Self-adaptive automatic hooking control method and system and medium

Abstract

The invention discloses a self-adaptive automatic hooking control method and system and a medium, belongs to the technical field of automatic traction hooking, and aims to solve the technical problems that an existing trailer automatic hooking system can only automatically hook a triangular arm of a trailer with a specific height and cannot adapt to triangular arm trailers with different mounting heights, and the working efficiency is low easily. The method comprises the following steps: performing path planning on the unmanned tractor, and determining a pre-hooking position of the unmanned tractor; state recognition is conducted on the trailer triangular arm which is connected with the trailer in a hanging mode, and the current posture state of the trailer triangular arm is obtained; performing spatial attitude analysis on the pose state to obtain a deviation spatial parameter of the current trailer triangular arm; according to the deviation space parameters, self-adaptive adjustment control related to connection is carried out on the unmanned tractor and the automatic hooking system, and vehicle control information of the unmanned tractor is obtained; and performing tractable control adjustment on the automatic hooking system to obtain automatic hooking completion information of the trailer.

Description

Technical Field

[0001] This application relates to the field of automatic towing hooks, and particularly to an adaptive automatic hook control method, system and medium. Background Art

[0002] The connection between the traditional trailer tri - arm (usually referring to the kingpin) and the tractor is mainly achieved through a mechanical locking structure. The specific steps are as follows: Before connection, it is necessary to check whether the surface of the tractor saddle is smeared with enough lithium - based grease to ensure uniform lubrication and reduce wear. Adjust the height of the trailer. Adjust the height of the trailer kingpin through the support legs so that it is lower than the plane of the tractor saddle, and ensure that the center lines of the two are aligned. If the height difference is too large, it may lead to connection failure or component damage.

[0003] When existing driverless tractors perform cargo transfer tasks, different trailers will be hooked as needed. To achieve unmanned operation, the trailer hooking action is automatically completed by the vehicle. Generally, in the prior art, after the vehicle identifies the position of the trailer, it adjusts the vehicle pose so that the tractor hook aligns with the trailer. However, the existing trailer automatic hook system of the towing vehicle can only automatically hook the tri - arm of the trailer at a specific height and cannot adapt to the tri - arm trailers with different installation heights. In the existing trailer hook, the kingpin and the tri - arm guide cannot be independently controlled. For example, if the vehicle loses power abnormally, the hook cannot be disengaged from the trailer. Summary of the Invention

[0004] The embodiments of this application provide an adaptive automatic hook control method, system and medium to solve the following technical problems: The existing trailer automatic hook system can only automatically hook the tri - arm of the trailer at a specific height and cannot adapt to the tri - arm trailers with different installation heights, which easily leads to slow working efficiency.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] On the one hand, the embodiments of this application provide a method for path - planning an unmanned tractor based on the position of the hooked trailer, determining the pre - hooking position of the unmanned tractor; according to the pre - hooking position, and through the vision sensor of the unmanned tractor, identifying the state of the trailer tri - arm of the hooked trailer to obtain the pose state of the current trailer tri - arm; performing spatial attitude analysis on the pose state to obtain the deviation space parameters of the current trailer tri - arm; according to the deviation space parameters, performing adaptive adjustment control on the unmanned tractor and the automatic hook system regarding the connection to be made to obtain the vehicle control information of the unmanned tractor; according to the vehicle control information, and based on the hook - in - place detection information, performing control adjustment on the automatic hook system for traction to obtain the information that the trailer is automatically hooked up.

[0007] In the embodiments of the present application, through path planning based on the position of the towed trailer, it is possible to ensure that the driverless tractor accurately reaches the predetermined coupling position during driving, improving the accuracy of operation. The determination of the automatic coupling position and the state recognition of the trailer's triangular arm reduce manual intervention and improve the automation level of the driverless tractor operation. It can also quickly and accurately obtain the pose state, thereby accelerating the coupling process and improving the overall operation efficiency. It helps to predict and adjust potential risks in the coupling process in advance, reduce the possibility of coupling failure, and enhance operation safety. It enables the driverless tractor and the automatic hook system to adapt to different coupling environments and improve the adaptability of the system. The use of the hook-in-place detection information can ensure the completion of the coupling action and avoid subsequent problems caused by insecure coupling. Through visual sensors and pose state analysis, coupling errors caused by visual errors or operator mistakes can be reduced.

