art, and therefore, detailed descriptions of the process in the embodiments of the present invention are omitted.
300. And designing a loss function according to the future advancing track and the error of the segment of the planned reference track corresponding to the future advancing track, wherein the planned reference track is a driving track to a target parking space generated in advance when the vehicle parks.
The driving trajectory to the target parking space generated in advance when the vehicle parks can be obtained through a path planning function known by a person skilled in the art, and the vehicle needs to complete parking along the driving trajectory.
It can be understood that the segment of the planned reference trajectory corresponding to the future travel trajectory refers to a segment of the planned reference trajectory corresponding to the future travel trajectory on the time node, for example, the future travel trajectory refers to a travel trajectory generated by the prediction model predicting that the vehicle travels for a second preset time period from the current time, and then the planned reference trajectory corresponding to the segment of the planned reference trajectory starts from the reference point at the current time, and the second predicted time period may be set according to actual requirements, for example, 20ms, 40ms, 60ms, and the like, which is not limited in this embodiment of the present invention.
Specifically, as shown in fig. 2, a reference point X (k) matching the pose of the vehicle at the current time is provided on the planned reference track of the vehicle (which indicates the position of the vehicle at this time to which the vehicle has traveled), the predicted track point on the future travel track predicted by the vehicle and the planned reference track point on the planned reference track after the reference point are in one-to-one correspondence according to the time nodes, for example, the predicted track point at the next time when the vehicle predicts the current time is the first predicted track point X (k + 1), and the planned reference track point at the next time when the reference point on the planned reference track is the first planned reference track point X (k + 1) ref (k + 1), a first predicted track point X (k + 1) and a first planning reference track point X ref (k + 1) has a time correspondence, that is, the vehicle has traveled X (k + 1) relative to X (k) for a first preset period of timeThe vehicle is at X ref (k + 1) also traveled for a first preset duration relative to X (k); by analogy, the second predicted track point X (k + 2) and the second planning reference track point X ref (k + 2), a third predicted track point X (k + 3) and a third planning reference track point X ref (k + 3) has a corresponding relation on the time node, the nth predicted track point and the nth planning reference track point have a corresponding relation on the time node, wherein the time length from the current moment to the next moment is the same as the first preset time length, and the time interval between each predicted track point and the predicted track point at the next moment corresponding to the predicted track point is the same.
It can be understood that, in order to better understand the relationship between the predicted track point and the planned reference track point, the error between the corresponding segments of the future travel trajectory and the planned reference trajectory in fig. 2 is obvious, and in practice, the corresponding segments of the future travel trajectory and the planned reference trajectory may coincide or have a smaller error.
It should be noted that the error of the future travel track and the segment of the planned reference track corresponding to the future travel track refers to the difference between each predicted track point and the corresponding planned reference track point.
400. And solving the increment of the steering wheel angle when the error of the corresponding segments of the future travel track and the planning reference track is minimum according to the loss function.
Because the prediction model can predict the future travel track of the vehicle according to the pose, the steering wheel angle and the increment of the steering wheel at the current moment of the vehicle, a loss function is designed according to the error of the future travel track predicted by the prediction model and the planning reference track by taking the increment of the steering wheel angle as an unknown quantity, so that the increment of the steering wheel angle when the error of the future travel track and the planning reference track is minimum can be solved.
500. And correcting the steering wheel angle according to the solved incremental value of the steering wheel angle.
600. And controlling the vehicle to walk at the corrected steering wheel angle.
It will be appreciated that in some specific examples, the incremental value of the solved steering wheel angle may be 0, and when the incremental value of the steering wheel angle is 0, the corrected steering wheel angle is the same as the steering wheel angle at the current time.
In the track tracking control method for automatic parking provided by the embodiment of the invention, a future advancing track of a vehicle is predicted by using a prediction model based on the pose of the vehicle at the current moment, the steering wheel angle and the increment of the steering wheel angle, a loss function is designed according to the error of the corresponding segment of the future advancing track and the planning reference track, the increment value of the steering wheel angle when the error of the corresponding segment of the future advancing track and the planning reference track is minimum is solved through the loss function, and the steering wheel is controlled according to the solved increment value of the steering wheel angle to correct the steering wheel angle, so that the vehicle is controlled to walk at the corrected steering wheel angle. The incremental value of the steering wheel angle is the incremental value of the steering wheel angle when the error between the future advancing track and the planned reference track is the minimum, so that the vehicle can be controlled in advance according to the incremental value of the steering wheel angle, the future advancing path of the vehicle is closer to the pre-planned driving track, the vehicle does not need to be controlled when the actual advancing track of the vehicle deviates from the planned reference track, the vehicle smoothly and stably parks along the pre-planned driving track, the good track tracking effect can be achieved, the vehicle control precision is improved, the steering wheel control stability is improved, and the vehicle comfort in the parking process is improved.
