Method, device, equipment, and storage medium for pallet truck position identification

Abstract

This application discloses a method, device, and apparatus for identifying the position of a pallet truck. The method, device, and apparatus are applied to a tractor. The method first collects the pallet truck's position data, where the position data includes the pallet truck's boundary data. Secondly, based on the collected pallet truck boundary data, laser point cloud data of the pallet truck's boundary and within the boundary is obtained. Thirdly, based on the obtained laser point cloud data, feature data of a preset pallet component on the pallet truck is extracted. Finally, the position of the pallet truck's traction component is determined based on the pallet component's feature data. The technical solution of the present invention enables an autonomous tractor to accurately and automatically identify the position of the pallet truck's traction component, while also providing important assistance for subsequent tractors in achieving real-time decision-making and route planning.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to methods, devices, equipment, and storage media for position identification of pallet trucks. Background Art

[0002] Autonomous vehicles (AVs), also known as driverless cars, computer-driven cars, or wheeled mobile robots, are intelligent vehicles that are unmanned by computers. They rely on artificial intelligence, visual computing, radar, monitoring systems, and global positioning systems to enable computers to operate the vehicle safely and autonomously without any active human intervention.

[0003] With the development of unmanned driving technology, autonomous vehicles have also begun to be used in industry. Object recognition and road planning have become important components of environmental perception in the unmanned driving process, providing important auxiliary functions for unmanned driving scene perception, real-time decision-making, and route planning.

[0004] At present, autonomous driving object recognition mainly provides a reference for vehicle obstacle avoidance. There is no mature technology that can enable autonomous driving traction vehicles to automatically identify the position of the traction parts of pallet trucks and automatically lift them, including but not limited to traction vehicles used for airport baggage handling to automatically identify the position of the traction parts of pallet trucks and automatically lift them. Summary of the Invention

[0005] In response to the aforementioned issues, embodiments of the present application provide a method, apparatus, device, and storage medium for identifying the position of a pallet truck, including but not limited to airport baggage handling pallet trucks. This method, apparatus, and device are designed to detect the position of a pallet truck by a tractor and accurately identify its towing components, ultimately enabling automatic towing of the tractor and pallet truck. The technical solution provided by this application significantly improves the efficiency and accuracy of identifying the towing components of a tractor, demonstrating its practicality.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for identifying the position of a pallet truck, the method being applied to a tractor truck, the method comprising:

[0008] Collecting pallet truck position data, including pallet truck boundary data, wherein the position data is acquired by a visual sensor to provide a visual reference for subsequent processing;

[0009] Based on the pallet truck boundary data, laser point cloud data of the pallet truck boundary and within the boundary is obtained. The laser cloud point data here is obtained by a laser sensor, combined with the pallet truck boundary data obtained by the visual sensor, and processed to obtain laser point cloud data of the pallet truck boundary and within the boundary;

[0010] Extracting feature data of preset pallet components on the pallet truck based on the laser point cloud data, wherein the feature data is information of some feature points of the pallet truck, such as feature information of the pallet triangular arm, the pallet traction component, etc.;

[0011] The position of the pallet truck's towing component is determined based on the characteristic data of the pallet component, thereby enabling the identification of the pallet truck's position, particularly the pallet truck's towing component. Furthermore, by confirming the towing component's position information, the towing truck can make its own decisions, plan its route, and move toward the pallet truck. During the movement, the relative position of the towing truck and the towing component may change due to factors such as terrain and the environment. The towing truck will then automatically adjust its relative position information, thereby achieving automatic towing and hooking with the pallet truck.

[0012] Preferably, the tractor includes a visual sensor and a laser sensor. The visual sensor is used to obtain the position and boundary data of the pallet truck; the laser sensor is used to collect the laser point cloud data of the pallet truck boundary and the boundary, which is used as the data basis for subsequent automatic towing.

[0013] Preferably, the step of obtaining the boundary of the pallet truck and laser point cloud data within the boundary based on the boundary data of the pallet truck includes: obtaining the boundary image data of the pallet truck and the image data of the target area within the boundary according to the visual sensor, thereby providing a data basis for subsequently determining the position of the pallet truck; inputting the boundary image data of the pallet truck into a preset deep learning model to obtain the boundary data of the pallet truck; and obtaining the laser point cloud data within the boundary according to the image data of the target area within the boundary and the laser sensor.

[0014] Preferably, the laser point cloud data within the boundary is obtained by the laser sensor based on the image data of the target area within the boundary, including: obtaining two-dimensional boundary data based on the vehicle coordinate system according to the boundary image data of the pallet truck, and quantifying the data information obtained by the laser sensor according to the coordinate data; obtaining two-dimensional image data within a preset boundary range according to the image data of the target area within the boundary; and obtaining laser point cloud data of the target area within the boundary through the laser sensor based on the two-dimensional boundary data and the two-dimensional image data within the preset boundary range. The acquisition of the laser point cloud data of the target area enables the target to be quantified in a coordinate system based on the tractor, which facilitates the subsequent automatic towing.

[0015] Preferably, the laser point cloud data of the target area within the boundary is obtained by collecting the laser point cloud data by the laser sensor based on the two-dimensional boundary data and the two-dimensional image data within the preset boundary range, and further includes:

[0016] The laser point cloud data of the target area within the boundary of the current position of the pallet truck is obtained by cropping, wherein the laser point cloud data of the target area within the boundary includes the laser point cloud data of the pallet truck itself, which provides data support for subsequent automatic towing.