[0008] In a feasible implementation manner, based on the position of the towed trailer, path planning is performed on the driverless tractor to determine the pre-coupling position of the driverless tractor, which specifically includes: determining the position of the towed trailer based on the map positioning information of the towed trailer; through the A* algorithm, performing global planning topological structure processing on the current position node of the driverless tractor and the position of the towed trailer, and obtaining path planning information in the obstacle-free area based on the reward function and the local restricted topological structure of dynamic obstacles; performing target tracking control on the driverless tractor according to the path planning information to determine the final position node of the driverless tractor; determining the framed topological knot area corresponding to the final position node as the pre-coupling position; where the final position node is the center point of the framed topological knot area.

[0009] In a feasible implementation, according to the pre-hitching position and through the vision sensor of the driverless tractor, the state of the trailer triangular arm of the hitch trailer is recognized to obtain the pose state of the current trailer triangular arm, which specifically includes: when the driverless towing vehicle is in the pre-hitching position, through the vision sensor, three-dimensional acquisition of image data of the trailer triangular arm is performed to obtain a three-dimensional image of the trailer triangular arm; the three-dimensional image of the trailer triangular arm is subjected to edge contour cropping processing, and based on the differential pixels of the front and back backgrounds, the trailer triangular arm region map is segmented; according to a preset three-dimensional shape template of the trailer triangular arm, template matching processing for type recognition is performed on the trailer triangular arm region map to determine the trailer triangular arm type map; a fixed pixel position filling judgment process regarding the connection state of the drawbar pin is performed on the trailer triangular arm type map to obtain pixel filling result information; if the pixel filling result information indicates the existence of filled pixels, the pose state of the current trailer triangular arm is determined to be a non-hitchable pose; if the pixel filling result information indicates the non-existence of filled pixels, the pose state of the current trailer triangular arm is determined to be a hitchable pose; wherein, the pose state includes: the non-hitchable pose and the hitchable pose.

[0010] In a feasible implementation, spatial pose analysis is performed on the pose state to obtain the deviation space parameters of the current trailer triangular arm, which specifically includes: when the pose state is a hitchable pose, the three-dimensional image of the trailer triangular arm is extracted; the spatial position information of the drawbar pin of the automatic hitching system in the driverless tractor is obtained; wherein, the spatial position information of the drawbar pin is a three-dimensional spatial coordinate based on the ground; the spatial coordinates of the key points in the three-dimensional image of the trailer triangular arm are extracted to obtain the key point coordinates of the current trailer triangular arm; wherein, the key point coordinates are three-dimensional spatial coordinates based on the ground; a deviation vector calculation is performed between the key point coordinates and the alignment point coordinates in the spatial position information of the drawbar pin to obtain deviation vector information; wherein, the deviation vector information includes: deviation space distance information and deviation angle information; the deviation vector information is determined as the deviation space parameters of the current trailer triangular arm.

[0011] In a feasible implementation manner, before performing adaptive adjustment control on the driverless tractor and the automatic hitching system according to the deviation space parameter to obtain the vehicle control information of the driverless tractor, the method further includes: using a lidar to identify the spatial positions of the pre-hitching position of the driverless tractor and the hitching trailer position, respectively obtaining the first frame coordinates of the driverless tractor and the second frame coordinates of the trailer triangular arm; extracting the automatic hitching device coordinates corresponding to the automatic hitching system in the first frame coordinates; performing spatial simulation overlap calculation on the automatic hitching device coordinates and the second frame coordinates to obtain the path deviation parameter of the driverless tractor; performing parameter correction processing on the path deviation parameter through the deviation space parameter to obtain the local path control information of the driverless tractor; wherein, the local path control information includes: path interval distance information and horizontal offset distance information.

[0012] In a feasible implementation manner, performing adaptive adjustment control on the driverless tractor and the automatic hitching system according to the deviation space parameter to obtain the vehicle control information of the driverless tractor specifically includes: performing adaptive height adjustment control on the shovel-shaped guiding electric cylinder and the horn-shaped guiding electric cylinder in the automatic hitching system according to the deviation space parameter to obtain the shovel-shaped guiding control parameter and the horn-shaped guiding control parameter; combining the shovel-shaped guiding control parameter and the horn-shaped guiding control parameter into the device control information of the automatic hitching system; determining the execution time of the device control information as the first execution time, and setting the execution time of the local path control information as the second execution time; integrating the first execution time and the second execution time into a control information execution time strategy; generating the vehicle control information of the driverless tractor based on the control information execution time strategy, the local path control information, and the device control information.

[0013] In a feasible implementation manner, performing traction control adjustment on the automatic hitching system according to the vehicle control information and based on the hitching-in-place detection information to obtain the trailer automatic hitching completion information specifically includes: when the execution of the vehicle control information is completed, detecting and obtaining the hitching-in-place detection information through the in-place detection switch preset in the automatic hitching system; performing parameter control adjustment on the shovel-shaped guiding electric cylinder and the horn-shaped guiding electric cylinder based on the traction state according to the hitching-in-place detection information to obtain the device secondary control information; determining the hitching state information of the driverless tractor as the trailer automatic hitching completion information based on the execution completion state of the device secondary control information.

[0014] In a feasible implementation manner, the secondary control information of the device is used to control the lifting and / or lowering of both the shovel-shaped guiding structure and the horn-shaped guiding structure in the automatic hooking system, so that the driverless tractor can complete the towing of the towed trailer.

[0015] In a second aspect, the present application provides an adaptive automatic hooking control system, which is characterized in that the adaptive automatic hooking control system mainly includes: a vision sensor module, a shovel-shaped guiding electric cylinder module, a horn-shaped guiding electric cylinder module, a position detection switch, and a towing pin; the vision sensor module is used to identify the state of the trailer triangular arm of the towed trailer to obtain the pose state of the current trailer triangular arm; the shovel-shaped guiding electric cylinder module is used to control the lifting and / or lowering of the shovel-shaped guiding structure; the horn-shaped guiding electric cylinder module is used to control the lifting and / or lowering of the horn-shaped guiding structure; the position detection switch is used to detect and obtain the hooking position detection information; the towing pin is used to connect and fix the trailer triangular arm.

[0016] In a third aspect, the present application provides a non-volatile computer storage medium, which is characterized in that the storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, and each program includes instructions, and when the instructions are executed by a terminal, the terminal is enabled to execute an adaptive automatic hooking control method according to any one of the above embodiments.

[0017] The present application provides an adaptive automatic hooking control method, system and medium. Compared with the prior art, the embodiments of the present application have the following beneficial technical effects:

[0018] 1. Precise path planning: Through path planning based on the position of the towed trailer, it can ensure that the driverless tractor accurately reaches the predetermined hooking position during driving, improving the accuracy of operation.

[0019] 2. Improved automation level: The determination of the automatic hooking position and the identification of the state of the trailer triangular arm reduce manual intervention and improve the automation level of the operation of the driverless tractor.

[0020] 3. Improved hooking efficiency: By using a vision sensor to identify the state of the trailer triangular arm, the pose state can be quickly and accurately obtained, thereby accelerating the hooking process and improving the overall operation efficiency.

[0021] 4. Enhanced safety: The spatial attitude analysis and the acquisition of deviation space parameters help to predict and adjust potential risks in the hooking process in advance, reduce the possibility of hooking failure, and enhance the operation safety.

[0022] 5. Adaptive adjustment control: Adaptive adjustment control is performed according to the deviation space parameters, enabling the unmanned tractor and the automatic coupling system to adapt to different coupling environments and improving the adaptability of the system.

[0023] 6. Precise control information: By obtaining vehicle control information, precise control of the unmanned tractor can be achieved, ensuring a stable and reliable coupling process.

[0024] 7. Hook-in-place detection: The use of hook-in-place detection information can ensure the completion of the coupling action and avoid subsequent problems caused by insecure coupling.

[0025] 8. Reduction of operation errors: Through visual sensors and pose state analysis, coupling errors caused by visual errors or operator mistakes can be reduced.

[0026] 9. Enhancement of user experience: The automated coupling process can provide a safer and more convenient user experience for operators. Description of the Drawings

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0028] Figure 1 It is a flowchart of an adaptive automatic coupling control method provided by an embodiment of the present application;

[0029] Figure 2 It is a schematic diagram of the structural connection relationship of an automatic coupling system provided by an embodiment of the present application; where it includes: lidar / camera, shovel-shaped guiding electric cylinder, horn-shaped guiding electric cylinder, in-place detection switch, drawbar pin, shovel-shaped guiding, and horn-shaped guiding;

[0030] Figure 3 It is a schematic diagram of the structure of an adaptive automatic coupling control system provided by an embodiment of the present application. Detailed Embodiments

[0031] In order to enable those skilled in the art to better understand the technical solutions in the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0032] An embodiment of the present application provides an adaptive automatic hook control method, as Figure 1 shown, the adaptive automatic hook control method specifically includes steps S101 - S105:

[0033] S101. Based on the position of the towed trailer, perform path planning for the driverless tractor, and determine the pre - connection position of the driverless tractor.