It can be understood that, when predicting the future travel track of the vehicle, the vehicle may be traveling at the same time, and from the current time, the increment of the steering wheel angle when the error between the future travel track within a preset period of time (a second preset duration) and the planning reference track is minimum is solved according to the vehicle loss function, the pose and the steering wheel angle at the current time, and the steering wheel angle is corrected according to the solved increment of the steering wheel angle.
In some embodiments, the error of the future travel trajectory and the planned reference trajectory of the vehicle is: and the difference value of the pose of each predicted track point and the pose of the corresponding planning reference track point is as follows:
wherein the content of the first and second substances,
X ref (k + n) is the pose matrix of the nth planning reference trajectory point, and Q is the weight coefficient of the position of the vehicle and the heading angle of the vehicle.
The loss function is the sum of squares of difference values between the poses of the n predicted track points and the poses of the corresponding planning reference track points, and the poses of the vehicles comprise the positions of the vehicles and the heading angles of the vehicles, so the positions of the vehicles and the weights of the heading angles of the vehicles in the loss function can be set according to requirements ref And (k + n) setting a coefficient matrix, wherein each coefficient in the coefficient matrix corresponds to the weight of the position of the vehicle and the heading angle of the vehicle respectively.
Because the loss function is the sum of squares of the difference values of the poses of the n predicted track points and the corresponding planning reference track points, and when the loss function is minimum, the error between the future advancing track and the planning reference track is minimum, the increment of the steering wheel angle when the error between the future advancing track and the planning reference track is minimum can be solved by solving the minimum value of the loss function. The loss function is a quadratic convex function, the unknown quantity of the quadratic convex function is the increment of the steering wheel angle, a minimum value solution is certain to exist in a certain increment range of the steering wheel angle, and specifically, the minimum value of the loss function can be solved through a gradient descent method or a Newton iteration method, so that the increment of the steering wheel angle when the error between the future travel track and the planning reference track is minimum is solved.
Of course, the minimum of the loss function can be solved by any method known to those skilled in the art to solve the minimum of the function, and is not limited to the gradient descent method or the newton iteration method described above.
In a specific example, the collected pose of the vehicle at the current moment isThe steering wheel angle of the vehicle is u (k), the increment of the steering wheel angle is delta u (k), and the vehicle wheel turning angle is:
δ(k)=f(u(k),Δu(k))
where f (u (k), Δ u (k)) may be set according to the correspondence between the wheel turning angles and the steering wheel angles of different vehicles. For example, the wheel steering angle may be:
δ(k)=f(u(k),Δu(k))=steer_ratio*(u(k)+Δu(k))
that is, the wheel rotation angle of the vehicle has a certain linear proportionality with u (k) + Δ u (k), and the specific proportionality coefficient is set according to the structural parameters of the vehicle, which is not limited by the invention.
The prediction of the future travel track of the vehicle by using the prediction model based on the current pose of the vehicle, the steering wheel angle and the increment of the steering wheel angle can be explained by the prediction process of a first predicted track point, wherein the pose matrix of the first predicted track point is
Obtaining the pose of the first predicted track pointAccording to the prediction model X (k + n) = A X (k + n-1), a plurality of predicted track points X (k + 1), X (k + 2), X (k + 3), … and X (k + n) on the future travel track of the vehicle can be obtained through successive recursion, because the first predicted track point is obtained according to the increment of the vehicle pose, the steering wheel angle and the steering wheel angle at the current moment, and each predicted track point is obtained according to the recursion of the previous predicted track point, the pose of each predicted track point is related to the increment of the vehicle pose, the steering wheel angle and the steering wheel angle at the current moment, and therefore, a loss function designed according to the error of the future travel track and the planning reference track of the vehicle comprises the increment of the vehicle pose, the steering wheel angle and the steering wheel angle at the current moment.
As shown in fig. 3, an embodiment of the present invention further provides a trajectory tracking control device for automatic parking, including:
and the acquisition module 10 is used for acquiring the pose and the steering wheel angle of the vehicle at the current moment.
And the prediction module 11 is used for predicting the future travel track of the vehicle by using the prediction model of the vehicle based on the pose, the steering wheel angle and the increment of the steering wheel angle of the current time of the vehicle.
The design module 12 is configured to design a loss function according to the future travel track and an error of a segment of the planned reference track corresponding to the future travel track, where the planned reference track is a driving track to a target parking space generated in advance when the vehicle parks.
