Intelligent steer-by-wire automatic parking method for semitrailer

Abstract

The invention discloses an intelligent steer-by-wire automatic parking method for a semitrailer, which comprises the following steps of: S1, modeling a parking environment, defining a vehicle state and performing kinematics modeling; s2, generating a parking path based on a mixed A * algorithm; and S3, designing a target function and carrying out optimization solution by utilizing a model prediction control algorithm to realize rolling optimization of the automatic parking process. According to the intelligent steer-by-wire automatic parking method for the semitrailer, autonomous parking control of the semitrailer in a complex environment is achieved, and automatic collision avoidance, posture adjustment, path minimization and cost control are achieved in the parking process.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle intelligent control, and in particular to an intelligent wire-controlled steering automatic parking method for a semi-trailer. Background Art

[0002] When parking a semitrailer, due to its length and large turning radius, drivers struggle to accurately identify surrounding obstacles through rearview mirrors, resulting in low parking efficiency and a high risk of collisions. Existing semitrailer assistance systems rely heavily on manual operation and lack automated steering and path coordination control. Existing automated parking systems for standard vehicles are not adapted to the articulated structure of a semitrailer, and traditional path planning algorithms fail to consider the impact of dynamic changes in the folding angle on the rear axle trajectory.

[0003] Therefore, it is necessary to propose an intelligent wire-controlled steering automatic parking method for a semi-trailer. Summary of the Invention

[0004] The purpose of the present invention is to provide a semi-trailer intelligent steer-by-wire automatic parking method for solving the technical problems existing in the background technology.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A method for automatic parking of a semitrailer with intelligent steer-by-wire control comprises the following steps:

[0007] S1, modeling the parking environment, defining the vehicle state, and performing kinematic modeling;

[0008] S2, generates parking paths based on the hybrid A* algorithm;

[0009] S3 uses the model predictive control algorithm to design the objective function and perform optimization to achieve rolling optimization of the automatic parking process.

[0010] Furthermore, in step S1, when the parking environment is modeled, a point cloud map of the parking area is generated by laser radar scanning, and road boundaries, target parking spaces, and obstacle information are identified.

[0011] Furthermore, in step S1, when defining the vehicle state and kinematic modeling, the semi-trailer state vector is expressed as Indicates that:

[0012] x, y represent the coordinates of the rear axle center of the tractor. represents the heading angle of the tractor, Indicates the folding angle between the tractor and trailer. Indicates the trailer heading angle, ;

[0013] In the kinematic model of the vehicle, the differential equation is as follows:

[0014] ;

[0015] ;

[0016] ;

[0017] ;

[0018] ;

[0019] Where v represents the reverse speed, L1 represents the wheelbase of the tractor, and L2 represents the wheelbase of the trailer;

[0020] Semi-trailer control variables express, Indicates the front axle steering angle of the tractor, Indicates the rear axle steering angle of the trailer;

[0021] After the semi-trailer state vector is discretized, the state is updated using the Euler method as shown below:

[0022] ;

[0023] in , represents the state vector of the kth step, , Represents the control variable of the semi-trailer at step k.

[0024] Furthermore, in step S2, when generating a parking path based on the hybrid A* algorithm, specifically:

[0025] The following heuristic function is used for path planning:

[0026] ;

[0027] Where S represents the position part of the current state vector [ ], that is, the coordinate of the rear axle center of the tractor, H(S) represents the total cost estimate of the current position S, It is the traditional A* algorithm heuristic term, which represents the Euclidean distance between the current position and the target position. is the posture penalty term, λ is the dynamic weight of the folding angle;

[0028] And generate the reference trajectory by interpolation, according to the initial state and target state , generate reference path points that are evenly distributed in time:

[0029] ;

[0030] in, is the total number of steps.

[0031] Furthermore, in step S3, the following objective function is established:

[0032] ;

[0033] in , represents the state tracking error, represents the control variable of the semi-trailer at step k, and Q and R are both weight matrices;

[0034] And include the following constraints:

[0035] Position constraint, so that the x and y coordinates of the rear axle center of the tractor are limited to the preset rectangular frame when parking is completed;

[0036] Obstacle avoidance constraint, so that the trailer tail coordinates always avoid the identified obstacles, the trailer tail coordinates The conversion is performed using the following formula:

[0037] ;

[0038] The consistency constraint ensures that the trailer and the tractor are aligned when parking is completed, that is, ;

[0039] Also, during parking, the folding angle The maximum value is limited to 30°, which will fold the angle The rate of change is limited to no more than 15° / s.