[0034] Specifically, it is necessary to first determine the position of the towed trailer based on the map positioning information where the towed trailer is located.

[0035] Furthermore, through the A* algorithm, perform global - planning topological structure processing on the current position node of the driverless tractor and the position of the towed trailer, and based on the reward function and the local restricted topological structure of dynamic obstacles, obtain the path - planning information in the obstacle - free area.

[0036] Furthermore, according to the path - planning information, perform target - tracking control on the driverless tractor to determine the final position node of the driverless tractor.

[0037] Furthermore, determine the box - selected topological knot area corresponding to the final position node as the pre - connection position; wherein, the final position node is the center point of the box - selected topological knot area.

[0038] In one embodiment, first perform precise map positioning on the towed trailer. This usually involves using GPS, inertial measurement unit (IMU) or other positioning systems to obtain the precise position of the trailer on the map. Then use the A* algorithm for global path planning. The A* algorithm is a heuristic search algorithm that combines the advantages of best - first search and Dijkstra's algorithm and can find the shortest path from the current position of the driverless tractor to the position of the towed trailer. During this process, the algorithm will consider reward functions, which may include the efficiency, safety, or minimization of energy consumption of the path. At the same time, the algorithm also needs to handle dynamic obstacles, which may appear or disappear during the planning process, so the topological structure needs to be updated dynamically.

[0039] In one embodiment, according to the path - planning information generated by the A* algorithm, the driverless tractor performs target - tracking control. This involves the control algorithm of the driverless tractor, which can adjust the speed and direction of the vehicle according to the path - planning information to ensure that the vehicle moves along the planned path. When the driverless tractor approaches the towed trailer, the system determines the final position node of the driverless tractor, that is, the specific position where the driverless tractor should arrive. The box - selected topological knot area corresponding to the final position node is determined as the pre - connection position. This area usually has the final position node as the center point, and its size and shape may be adjusted according to actual needs and safety requirements.

[0040] S102. Identify the pose state of the trailer triangular arm of the towed trailer according to the pre-hitching position and through the vision sensor of the driverless tractor, so as to obtain the current pose state of the trailer triangular arm.

[0041] Specifically, when the driverless vehicle is in the pre-hitching position, use the vision sensor to perform three-dimensional acquisition of the image data of the trailer triangular arm to obtain the three-dimensional image of the trailer triangular arm.

[0042] Furthermore, perform cropping processing on the edge contour of the three-dimensional image of the trailer triangular arm, and based on the differential pixels of the front and back backgrounds, segment out the regional map of the trailer triangular arm.

[0043] Furthermore, according to the preset three-dimensional shape template of the trailer triangular arm, perform template matching processing for type recognition on the regional map of the trailer triangular arm to determine the type map of the trailer triangular arm.

[0044] Furthermore, perform fixed pixel position filling judgment processing on the type map of the trailer triangular arm regarding the connection state of the towing pin to obtain pixel filling result information.

[0045] If the pixel filling result information indicates the existence of filled pixels, then determine the pose state of the current trailer triangular arm as a non-hitchable pose. If the pixel filling result information indicates the non-existence of filled pixels, then determine the pose state of the current trailer triangular arm as a hitchable pose. Among them, the pose state includes: non-hitchable pose and hitchable pose.

[0046] In one embodiment, use the vision sensor on the driverless vehicle to collect the three-dimensional image of the trailer triangular arm. This may involve using multiple cameras or depth sensors to obtain the omnidirectional information of the triangular arm. Then preprocess the collected three-dimensional image data, including denoising, correcting distortion, etc., to improve the image quality. After that, perform edge contour cropping processing on the preprocessed image to remove the unnecessary parts in the image and only retain the area of the trailer triangular arm. Finally, use the differential pixels of the front and back backgrounds to segment the cropped image, thereby extracting the regional map of the trailer triangular arm.

[0047] In one embodiment, a preset three-dimensional shape template of the trailer triangular arm is used to identify the type of the trailer triangular arm area diagram. Through the template matching algorithm, the type and shape of the trailer triangular arm can be determined. Analyze the trailer triangular arm type diagram, and use fixed pixel position filling judgment processing to determine the connection state of the drawbar pin. This usually involves image recognition technologies such as edge detection and morphological operations. Then, judge the pose state of the trailer triangular arm according to the pixel filling result information: if there are filled pixels, it indicates that the drawbar pin of the previous tractor may not be completely disengaged, or the triangular arm is in an ungrippable pose, so the pose state is determined to be an ungrippable pose. If there are no filled pixels, it indicates that the drawbar pin has been completely disengaged and the triangular arm is in a grippable pose, so the pose state is determined to be a grippable pose.

[0048] S103. Conduct a spatial attitude analysis on the pose state to obtain the deviation space parameters of the current trailer triangular arm.

[0049] Specifically, when the pose state is a grippable pose, extract the three-dimensional image of the trailer triangular arm.

[0050] Further, obtain the spatial position information of the drawbar pin of the automatic hitching system in the driverless tractor. Among them, the spatial position information of the drawbar pin is the three-dimensional coordinates in space based on the ground.

[0051] Further, extract the spatial coordinates of the key points in the three-dimensional image of the trailer triangular arm to obtain the key point coordinates of the current trailer triangular arm. Among them, the key point coordinates are the three-dimensional coordinates in space based on the ground.

[0052] Further, calculate the deviation vector between the key point coordinates and the alignment point coordinates in the spatial position information of the drawbar pin to obtain the deviation vector information. Among them, the deviation vector information includes: deviation space distance information and deviation angle information.

[0053] Further, determine the deviation vector information as the deviation space parameters of the current trailer triangular arm.

[0054] In one embodiment, a vision sensor (such as a stereo camera or a depth camera) on the driverless tractor is used to capture the three-dimensional image of the trailer triangular arm. The automatic hitching system is internally integrated with sensors (such as lidar, ultrasonic sensors or GPS) for detecting the spatial position of the drawbar pin. The data provided by these sensors are based on the ground and describe the three-dimensional coordinates (x, y, z) of the drawbar pin. In the three-dimensional image of the trailer triangular arm, key points are identified, and these points are crucial for determining the position and attitude of the triangular arm. Use image processing algorithms (such as point cloud processing technology) to extract these key points from the three-dimensional image and calculate their three-dimensional coordinates relative to the ground.

[0055] As a feasible implementation, the key point coordinates of the trailer triangular arm are compared with the alignment point coordinates in the spatial position information of the towing pin. By calculating the difference between the two coordinates, a deviation vector is obtained, including the deviation spatial distance and deviation angle information. The deviation spatial distance refers to the straight-line distance between the key point and the alignment point of the towing pin, and the deviation angle refers to the included angle between the two vectors. Then the deviation vector information is used as the deviation spatial parameter of the current trailer triangular arm. These parameters will be used for subsequent adaptive adjustment control to ensure that the driverless towing vehicle can accurately hook the trailer triangular arm to the towing pin. S104. According to the deviation spatial parameters, perform adaptive adjustment control on the driverless towing vehicle and the automatic hooking system for the connection to be made, and obtain the vehicle control information of the driverless towing vehicle.

[0056] Specifically, it is also necessary to use lidar to identify the spatial positions of the pre-hooking position of the driverless towing vehicle and the hooking trailer position, and obtain the first frame coordinates of the driverless towing vehicle and the second frame coordinates of the trailer triangular arm respectively.

[0057] Furthermore, extract the automatic hooking device coordinates corresponding to the automatic hooking system from the first frame coordinates.

[0058] Furthermore, perform a spatial simulation overlap calculation on the automatic hooking device coordinates and the second frame coordinates to obtain the path deviation parameters of the driverless towing vehicle.

[0059] In one embodiment, lidar (LiDAR) technology is used to accurately identify the spatial positions of the pre-hooking position of the driverless towing vehicle and the position of the hooking trailer. Through lidar scanning, the first frame coordinates of the driverless towing vehicle (the first frame generally refers to the vehicle body frame of the driverless towing vehicle) and the second frame coordinates of the trailer triangular arm are obtained respectively. The coordinate information of the automatic hooking device corresponding to the automatic hooking system is extracted from the first frame coordinates. Perform a spatial simulation overlap calculation on the coordinates of the automatic hooking device and the second frame coordinates of the trailer triangular arm. Through calculation, the path deviation parameters of the driverless towing vehicle are obtained, and these parameters describe the deviation between the position of the driverless towing vehicle in space and the ideal hooking path. The path deviation parameters can also be corrected using the deviation spatial parameters. Through correction, the local path control information of the driverless towing vehicle is obtained, including path interval distance information and horizontal offset distance information.

[0060] Furthermore, perform parameter correction processing on the path deviation parameters through the deviation spatial parameters to obtain the local path control information of the driverless towing vehicle. Among them, the local path control information includes: path interval distance information and horizontal offset distance information.

[0061] Further, according to the deviation space parameters, adaptive height adjustment control is performed on the shovel-shaped guiding electric cylinder and the horn-shaped guiding electric cylinder in the automatic hooking system to obtain the shovel-shaped guiding control parameters and the horn-shaped guiding control parameters.

[0062] Further, the shovel-shaped guiding control parameters and the horn-shaped guiding control parameters are combined into the device control information of the automatic hooking system.

[0063] Further, the execution time of the device control information is determined as the first execution time, and the execution time of the local path control information is the second execution time. The first execution time and the second execution time are integrated into the control information execution time strategy.

[0064] Further, based on the control information execution time strategy, the local path control information, and the device control information, the vehicle control information of the driverless tractor is generated.

[0065] As a feasible implementation manner, the deviation space parameters can also be used to perform adaptive height adjustment control on the shovel-shaped guiding electric cylinder and the horn-shaped guiding electric cylinder in the automatic hooking system. Through adjustment, the shovel-shaped guiding control parameters and the horn-shaped guiding control parameters are obtained. Then, the shovel-shaped guiding control parameters and the horn-shaped guiding control parameters are combined into the device control information of the automatic hooking system. After that, the execution time of the device control information is determined as the first execution time, and the execution time of the local path control information is the second execution time. The first execution time and the second execution time are integrated into the control information execution time strategy. Finally, based on the control information execution time strategy, the local path control information, and the device control information, the vehicle control information of the driverless tractor is generated. These control information will guide the movement of the driverless tractor to ensure that it can perform the hooking operation according to the predetermined path and posture.

[0066] S105. According to the vehicle control information and based on the hooking-in-place detection information, perform traction control adjustment on the automatic hooking system to obtain the trailer automatic hooking completion information.

[0067] Specifically, Figure 2 is a schematic diagram of the structural connection relationship of an automatic hooking system provided by an embodiment of the present application. As Figure 2 shown, when the execution of the vehicle control information is completed, the hooking-in-place detection information is detected and obtained through the in-place detection switch preset in the automatic hooking system.

[0068] Further, based on the hook-in-place detection information, parameter control and adjustment are performed on the shovel-shaped guiding electric cylinder and the horn-shaped guiding electric cylinder in the traction-enabled state to obtain secondary device control information. The secondary device control information is used to control the lifting and / or lowering of both the shovel-shaped guiding structure and the horn-shaped guiding structure in the automatic hook system, so that the driverless tractor can complete the traction driving of the towed trailer. That is, triggered by the detection of the angular arm in place, the hook is hooked, and the shovel-shaped guiding and horn-shaped guiding are lifted to the traction-enabled position.

[0069] Further, based on the execution completion status of the secondary device control information, the hitching status information of the driverless tractor is determined as the trailer automatic hitching completion information.

[0070] As a feasible implementation, the control system of the adaptive automatic hook includes: a trailer recognition system, a servo system, a sensor switch, a controller, and a host system. A simple introduction and relevant mechanical structures are referred to in the appendix Figure 2 :(1) The trailer recognition system includes a radar (camera). Before performing the hook action, it detects the state of the trailer towing triangular arm, and calculates the height deviation and angle deviation between the triangular arm and the tow hook through the host computer. (2) The servo system mainly includes servo electric cylinders and servo drivers that control the actions of the shovel-shaped guiding and horn-shaped guiding. They slide up and down according to the target position issued by the controller to adjust the guiding position. (3) The sensor switch of the in-place detection switch is a trigger type travel switch, which is used for the in-place detection of the trailer triangular arm and can provide the conditions for the hitching action. (4) The controller mainly performs data processing, sensor signal acquisition, and control functions such as issuing commands for the tow hook action. (5) The host system is used to process the fusion data of the radar or camera, etc., and is used to control the vehicle body to adjust its pose.

[0071] In addition, the embodiment of the present application also provides an adaptive automatic hook control system, as Figure 3 shown, the adaptive automatic hook control system 300 mainly includes: a vision sensor module 310, a shovel-shaped guiding electric cylinder module 320, a horn-shaped guiding electric cylinder module 330, an in-place detection switch 340, and a draw pin 350;

[0072] The vision sensor module 310 is used to identify the state of the trailer triangular arm of the towed trailer to obtain the pose state of the current trailer triangular arm;

[0073] The shovel-shaped guiding electric cylinder module 320 is used to control the lifting and / or lowering of the shovel-shaped guiding structure;

[0074] The horn-shaped guiding electric cylinder module 330 is used to control the lifting and / or lowering of the horn-shaped guiding structure;

[0075] The in-place detection switch 340 is used to detect and obtain the hook-in-place detection information;

[0076] The drawbar pin 350 is used to connect and fix the trailer triangular arm.

[0077] Through path planning based on the position of the towed trailer, the embodiments of the present application can ensure that the driverless tractor accurately reaches the predetermined hitch position during driving, improving the accuracy of operation. The determination of the automatic hitch position and the state recognition of the trailer triangular arm reduce manual intervention and improve the automation level of the driverless tractor operation. The pose state can also be quickly and accurately obtained, thus speeding up the hitch process and improving the overall operation efficiency. It helps to predict and adjust potential risks in the hitch process in advance, reduces the possibility of hitch failure, and enhances operation safety. It enables the driverless tractor and the automatic hitch system to adapt to different hitch environments and improves the adaptability of the system. The use of the hitch-in-place detection information can ensure the completion of the hitch action and avoid subsequent problems caused by insecure hitching. Through visual sensors and pose state analysis, hitch errors caused by visual errors or operator mistakes can be reduced.

[0078] Each embodiment in the present application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0079] The devices and media provided by the embodiments of the present application correspond one-to-one with the methods. Therefore, the devices and media also have beneficial technical effects similar to those of the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be elaborated here.

[0080] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0081] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, as well as the combination of flows and / or blocks in the flowchart and / or block diagram. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0082] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0084] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0085] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0086] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0088] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the specification of the present application.

Claims

1. An adaptive automatic hook control method, characterized in that, The method includes: Based on the position of the towed trailer, perform path planning for the driverless tractor and determine the pre - connection position of the driverless tractor; According to the pre - connection position, and through the vision sensor of the driverless tractor, identify the state of the trailer's triangular arm of the towed trailer to obtain the pose state of the current trailer's triangular arm; Perform spatial attitude analysis on the pose state to obtain the deviation space parameters of the current trailer's triangular arm; According to the deviation space parameters, perform adaptive adjustment control on the driverless tractor and the automatic hook system for connection to be made to obtain the vehicle control information of the driverless tractor; According to the vehicle control information, and based on the hook - in - place detection information, perform control adjustment on the automatic hook system for tow - able operation to obtain the information indicating the completion of automatic connection of the trailer.

2. The adaptive automatic hook control method according to claim 1, wherein, Based on the position of the towed trailer, perform path planning for the driverless tractor and determine the pre - connection position of the driverless tractor, specifically including: Based on the map location information of the towed trailer, determine the position of the towed trailer; Through the A* algorithm, perform global - planning topological structure processing on the current position node of the driverless tractor and the position of the towed trailer, and based on the reward function and the local restricted topological structure of dynamic obstacles, obtain the path - planning information in the obstacle - free area; According to the path - planning information, perform target - tracking control on the driverless tractor to determine the final position node of the driverless tractor; Determine the box - selected topological - knot area corresponding to the final position node as the pre - connection position; wherein, the final position node is the center point of the box - selected topological - knot area.

3. The adaptive automatic hook control method according to claim 1, characterized in that, According to the pre - connection position, and through the vision sensor of the driverless tractor, identify the state of the trailer's triangular arm of the towed trailer to obtain the pose state of the current trailer's triangular arm, specifically including: When the driverless tractor is at the pre - connection position, through the vision sensor, perform three - dimensional acquisition of image data of the trailer's triangular arm to obtain a three - dimensional image of the trailer's triangular arm; Perform edge - contour cropping processing on the three - dimensional image of the trailer's triangular arm, and based on the differential pixels of the front and back backgrounds, segment out the area map of the trailer's triangular arm; According to the preset three - dimensional shape template of the trailer's triangular arm, perform template - matching processing for type recognition on the area map of the trailer's triangular arm to determine the type map of the trailer's triangular arm; Perform fixed - pixel - position filling - judgment processing on the type map of the trailer's triangular arm for the connection state of the hitch pin to obtain the pixel - filling result information; If the pixel - filling result information indicates the existence of filled pixels, determine the pose state of the current trailer's triangular arm as a non - connectable pose; If the pixel - filling result information indicates the non - existence of filled pixels, determine the pose state of the current trailer's triangular arm as a connectable pose; Wherein, the pose state includes: the non - connectable pose and the connectable pose.