And the solving module 13 is configured to solve, according to the loss function, an incremental value of the steering wheel angle when the error of the corresponding segment of the future travel trajectory and the planned reference trajectory is minimum.
And the correction module 14 is used for controlling the steering wheel of the vehicle according to the solved increment value of the steering wheel angle so as to correct the steering wheel angle according to the increment of the steering wheel angle.
And a control module 15 for controlling the vehicle to walk at the corrected steering wheel angle.
It should be noted that all or part of the modules in the trajectory tracking control device for automatic parking may be implemented by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
As shown in fig. 4, an embodiment of the present invention further discloses a trajectory tracking control system for automatic parking, including:
a processor 20; and
a memory 30 for storing executable instructions for the processor 20;
wherein the processor 20 is configured to execute the trajectory tracking control method of automatic parking as before via execution of the executable instructions.
The embodiment of the invention also discloses a computer readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the trajectory tracking control method for automatic parking as described above is implemented.
The embodiment of the application also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the trajectory tracking control method for automatic parking as described above.
It should be understood that in the embodiments of the present invention, the processor may be a Central Processing Unit (CPU), and the processor may also be other general processors, digital signal processors (DP), application specific integrated circuits (AIC), field-Programmable Gate arrays (FPGA) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer program instructions, and that the programs can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above disclosure is only a preferred embodiment of the present invention, which is convenient for those skilled in the art to understand and implement, and certainly not to limit the scope of the present invention, which is not intended to be covered by the present invention.
Claims (6)
1. A trajectory tracking control method for automatic parking is characterized by comprising the following steps:
collecting the pose and the steering wheel angle of the vehicle at the current moment;
predicting a future travel track of the vehicle by using a prediction model of the vehicle based on the pose of the vehicle at the current moment, the steering wheel angle and the increment of the steering wheel angle;
designing a loss function according to the future advancing track and the error of a segment of a planned reference track corresponding to the future advancing track, wherein the planned reference track is a driving track to a target parking space generated in advance when a vehicle parks;
solving an increment value of the steering wheel angle when the error of the corresponding segments of the future travel track and the planning reference track is minimum according to the loss function;
correcting the steering wheel angle according to the solved incremental value of the steering wheel angle;
controlling the vehicle to walk at the corrected steering wheel angle; the obtaining mode of the prediction model comprises the following steps:
obtaining a vehicle kinematic model;
carrying out differential discretization on the vehicle kinematic model to obtain the prediction model;
the prediction model is as follows:
X(k+n)=A*X(k+n-1)
wherein the content of the first and second substances,
the collected pose of the vehicle at the current moment is For the pose of the nth predicted track point, x (k + n) represents the predicted value of the abscissa of the nth predicted track point, y (k + n) is the predicted value of the ordinate of the nth predicted track point, and the position of the nth predicted track point is based on the coordinate of the nth predicted track point>Predicted value of vehicle course angle for nth predicted track point, v r The central speed of a rear axle of the vehicle, the wheel base of the vehicle, the wheel rotation angle of the vehicle, delta (k) and T are respectively acquired according to the steering wheel angle and the increment of the steering wheel angle, and the T is sampling time.
2. The trajectory tracking control method of automatic parking according to claim 1,
the errors of the segments corresponding to the future travel trajectory and the planning reference trajectory are as follows: the difference value of the pose of each predicted track point and the pose of the corresponding planning reference track point is obtained;
the loss function is:
wherein the content of the first and second substances,
3. The trajectory tracking control method for automatic parking according to claim 2,
the loss function is used for solving the minimum value by a gradient descent method or a Newton iteration method.
4. A trajectory tracking control device for automatic parking, characterized by comprising:
the acquisition module is used for acquiring the pose and the steering wheel angle of the vehicle at the current moment;
the prediction module is used for predicting the future travel track of the vehicle by utilizing a prediction model of the vehicle based on the pose of the vehicle at the current moment, the steering wheel angle and the increment of the steering wheel angle;
the design module is used for designing a loss function according to the future advancing track and the error of a segment of a planned reference track corresponding to the future advancing track, wherein the planned reference track is a driving track to a target parking space generated in advance when a vehicle parks;
a solving module, configured to solve, according to the loss function, an incremental value of the steering wheel angle when an error of a corresponding segment of the future travel trajectory and the planned reference trajectory is minimum;
the correction module is used for controlling a steering wheel of a vehicle according to the solved increment value of the steering wheel angle so as to correct the steering wheel angle according to the increment value of the steering wheel angle;
a control module for controlling the vehicle to travel at the corrected steering wheel angle;
the obtaining mode of the prediction model comprises the following steps:
obtaining a vehicle kinematic model;
carrying out differential discretization on the vehicle kinematic model to obtain the prediction model;
the prediction model is as follows:
X(k+n)=A*X(k+n-1)
wherein the content of the first and second substances,
the collected pose of the vehicle at the current moment is Predicting the track for the nthPosition and pose of the locus point, x (k + n) represents the predicted value of the abscissa of the nth predicted locus point, y (k + n) is the predicted value of the ordinate of the nth predicted locus point, and the position and pose of the nth predicted locus point are selected according to the predicted value of the ordinate of the nth predicted locus point>Predicted value of vehicle heading angle v for nth predicted track point r The central speed of a rear axle of the vehicle, the wheel base of the vehicle, the wheel rotation angle of the vehicle, delta (k) and T are respectively acquired according to the steering wheel angle and the increment of the steering wheel angle, and the T is sampling time.