[0040] Furthermore, in step S3, when optimizing the objective function, the fmincon function is used to solve the constrained nonlinear optimization problem to output the following optimal control sequence: :

[0041] .

[0042] Compared with the prior art, the advantages of the present invention are as follows:

[0043] The intelligent steer-by-wire automatic parking method for a semi-trailer provided by the present invention realizes autonomous parking control of the semi-trailer in complex environments, and automatically avoids collisions, adjusts posture, minimizes path, and controls costs during parking. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solution in this embodiment, the following is a brief introduction to the drawings required for describing the embodiment. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 This is a flow chart of a method for automatic parking of a semi-trailer with intelligent steer-by-wire provided by the present invention;

[0046] Figure 2 This is a simulation diagram at the beginning of the parking process;

[0047] Figure 3 This is a simulation diagram when the parking process is about to end. DETAILED DESCRIPTION

[0048] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the following further describes how the present invention is implemented in conjunction with the accompanying drawings and specific implementation methods.

[0049] In a specific embodiment, referring to Figure 1 As shown, the present invention provides a method for automatic parking of a semi-trailer with intelligent steer-by-wire control, comprising the following steps:

[0050] S1, modeling the parking environment, defining the vehicle state, and performing kinematic modeling;

[0051] S2, generates parking paths based on the hybrid A* algorithm;

[0052] S3 uses the model predictive control algorithm to design the objective function and perform optimization to achieve rolling optimization of the automatic parking process.

[0053] In one specific embodiment, during parking environment modeling in step S1, a LiDAR scan is used to generate a point cloud map of the parking area, identifying road boundaries, target parking spaces, and obstacles. This point cloud map can also be generated by integrating cameras, ultrasonic sensors, and other devices. Vehicle posture angle data provided by an IMU device is then combined with high-precision positioning information obtained by a GPS device to generate the vehicle's initial pose.

[0054] In a simulation experiment, referring to Figure 2 and Figure 3 As shown, the target parking space is represented by a dotted line, and its left end coordinates are [10, -7.5, 10, 4].

[0055] When defining the vehicle state and kinematic modeling, the semi-trailer state vector is used Indicates that:

[0056] x, y represent the coordinates of the rear axle center of the tractor. represents the heading angle of the tractor, Indicates the folding angle between the tractor and trailer. Indicates the trailer heading angle, ;

[0057] In the kinematic model of the vehicle, the differential equation is as follows:

[0058] ;

[0059] ;

[0060] ;

[0061] ;

[0062] ;

[0063] Where v represents the reverse speed, L1 represents the wheelbase of the tractor, and L2 represents the wheelbase of the trailer.

[0064] Semi-trailer control variables express, Indicates the front axle steering angle of the tractor, Indicates the steering angle of the trailer's rear axle.

[0065] After the semi-trailer state vector is discretized, the state is updated using the Euler method as shown below:

[0066] ;

[0067] in , represents the state vector of the kth step, , Represents the control variable of the semi-trailer at step k.

[0068] In the kinematic model of the vehicle, the state is updated by the reversing speed v and the discrete time step Ts. In this embodiment, v=-1m / s and Ts=0.2s can be set.

[0069] In step S2, when generating a parking path based on the hybrid A* algorithm, specifically:

[0070] The following heuristic function is used for path planning:

[0071] ;

[0072] Where S represents the position part of the current state vector [ ], that is, the coordinate of the rear axle center of the tractor, H(S) represents the total cost estimate of the current position S, It is the traditional A* algorithm heuristic term, which represents the Euclidean distance between the current position and the target position. is the posture penalty term, and λ is the dynamic weight of the folding angle.

[0073] The traditional A* algorithm only considers the geometric path. The present invention introduces a posture penalty term based on the Euclidean distance heuristic term of the traditional A* algorithm to limit the folding behavior in the path and ensure that the path meets the motion coupling characteristics of the trailer and the tractor.

[0074] And generate the reference trajectory by interpolation, according to the initial state and target state , λ is the dynamic weight of the folding angle, which avoids excessive bending and generates reference path points with uniform time distribution:

[0075] ;

[0076] in, is the total number of steps.

[0077] In step S3, the following objective function is established:

[0078] ;

[0079] in , represents the state tracking error, represents the control variable of the semi-trailer at step k, and Q and R are both weight matrices. The weight matrices Q and R correspond to the weights of the state variables and control variables respectively. The weight matrix R is used to suppress the excessive change of the control variable and avoid drastic switching of direction, that is, to suppress mutations to keep the system stable.

[0080] And include the following constraints:

[0081] The position constraint limits the x and y coordinates of the rear axle center of the tractor vehicle to within a preset rectangular frame when parking is completed. In this embodiment, 10 ≤ x ≤ 20, -7 ≤ y ≤ -3.

[0082] Obstacle avoidance constraint, so that the trailer tail coordinates always avoid the identified obstacles, the trailer tail coordinates The conversion is performed using the following formula:

[0083] ;

[0084] The consistency constraint ensures that the trailer and the tractor are aligned when parking is completed, that is, .

[0085] Also, during parking, the folding angle The maximum value is limited to 30°, which will fold the angle The rate of change is limited to no more than 15° / s.

[0086] Furthermore, in step S3, when optimizing the objective function, the fmincon function is used to solve the constrained nonlinear optimization problem to output the following optimal control sequence: :

[0087] .

[0088] Obtaining the optimal control sequence After that, the front axle steering angle is automatically adjusted accordingly Rear axle steering angle In this way, the precise parking of the semi-trailer is finally achieved.

[0089] In summary, the intelligent wire-controlled steering automatic parking method for a semi-trailer provided by the present invention realizes autonomous parking control of the semi-trailer in complex environments, and automatically avoids collisions, adjusts posture, minimizes path and controls costs during the parking process.

[0090] Finally, it should be noted that the above description is only an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A semi-trailer intelligent steer-by-wire automatic parking method, characterized in that: The following steps are involved: S1, modeling the parking environment, defining the vehicle state, and performing kinematic modeling; S2, generates parking paths based on the hybrid A* algorithm; S3 uses the model predictive control algorithm to design the objective function and perform optimization to achieve rolling optimization of the automatic parking process.

2. The semi-trailer intelligent steer-by-wire automatic parking method according to claim 1, characterized in that: In step S1, when modeling the parking environment, a point cloud map of the parking area is generated by laser radar scanning, and road boundaries, target parking spaces, and obstacle information are identified.

3. The semi-trailer intelligent steer-by-wire automatic parking method according to claim 2, characterized in that: In step S1, when defining the vehicle state and kinematic modeling, the semi-trailer state vector is Indicates that: x, y represent the coordinates of the rear axle center of the tractor. represents the heading angle of the tractor, Indicates the folding angle between the tractor and trailer. Indicates the trailer heading angle, ; In the kinematic model of the vehicle, the differential equation is as follows: ； ； ； ； ； Where v represents the reverse speed, L1 represents the wheelbase of the tractor, and L2 represents the wheelbase of the trailer; Semi-trailer control variables express, Indicates the front axle steering angle of the tractor, Indicates the rear axle steering angle of the trailer; After the semi-trailer state vector is discretized, the state is updated using the Euler method as shown below: ； in , represents the state vector of the kth step, , Represents the control variable of the semi-trailer at step k.

4. The semi-trailer intelligent steer-by-wire automatic parking method according to claim 3, characterized in that: In step S2, when generating a parking path based on the hybrid A* algorithm, specifically: The following heuristic function is used for path planning: ； Where S represents the position part of the current state vector [ ], that is, the coordinate of the rear axle center of the tractor, H(S) represents the total cost estimate of the current position S, It is the traditional A* algorithm heuristic term, which represents the Euclidean distance between the current position and the target position. is the posture penalty term, λ is the dynamic weight of the folding angle; And generate the reference trajectory by interpolation, according to the initial state and target state , generate reference path points that are evenly distributed in time: ； in, is the total number of steps.

5. The semi-trailer intelligent steer-by-wire automatic parking method according to claim 4, characterized in that: In step S3, the following objective function is established: ； in , represents the state tracking error, represents the control variable of the semi-trailer at step k, and Q and R are both weight matrices; And include the following constraints: Position constraint, so that the x and y coordinates of the rear axle center of the tractor are limited to the preset rectangular frame when parking is completed; Obstacle avoidance constraint, so that the trailer tail coordinates always avoid the identified obstacles, the trailer tail coordinates The conversion is performed using the following formula: ； The consistency constraint ensures that the trailer and the tractor are aligned when parking is completed, that is, ; Also, during parking, the folding angle The maximum value is limited to 30°, which will fold the angle The rate of change is limited to no more than 15° / s.

6. The semi-trailer intelligent steer-by-wire automatic parking method according to claim 5, characterized in that: In step S3, when optimizing the objective function, the fmincon function is used to solve the constrained nonlinear optimization problem to output the following optimal control sequence: : 。

Images