4. The adaptive automatic hook control method according to claim 1, characterized in that, Perform spatial attitude analysis on the pose state to obtain the deviation space parameters of the current trailer's triangular arm, specifically including: When the pose state is a connectable pose, extract the three - dimensional image of the trailer's triangular arm; Obtain the spatial position information of the towing pin of the automatic hook system in the driverless tractor; wherein, the spatial position information of the towing pin is the three-dimensional coordinates in space with the ground as the reference. Extract the spatial coordinates of the key points in the three-dimensional image of the trailer triangular arm to obtain the key point coordinates of the current trailer triangular arm; wherein, the key point coordinates are the three-dimensional coordinates in space with the ground as the reference. Calculate the deviation vector between the key point coordinates and the alignment point coordinates in the spatial position information of the towing pin to obtain the deviation vector information; wherein, the deviation vector information includes: deviation spatial distance information and deviation angle information. Determine the deviation vector information as the deviation spatial parameters of the current trailer triangular arm.

5. The adaptive automatic hook control method according to claim 1, wherein, Before performing adaptive adjustment control on the driverless tractor and the automatic hook system for connection based on the deviation spatial parameters to obtain the vehicle control information of the driverless tractor, the method further includes: Use lidar to identify the spatial positions of the pre-hooking position of the driverless tractor and the position of the hooked trailer, and respectively obtain the first frame coordinates of the driverless tractor and the second frame coordinates of the trailer triangular arm. Extract the coordinates of the automatic hook device corresponding to the automatic hook system in the first frame coordinates. Perform spatial simulation overlap calculation on the coordinates of the automatic hook device and the second frame coordinates to obtain the path deviation parameters of the driverless tractor. Perform parameter correction processing on the path deviation parameters through the deviation spatial parameters to obtain the local path control information of the driverless tractor; wherein, the local path control information includes: path interval distance information and horizontal offset distance information.

6. The adaptive automatic hook control method according to claim 5, characterized in that, Perform adaptive adjustment control on the driverless tractor and the automatic hook system for connection based on the deviation spatial parameters to obtain the vehicle control information of the driverless tractor, specifically including: Perform adaptive height adjustment control on the shovel-shaped guiding electric cylinder and the horn-shaped guiding electric cylinder in the automatic hook system according to the deviation spatial parameters to obtain the shovel-shaped guiding control parameters and the horn-shaped guiding control parameters. Combine the shovel-shaped guiding control parameters and the horn-shaped guiding control parameters into the device control information of the automatic hook system. Determine the execution time of the device control information as the first execution time, and the execution time of the local path control information as the second execution time; integrate the first execution time and the second execution time into the control information execution time strategy. Generate the vehicle control information of the driverless tractor based on the control information execution time strategy, the local path control information, and the device control information.

7. The adaptive automatic hook control method according to claim 1, characterized in that According to the vehicle control information and based on the hook-in-place detection information, perform control adjustment on the automatic hook system for towability to obtain the trailer automatic hook-up completion information, specifically including: When the execution of the vehicle control information is completed, detect and obtain the hook-in-place detection information through the in-place detection switch preset in the automatic hook system. Based on the hook-in-place detection information, perform parameter control adjustment on the shovel-shaped guiding electric cylinder and the horn-shaped guiding electric cylinder in a traction-enabled state to obtain secondary device control information; Based on the execution completion status of the secondary device control information, determine the hitch state information of the driverless towing vehicle as the trailer automatic hitch completion information.

8. The adaptive automatic hook control method according to claim 7, characterized in that The secondary device control information is used to perform lifting and / or lowering control on both the shovel-shaped guiding structure and the horn-shaped guiding structure in the automatic hook system, so that the driverless towing vehicle can complete the towing and driving of the attached trailer.

9. An adaptive automatic hook control system, characterized in that, The adaptive automatic hook control system mainly includes: a vision sensor module, a shovel-shaped guiding electric cylinder module, a horn-shaped guiding electric cylinder module, a in-place detection switch, and a drawbar pin; The vision sensor module is used to identify the state of the trailer triangular arm of the attached trailer to obtain the pose state of the current trailer triangular arm; The shovel-shaped guiding electric cylinder module is used to control the lifting and / or lowering of the shovel-shaped guiding structure; The horn-shaped guiding electric cylinder module is used to control the lifting and / or lowering of the horn-shaped guiding structure; The in-place detection switch is used to detect and obtain the hook-in-place detection information; The drawbar pin is used to connect and fix the trailer triangular arm.

10. A non-volatile computer storage medium, characterized in that, The storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, and each program includes instructions that, when executed by the terminal, cause the terminal to execute an adaptive automatic hook control method according to any one of claims 1-8.

Images