5. A trajectory tracking control system for automatic parking, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to execute the trajectory tracking control method of automatic parking according to any one of claims 1 to 3 via execution of the executable instructions.
6. A computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing the trajectory tracking control method for automatic parking according to any one of claims 1 to 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210546846.XA CN114834441B (en) | 2022-05-19 | 2022-05-19 | Trajectory tracking control method, device and system for automatic parking and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210546846.XA CN114834441B (en) | 2022-05-19 | 2022-05-19 | Trajectory tracking control method, device and system for automatic parking and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114834441A CN114834441A (en) | 2022-08-02 |
CN114834441B true CN114834441B (en) | 2023-03-31 |
Family
ID=82570977
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210546846.XA Active CN114834441B (en) | 2022-05-19 | 2022-05-19 | Trajectory tracking control method, device and system for automatic parking and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114834441B (en) |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
IT201600109633A1 (en) * | 2016-10-31 | 2018-05-01 | Magneti Marelli Spa | Process and adaptive control system in a land vehicle for tracking a route, particularly in an autonomous driving scenario. |
CN111547066B (en) * | 2020-04-27 | 2021-11-30 | 中汽信息科技(天津)有限公司 | Vehicle trajectory tracking method, device, equipment and storage medium |
CN113635891A (en) * | 2021-08-02 | 2021-11-12 | 北京科技大学 | Integrated parallel parking trajectory planning and tracking control method and system |
CN114148320B (en) * | 2021-12-08 | 2023-10-20 | 华人运通(上海)自动驾驶科技有限公司 | Path tracking control method and equipment |
-
2022
- 2022-05-19 CN CN202210546846.XA patent/CN114834441B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN114834441A (en) | 2022-08-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8751089B2 (en) | Trajectory tracking control system and method for mobile unit | |
CN109421709B (en) | Driving support device for vehicle | |
CN110171416B (en) | Vehicle running control method and device, computer readable medium and electronic equipment | |
US11919518B2 (en) | Vehicle lane change control method and device | |
CN109080631A (en) | The system and method for low speed crosswise joint for vehicle | |
US9499197B2 (en) | System and method for vehicle steering control | |
US10077072B2 (en) | Vehicle steering device and vehicle steering control method with reduced lateral speed | |
US8140210B2 (en) | Method and device for object tracking in a driver assistance system of a motor vehicle | |
CN107618503A (en) | A kind of automatic parking control method and system | |
CN112703539B (en) | Travel route generation device and vehicle control device | |
CN111868801A (en) | Route generation device and vehicle control system | |
CN110398966B (en) | Path tracking control method and path tracking system | |
CN115127576B (en) | Path planning method, device, chip, terminal, electronic equipment and storage medium | |
CN113665587A (en) | Lateral control method, device, storage medium, and apparatus for autonomous vehicle | |
CN111123947A (en) | Robot traveling control method and device, electronic device, medium, and robot | |
CN114852085A (en) | Automatic vehicle driving track planning method based on road right invasion degree | |
CN114834441B (en) | Trajectory tracking control method, device and system for automatic parking and storage medium | |
CN111045428B (en) | Obstacle avoidance method, mobile robot, and computer-readable storage medium | |
JP2019066444A (en) | Position calculation method, vehicle control method, and position calculation device | |
CN115718494A (en) | Parameter calibration method of mobile robot and mobile robot | |
CN112550449B (en) | Lateral control of vehicle wireless charging guidance | |
CN114194216B (en) | Vehicle control method and device | |
CN112912293B (en) | Target track generation device, vehicle control device, target track generation method, and vehicle control method | |
JP7302693B1 (en) | Operation control device, operation control method and program | |
CN114253241B (en) | Path tracking method for industrial intelligent trolley |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |