Method, device and equipment for predicting backing track of trailer and storage medium

Abstract

The invention discloses a trailer backing track prediction method, device and equipment and a storage medium, and belongs to the technical field of vehicle control. The method for predicting the backing track of the trailer comprises the following steps: correcting a theoretical steering angle of the trailer according to a measured value of a hinge angle between a tractor and the trailer, a measured value of a transverse offset between an actual position of the trailer and a theoretical track, a measured value of a road adhesion coefficient and a Kalman filtering algorithm to obtain a target steering angle; according to the target steering angles of the trailer at the multiple moments and the vehicle speeds of the tractor at the corresponding moments, an undetermined backing track of the trailer at the corresponding moments is predicted; according to a Monte Carlo algorithm, determining a risk value of an undetermined backing track at each moment; and determining an optimal backing track from the undetermined backing tracks at all moments according to the risk value. According to the method, the Kalman filtering dynamic correction steering angle and the Monte Carlo safety evaluation are combined, so that a safe backing track with small deviation can be obtained, and the driving risk is reduced.

Description

Technical Field

[0001] This application belongs to the field of vehicle control technology, and in particular relates to a method, device, equipment and storage medium for predicting the reversing trajectory of a trailer. Background Technology

[0002] A trailer is a vehicle that has no power of its own and needs to be towed by another vehicle (called a "tractor") to move. When towing a trailer, the tractor exhibits non-linear motion characteristics, and traditional cameras and ultrasonic sensors are greatly affected by ambient light and weather conditions, making it difficult to cover long distances and complex terrain. This results in high driving difficulty and poor maneuverability for tractor-trailers. Taking a car as the tractor and a caravan as the trailer as an example, the complex articulated structure and limited environmental perception during reversing of a car-trailer combination lead to inaccurate trajectory prediction and a high driving risk. Summary of the Invention

[0003] The embodiments of this application provide a method, apparatus, device, and storage medium for predicting the reversing trajectory of a trailer, thereby obtaining a trajectory with small deviation and safety to at least a certain extent, reducing driving risks.

[0004] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0005] According to a first aspect of the embodiments of this application, a method for predicting the reversing trajectory of a trailer is provided, comprising: The theoretical steering angle of the trailer is corrected based on the measured values ​​of the articulation angle between the tractor and the trailer, the measured values ​​of the lateral offset between the actual position and the theoretical trajectory of the trailer, the measured values ​​of the road adhesion coefficient, and the Kalman filter algorithm to obtain the target steering angle. Based on the target steering angle of the trailer at multiple times and the speed of the tractor at the corresponding times, predict the undetermined reversing trajectory of the trailer at the corresponding times. Based on the Monte Carlo algorithm, the risk value of the undetermined reversing trajectory at each time point is determined; The optimal reversing trajectory is determined from the undetermined reversing trajectories at each time point based on the risk value.

[0006] In some embodiments, the theoretical steering angle of the trailer is corrected based on the measured articulation angle between the tractor and the trailer, the measured lateral offset between the actual position of the trailer and the theoretical trajectory, the measured road adhesion coefficient, and a Kalman filter algorithm to obtain the target steering angle, including: The predicted state covariance matrix in the Kalman filter algorithm is updated based on the measured values ​​of the hinge angle, lateral offset, and road surface adhesion coefficient. The Kalman gain is determined based on the updated predicted state covariance matrix. The target steering angle is obtained by correcting the theoretical steering angle using Kalman gain.

[0007] In some embodiments, the Kalman filtering algorithm includes a noise covariance matrix. After determining the risk value of the undetermined reversing trajectory corresponding to each target steering angle, the method further includes: The weights of the road surface adhesion coefficient parameters in the noise covariance matrix are adjusted according to the risk value to obtain the updated Kalman filter algorithm. The theoretical steering angle of the trailer is corrected based on the updated extended Kalman filter algorithm.

[0008] In some embodiments, adjusting the weights of the road adhesion coefficient parameter in the noise covariance matrix according to the risk value includes: If the risk value is greater than the first preset threshold, reduce the weight of the road surface adhesion coefficient parameter in the noise covariance matrix.

[0009] In some embodiments, predicting the undetermined reversing trajectory of the trailer at a corresponding time based on the target steering angle of the trailer at multiple times and the speed of the tractor at the corresponding time includes: For each moment, based on the target steering angle and the random disturbance coefficient, the simulated steering angles for multiple future moments are obtained, and the target steering angle and the simulated steering angles are combined to obtain a steering angle sample group; For each moment, based on the steering angle sample set and vehicle speed, the undetermined reversing trajectory of the trailer is predicted.

[0010] In some embodiments, the risk value of the undetermined reversing trajectory at each time point is determined according to the Monte Carlo algorithm, including: Based on the Monte Carlo algorithm, the lateral deviation risk and steering angle fluctuation of the undetermined reversing trajectory at each time point are determined respectively; By weighting and summing the lateral deviation risk and steering angle volatility, the risk value of the undetermined reversing trajectory at the corresponding moment is obtained.

[0011] In some embodiments, determining the optimal reversing trajectory from the undetermined reversing trajectories at various times based on the risk value includes: Determine the undetermined reversing trajectory when the absolute value of the target steering angle is less than the second preset threshold; The reversing trajectory with the lowest risk value among the determined undetermined reversing trajectories is determined as the optimal reversing trajectory.

[0012] According to a second aspect of the embodiments of this application, a device for predicting the reversing trajectory of a trailer is provided, comprising: The steering angle correction module is used to correct the theoretical steering angle of the trailer based on the measured values ​​of the articulation angle between the tractor and the trailer, the measured values ​​of the lateral offset between the actual position and the theoretical trajectory of the trailer, the measured values ​​of the road adhesion coefficient, and the Kalman filter algorithm, so as to obtain the target steering angle. The trajectory prediction module is used to predict the undetermined reversing trajectory of the trailer at a corresponding time based on the target steering angle of the trailer at multiple times and the speed of the tractor at the corresponding time. The risk determination module is used to determine the risk value of the undetermined reversing trajectory at each time step based on the Monte Carlo algorithm. The trajectory filtering module is used to determine the optimal reversing trajectory from the pending reversing trajectories at various times based on the risk value.

[0013] According to a third aspect of the embodiments of this application, a device for predicting the reversing trajectory of a trailer is provided, including a processor and a memory. The memory stores computer program instructions that can be executed by the processor. When the processor executes the computer program instructions, it implements the steps of the method as described in any of the first aspects above.

[0014] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, which stores computer program instructions that, when executed by a processor, cause the processor to perform the steps of the method as described in any of the first aspects above.

[0015] In this application, by combining observations and Kalman filtering to dynamically correct the theoretical steering angle of the trailer, a more accurate target steering angle can be obtained, thereby reducing the deviation of the predicted reversing trajectory and improving the trajectory accuracy. Then, the Monte Carlo algorithm is used to evaluate the safety of each reversing trajectory, from which the trajectory with higher safety can be selected as the optimal reversing trajectory, thus reducing driving risks.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 A flowchart illustrating a method for predicting the reversing trajectory of a trailer according to some embodiments of this application is shown; Figure 2A block diagram of a device for predicting the reversing trajectory of a trailer according to some embodiments of this application is shown; Figure 3 A schematic diagram of the structure of a device for predicting the reversing trajectory of a trailer according to some embodiments of this application is shown. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0020] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0021] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0022] To enable those skilled in the art to better understand this application, a brief explanation will first be given in conjunction with the application scenarios of the method for predicting the reversing trajectory of a trailer involved in this application.

[0023] When a tractor unit is towing a trailer, it exhibits non-linear motion characteristics. Furthermore, traditional cameras and ultrasonic sensors are greatly affected by ambient light and weather conditions, making it impossible to cover long distances and complex terrains. This results in high driving difficulty and poor maneuverability for tractor units.

[0024] The scheme adopted in this application includes: correcting the theoretical steering angle of the trailer based on the measured articulation angle between the tractor and the trailer, the measured lateral offset between the actual position of the trailer and the theoretical trajectory, the measured road adhesion coefficient, and the Kalman filter algorithm to obtain the target steering angle; predicting the undetermined reversing trajectory of the trailer at corresponding times based on the target steering angle of the trailer at multiple times and the speed of the tractor at the corresponding times; determining the risk value of the undetermined reversing trajectory at each time time based on the Monte Carlo algorithm; and determining the optimal reversing trajectory from the undetermined reversing trajectories at each time time based on the risk value.

[0025] By combining observed values ​​and Kalman filtering to dynamically correct the theoretical steering angle of the trailer, a more accurate target steering angle can be obtained, thereby reducing the deviation of the predicted reversing trajectory and improving trajectory accuracy. Then, the Monte Carlo algorithm is used to conduct a safety assessment of each reversing trajectory, from which the safest trajectory can be selected as the optimal reversing trajectory, reducing driving risks.

[0026] Figure 1 A flowchart illustrating a method for predicting the reversing trajectory of a trailer according to some embodiments of this application is shown. Figure 1 As shown, a method for predicting the reversing trajectory of a trailer is provided, which may include the following steps 101 to 104.

[0027] In step 101, the theoretical steering angle of the trailer is corrected based on the measured hinge angle between the tractor and the trailer, the measured lateral offset between the actual position of the trailer and the theoretical trajectory, the measured road adhesion coefficient, and the Kalman filter algorithm to obtain the target steering angle.

[0028] Among them, the hinge angle measurement value, the lateral offset measurement value, and the road surface adhesion coefficient measurement value can all be obtained by measuring equipment.

[0029] Specifically, the aforementioned measurement values ​​can be obtained using a radar sensor array. A main radar can be installed at the rear of the tractor (specifically, it can be mounted horizontally in the middle of the rear bumper, pointing towards the trailer's articulation point); radars can be installed on both sides of the rear of the trailer (specifically, they can be installed at a 30° angle on either side of the rear of the trailer); a panoramic radar can be installed on the top of the trailer (specifically, it can be installed at a 5°~10° downward angle from the center of the top of the trailer); and optional side auxiliary radars (specifically, they can be installed below the tractor's rearview mirrors). The side auxiliary radars can reuse the radar from the Blind Spot Detection (BSD) system for intelligent driving vehicles, enabling 360° detection.

[0030] The main radar at the rear of the tractor unit monitors the articulation angle and lateral offset of the trailer in real time, and obtains corresponding articulation angle and lateral offset measurements. The radars on both sides of the rear of the trailer monitor the distance to surrounding obstacles and the curvature of the road surface. The panoramic radar on the top of the trailer constructs a three-dimensional environmental map, identifies the road adhesion coefficient, and obtains the road adhesion coefficient measurement. The theoretical steering angle of the vehicle can be calculated through the kinematic equations of the articulated vehicle.

[0031] The kinematic equations for articulated vehicles can be referenced from the following formulas: ; in, , These represent the left and right wheelbases of the tractor and trailer, respectively; β is the theoretical steering angle of the trailer; and s is the tire slip ratio. α is the road surface adhesion coefficient, and α is the hinge angle.

[0032] The Kalman filtering algorithm can be used to fuse radar observations with data such as vehicle speed and steering wheel angle from the vehicle's CAN signal to dynamically correct the theoretical steering angle β of the trailer.

[0033] In some embodiments, the predicted state covariance matrix in the Kalman filter algorithm is updated based on the measured hinge angle, the measured lateral offset, and the measured road surface adhesion coefficient; the Kalman gain is determined based on the updated predicted state covariance matrix; and the theoretical steering angle is corrected using the Kalman gain to obtain the target steering angle.

[0034] During implementation, state variables can be defined. ;in, This represents the speed of the tractor unit. (Radar observation value) ,in, For the measured value of the hinge angle, This is the measured value of the lateral offset. The measured value is the road surface adhesion coefficient. The predicted state covariance matrix is ​​iteratively updated by fusing radar observations with state variables.

[0035] State equations can be defined Observation equation Predicted state covariance matrix ;in, Let X be the estimated value at time t. Let be the radar observation value at time t. For measurement function, Let be the predicted state covariance matrix estimated at time t for the current state. For control inputs (such as steering wheel angle) F is the Jacobian matrix of the state transition, and Q is the process noise covariance matrix.

[0036] The Kalman gain can be calculated from the predicted state covariance matrix, and the specific formula is as follows: ;in, Let H be the Kalman gain at time t, H represent the measurement matrix, and R be the noise covariance matrix.

[0037] The theoretical steering angle in Kalman gain can be utilized. The corresponding component corresponds to the theoretical steering angle. The formula can be modified as follows: ,in, It is the target turning angle at time t. Let be the theoretical turning angle at time t. Theoretical turning angle in Kalman gain The corresponding components.

[0038] In step 102, the undetermined reversing trajectory of the trailer at the corresponding time is predicted based on the target steering angle of the trailer at multiple times and the speed of the tractor at the corresponding time.

[0039] In some embodiments, for each time moment, based on the target steering angle and the random disturbance coefficient, simulated steering angles for multiple future time moments are obtained, and the target steering angle and simulated steering angles are combined to obtain a steering angle sample set; for each time moment, based on the steering angle sample set and the vehicle speed, the undetermined reversing trajectory of the trailer is predicted.

[0040] The random disturbance coefficient can be steering wheel angle noise, road surface adhesion coefficient noise, or other noises, or a superposition of multiple noises. Steering wheel angle noise can be calculated by adding a small angle (e.g., the steering wheel angle itself). It can be seen that the road surface adhesion coefficient noise can be obtained by making small fluctuations in the measured value of the road surface adhesion coefficient. By injecting random disturbances, the uncertainties of real-world scenarios (such as sensor errors and dynamic changes in the road surface environment) can be simulated, and their impact on trajectory safety evaluation indicators can be quantified.

[0041] Taking the current time as time t as an example, multiple times can be time t+1, time t+2, ..., time t+n. The target steering angle at each time can be calculated using the formula... Calculated.

[0042] For the target steering angle at each moment, after adding a random disturbance coefficient, the target steering angle and the formula can be used. Calculate the simulated steering angle at future time points, where, Let i be the simulated steering angle corresponding to the i-th steering angle sample group at time t+1. Let i be the target steering angle corresponding to the i-th steering angle sample group at time t. Let be the hinge angle corresponding to the i-th steering angle sample group at time t. Let be the Kalman gain of the i-th steering angle sample group at time t. This is a function for measuring the hinge angle.

[0043] For each set of steering angle samples, the trajectory can be calculated using the following dynamic model: ; ; in, Let be the heading angle at time t. For the trajectory at time t+ x-coordinate Let x be the x-coordinate of the trajectory at time t. For the trajectory at time t+ The ordinate, Let be the ordinate of the trajectory at time t. For time step, It can be calculated using the following formula: ; in, Let be the heading angle at time t-1.

[0044] After predicting the trajectory using a dynamic model, the probability of abnormal fluctuations in steering angle caused by these random disturbance coefficients (such as collision probability, sideslip risk, etc.) can be statistically analyzed.

[0045] In step 103, the risk value of the undetermined reversing trajectory at each time point is determined according to the Monte Carlo algorithm.

[0046] During implementation, the Monte Carlo algorithm can be used to determine the lateral deviation risk, steering angle fluctuation, collision probability, sideslip risk, and other steering angle-related indicators of the undetermined reversing trajectory at each moment, thereby assessing the risk.

[0047] It is understandable that when the steering angle fluctuates abnormally, it may increase the trajectory deviation and thus trigger a collision; when the steering angle is greater than 15°, the vehicle is in an unstable state and may be at risk of sideslip; the variability of the steering angle can be determined based on the maximum value of the change in the steering angle.

[0048] In some embodiments, the lateral deviation risk and steering angle volatility of the undetermined reversing trajectory at each time point can be determined according to the Monte Carlo algorithm; the lateral deviation risk and steering angle volatility are weighted and summed to obtain the risk value of the undetermined reversing trajectory at the corresponding time point.

[0049] Understandably, through multiple Monte Carlo simulations, the lateral deviation risk and steering angle volatility of the undetermined reversing trajectory at each moment can be determined separately. By multiplying the lateral deviation risk by the corresponding weight and adding the steering volatility multiplied by the corresponding weight, the risk value of the undetermined reversing trajectory at the corresponding moment can be obtained.

[0050] Of course, the risk values ​​of the undetermined reversing trajectory at each time point can also be obtained by weighted summation of the lateral deviation risk, steering angle fluctuation, collision probability and sideslip risk.

[0051] In step 104, the optimal reversing trajectory is determined from the undetermined reversing trajectories at each time point based on the risk value.

[0052] In some embodiments, a pending reversing trajectory with an absolute value of the target steering angle less than a second preset threshold can be determined; the pending reversing trajectory with the lowest risk value among the determined pending reversing trajectories is determined as the optimal reversing trajectory.

[0053] The second preset threshold is the anti-rollover threshold, which can be obtained through calibration. Taking a second preset threshold of 15° as an example, considering that the vehicle is in an unstable state when the steering angle is greater than 15° and may have the risk of sideslip, we can first filter out the undetermined reversing trajectories from the undetermined reversing trajectories with an absolute value of the target steering angle less than 15°, and then select the trajectory with the lowest risk value from the filtered undetermined reversing trajectories.

[0054] In some embodiments, the Kalman filter algorithm includes a noise covariance matrix. After determining the risk value of the undetermined reversing trajectory corresponding to each target steering angle, the road surface adhesion coefficient parameter in the noise covariance matrix can be adjusted according to the risk value to obtain an updated Kalman filter algorithm. The theoretical steering angle of the trailer is then corrected according to the updated extended Kalman filter algorithm.

[0055] Understandably, the road surface adhesion coefficient is the random variable that has the greatest impact on the steering angle. After determining the risk value of the undetermined reversing trajectory corresponding to the target steering angle using the Monte Carlo algorithm, when the risk value is greater than the first preset threshold, the weight of the road surface adhesion coefficient parameter in the noise covariance matrix can be adjusted to improve the accuracy of the target steering angle and thus reduce the subsequent trajectory prediction deviation.

[0056] Specifically, when the risk value is greater than a first preset threshold, the weight of the road surface adhesion coefficient parameter in the noise covariance matrix is ​​reduced.

[0057] It should be noted that in the Monte Carlo simulation, the distribution range of the steering angle is used to assess the risk of different steering strategies. In the extended Kalman filter, the steering angle, as one of the state variables, is compensated for by real-time correction of radar observations to mitigate the influence of road friction. Large fluctuations in the road adhesion coefficient increase the estimation bias of the target steering angle. By reducing the weight of the road adhesion coefficient parameter in the noise covariance matrix, the dependence on noisy radar observations can be reduced, thus lowering the estimation error introduced by road friction.

[0058] By using Kalman filtering dynamic correction to provide a physical basis for Monte Carlo evaluation, and then using the Monte Carlo evaluation results to provide feedback for Kalman filtering dynamic correction, a closed-loop optimization is formed.

[0059] After determining the optimal reversing trajectory, the user can choose between automatic or active mode to control the vehicle to follow that trajectory. When the user selects automatic mode, the vehicle control system receives steering wheel angle commands. As a control system input, it works in conjunction with the electrically powered steering (EPS) system to actively limit the steering wheel angle to prevent deviation from the optimal reversing trajectory. The steering wheel angle command... The target steering angle can be obtained by tracking it using a PID controller.

[0060] After the user selects the active mode, the user takes the lead and the EPS system supervises. When the user's operation deviates from the optimal reversing trajectory, the suggested steering direction and danger zone can be displayed through the human-machine interface (HMI) on the central control screen to warn or remind the user.

[0061] This application combines observations and Kalman filtering to dynamically correct the theoretical steering angle of the trailer, thereby obtaining a more accurate target steering angle, which reduces the deviation of the predicted reversing trajectory and improves the trajectory accuracy. Then, the Monte Carlo algorithm is used to evaluate the safety of each reversing trajectory, from which the safest trajectory can be selected as the optimal reversing trajectory, thus reducing driving risks.

[0062] The following describes an embodiment of the apparatus described in this application, which can be used to execute the method for predicting the reversing trajectory of a trailer in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method for predicting the reversing trajectory of a trailer described above in this application.

[0063] See Figure 2 The diagram shows a block diagram of a device for predicting the reversing trajectory of a trailer in an embodiment of this application.

[0064] like Figure 2As shown, the device for predicting the reversing trajectory of a trailer according to an embodiment of this application includes: a steering angle correction module 201, a trajectory prediction module 202, a risk determination module 203, and a trajectory filtering module 204. The steering angle correction module 201 is used to correct the theoretical steering angle of the trailer based on the measured hinge angle between the tractor and the trailer, the measured lateral offset between the actual position of the trailer and the theoretical trajectory, the measured road surface adhesion coefficient, and a Kalman filter algorithm to obtain a target steering angle. The trajectory prediction module 202 is used to predict the undetermined reversing trajectory of the trailer at corresponding times based on the target steering angle of the trailer at multiple times and the speed of the tractor at the corresponding times. The risk determination module 203 is used to determine the risk value of the undetermined reversing trajectory at each time based on a Monte Carlo algorithm. The trajectory filtering module 204 is used to determine the optimal reversing trajectory from the undetermined reversing trajectories at each time based on the risk value.

[0065] In some embodiments of this application, based on the aforementioned scheme, the steering angle correction module 201 is further configured to update the predicted state covariance matrix in the Kalman filter algorithm according to the articulation angle measurement value, the lateral offset measurement value and the road surface adhesion coefficient measurement value; determine the Kalman gain according to the updated predicted state covariance matrix; and use the Kalman gain to correct the theoretical steering angle to obtain the target steering angle.

[0066] In some embodiments of this application, based on the aforementioned scheme, the Kalman filter algorithm includes a noise covariance matrix and a steering angle correction module 201, which is further used to adjust the weights of the road surface adhesion coefficient parameters in the noise covariance matrix according to the risk value, so as to obtain an updated Kalman filter algorithm; and to correct the theoretical steering angle of the trailer according to the updated extended Kalman filter algorithm.

[0067] In some embodiments of this application, based on the aforementioned scheme, the steering angle correction module 201 is further used to reduce the weight of the road surface adhesion coefficient parameter in the noise covariance matrix when the risk value is greater than a first preset threshold.

[0068] In some embodiments of this application, based on the aforementioned scheme, the trajectory prediction module 202 is further configured to obtain, for each time moment, a simulated steering angle for multiple future time moments based on the target steering angle and the random disturbance coefficient, and combine the target steering angle and the simulated steering angle to obtain a steering angle sample group; For each moment, based on the steering angle sample set and vehicle speed, the undetermined reversing trajectory of the trailer is predicted.

[0069] In some embodiments of this application, based on the aforementioned scheme, the risk determination module 203 is further configured to determine the lateral offset risk and steering angle fluctuation of the undetermined reversing trajectory at each time according to the Monte Carlo algorithm; and to perform a weighted summation of the lateral offset risk and steering angle fluctuation to obtain the risk value of the undetermined reversing trajectory at the corresponding time.

[0070] In some embodiments of this application, based on the aforementioned scheme, the trajectory filtering module 204 is further used to determine the undetermined reversing trajectory whose absolute value of the target steering angle is less than a second preset threshold; and to determine the undetermined reversing trajectory with the lowest risk value among the determined undetermined reversing trajectories as the optimal reversing trajectory.

[0071] Based on the same inventive concept, this application also provides a device for predicting the reversing trajectory of a trailer, referencing... Figure 3 The diagram shows a schematic of the structure of a trailer reversing trajectory prediction device according to an embodiment of this application. The trailer reversing trajectory prediction device includes one or more memories 304, one or more processors 302, and at least one computer program (computer program instruction) stored in the memory 304 and executable on the processor 302. When the processor 302 executes the computer program, it implements the method described above.

[0072] Among them, Figure 3 In this document, a bus architecture (represented by bus 300) is used. Bus 300 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 during operation.

[0073] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, cause the processor to perform the steps of the method described above.

[0074] Based on the same inventive concept, embodiments of this application provide a computer program product, including a computer program, which, when executed by a processor, causes the processor to perform the steps of the method described above.

[0075] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0077] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0078] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing computer program instructions, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0079] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for predicting the reversing trajectory of a trailer truck, characterized in that, include: The theoretical steering angle of the trailer is corrected based on the measured hinge angle between the tractor and the trailer, the measured lateral offset between the actual position and the theoretical trajectory of the trailer, the measured road adhesion coefficient, and the Kalman filter algorithm to obtain the target steering angle. Based on the target steering angle of the trailer at multiple times and the speed of the tractor at the corresponding times, predict the undetermined reversing trajectory of the trailer at the corresponding times; Based on the Monte Carlo algorithm, the risk value of the undetermined reversing trajectory at each time point is determined; The optimal reversing trajectory is determined from the undetermined reversing trajectories at each time point based on the aforementioned risk value.

2. The method for predicting the reversing trajectory of a trailer according to claim 1, characterized in that, The process of correcting the theoretical steering angle of the trailer based on the measured articulation angle between the tractor and the trailer, the measured lateral offset between the actual position and the theoretical trajectory of the trailer, the measured road adhesion coefficient, and the Kalman filter algorithm to obtain the target steering angle includes: The predicted state covariance matrix in the Kalman filter algorithm is updated based on the measured hinge angle, the measured lateral offset, and the measured road surface adhesion coefficient. The Kalman gain is determined based on the updated predicted state covariance matrix. The theoretical steering angle is corrected using the Kalman gain to obtain the target steering angle.

3. The method for predicting the reversing trajectory of a trailer according to claim 1, characterized in that, The Kalman filtering algorithm includes a noise covariance matrix. After determining the risk value of the undetermined reversing trajectory corresponding to each of the target steering angles, the method further includes: The weights of the road surface adhesion coefficient parameters in the noise covariance matrix are adjusted according to the risk value to obtain the updated Kalman filter algorithm. The theoretical steering angle of the trailer is corrected based on the updated extended Kalman filter algorithm.

4. The method for predicting the reversing trajectory of a trailer according to claim 3, characterized in that, The step of adjusting the weights of the road adhesion coefficient parameter in the noise covariance matrix based on the risk value includes: If the risk value is greater than a first preset threshold, the weight of the road surface adhesion coefficient parameter in the noise covariance matrix is ​​reduced.

5. The method for predicting the reversing trajectory of a trailer according to claim 1, characterized in that, The step of predicting the undetermined reversing trajectory of the trailer at a corresponding time based on the target steering angle of the trailer at multiple times and the speed of the tractor at the corresponding time includes: For each moment, based on the target steering angle and the random disturbance coefficient, simulated steering angles for multiple future moments are obtained, and the target steering angle and the simulated steering angles are combined to obtain a steering angle sample group; For each moment, based on the steering angle sample set and the vehicle speed, the undetermined reversing trajectory of the trailer is predicted.

6. The method for predicting the reversing trajectory of a trailer according to claim 5, characterized in that, The process of determining the risk value of the undetermined reversing trajectory at each moment based on the Monte Carlo algorithm includes: Based on the Monte Carlo algorithm, the lateral deviation risk and steering angle fluctuation of the undetermined reversing trajectory at each time point are determined respectively; The risk value of the undetermined reversing trajectory at the corresponding moment is obtained by weighted summation of the lateral offset risk and the steering angle fluctuation.

7. The method for predicting the reversing trajectory of a trailer according to claim 1, characterized in that, The step of determining the optimal reversing trajectory from the undetermined reversing trajectories at each time point based on the risk value includes: Determine the undetermined reversing trajectory where the absolute value of the target steering angle is less than a second preset threshold; The reversing trajectory with the lowest risk value among the determined undetermined reversing trajectories is determined as the optimal reversing trajectory.

8. A device for predicting the reversing trajectory of a trailer, characterized in that, include: The steering angle correction module is used to correct the theoretical steering angle of the trailer based on the measured hinge angle between the tractor and the trailer, the measured lateral offset between the actual position of the trailer and the theoretical trajectory, the measured road adhesion coefficient, and the Kalman filter algorithm, so as to obtain the target steering angle. The trajectory prediction module is used to predict the undetermined reversing trajectory of the trailer at a corresponding time based on the target steering angle of the trailer at multiple times and the speed of the tractor at the corresponding time. The risk determination module is used to determine the risk value of the undetermined reversing trajectory at each time step based on the Monte Carlo algorithm. The trajectory filtering module is used to determine the optimal reversing trajectory from the pending reversing trajectories at various times based on the risk value.

9. A device for predicting the reversing trajectory of a trailer, comprising a processor and a memory, characterized in that, The memory stores computer program instructions that can be executed by the processor, and when the processor executes the computer program instructions, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, cause the processor to perform the steps of the method as described in any one of claims 1 to 7.

Images