[0017] Preferably, the position of the traction component of the pallet truck based on the characteristic data of the pallet component is determined, including: extracting the characteristic points of the crossbeam on the side of the pallet truck on which the triangular arm is installed according to a preset filtering algorithm based on the laser point cloud data within the boundary; fitting the characteristic points according to a random sampling consistency algorithm to obtain fitting straight line data, that is, fitting according to the straight line characteristics of the crossbeam; obtaining fitting line segment data of the crossbeam on one side of the triangular arm of the pallet truck based on the fitting straight line data, wherein the line segment data is based on the tractor coordinate system and data information obtained by the laser sensor to obtain the endpoint information of the two end points of the crossbeam in the coordinate system; determining the midpoint coordinates and the slope of the line segment based on the fitting line segment data, and calculating the coordinates of the midpoint of the crossbeam and the slope of the line on which the crossbeam is located in the coordinate system according to the geometric algorithm; obtaining the heading angle of the vehicle based on the midpoint coordinates and the slope of the line segment, and the heading angle is based on the tractor coordinate system.

[0018] Preferably, after determining the position of the pallet truck's towing component based on the characteristic data of the pallet component, the method further includes: continuously calibrating the heading angle of the tractor vehicle as the tractor vehicle adjusts its course according to the heading angle to move toward the towing component, thereby achieving automatic towing of the tractor vehicle and the pallet truck. As the tractor vehicle moves toward the pallet truck, the relative positions of the tractor vehicle and the towing component may change due to terrain, environmental factors, and other factors. The tractor vehicle continuously updates its heading angle information as it adjusts its relative position information, thereby achieving automatic towing of the tractor vehicle and the pallet truck.

[0019] According to a second aspect of the present application, an embodiment of the present application further provides a position identification device for a pallet truck, the device being applied to a tractor truck, the device comprising:

[0020] Data acquisition module, used to obtain pallet truck boundary data and laser point cloud data;

[0021] The boundary determination module is used to process the acquired pallet truck boundary data and laser point cloud data to obtain the pallet truck boundary and the laser point cloud data within the boundary.

[0022] A feature extraction module, configured to extract feature data of a preset pallet component on the pallet truck based on the laser point cloud data;

[0023] The component position confirmation module is used to determine the position of the pallet truck traction component according to the characteristic information of the pallet component.

[0024] Through the coordinated execution of the above modules, the tractor can accurately identify the position of the towing part. The tractor makes its own decisions, plans the route, and moves towards the pallet truck. During the movement, due to terrain, environment and other factors, the relative position of the tractor and the towing parts may change. The tractor adjusts the relative position information by itself, thereby realizing automatic towing with the pallet truck.

[0025] According to a third aspect of the present application, an embodiment of the present application further provides a device for identifying the position of a pallet truck. The device comprises: a memory, a processor, and a program for identifying the position of a pallet truck stored and running on the processor. When the program for identifying the position of a pallet truck is executed by the processor, the following method is implemented:

[0026] First, the tractor's visual sensor collects the pallet truck's position data, including the pallet truck's boundary data. The position data is acquired by the visual sensor to provide a visual reference for subsequent processing.

[0027] Secondly, based on the pallet truck boundary data, laser point cloud data of the pallet truck boundary and within the boundary is obtained. The laser cloud point data here is obtained by a laser sensor, combined with the pallet truck boundary data obtained by the visual sensor, and processed to obtain laser point cloud data of the pallet truck boundary and within the boundary;

[0028] Thirdly, based on the laser point cloud data, feature data of the preset pallet components on the pallet truck are extracted, where the feature data is information of some feature points of the pallet truck, such as feature information of the pallet triangular arm, the pallet traction component, etc.;

[0029] Finally, the position of the traction component of the pallet truck is determined based on the characteristic data of the pallet component. By confirming the position information of the traction component, the tractor can make its own decisions, plan the route, and move towards the pallet truck. During the movement, due to terrain, environment and other factors, the relative position of the tractor and the traction component may change. The tractor adjusts the relative position information by itself, thereby realizing automatic towing with the pallet truck.

[0030] According to another aspect of the present application, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program for detecting and identifying a position of a pallet truck. When the program for detecting and identifying a position of a pallet truck is executed by a processor, any of the following methods is implemented:

[0031] First, the tractor's visual sensor collects the pallet truck's position data, including the pallet truck's boundary data. The position data is acquired by the visual sensor to provide a visual reference for subsequent processing.

[0032] Secondly, based on the pallet truck boundary data, laser point cloud data of the pallet truck boundary and within the boundary is obtained. The laser cloud point data here is obtained by a laser sensor, combined with the pallet truck boundary data obtained by the visual sensor, and processed to obtain laser point cloud data of the pallet truck boundary and within the boundary;

[0033] Thirdly, based on the laser point cloud data, feature data of the preset pallet components on the pallet truck are extracted, where the feature data is information of some feature points of the pallet truck, such as feature information of the pallet triangular arm, the pallet traction component, etc.;

[0034] Finally, the position of the traction component of the pallet truck is determined based on the characteristic data of the pallet component. By confirming the position information of the traction component, the tractor can make its own decisions, plan the route, and move towards the pallet truck. During the movement, due to terrain, environment and other factors, the relative position of the tractor and the traction component may change. The tractor adjusts the relative position information by itself, thereby realizing automatic towing with the pallet truck.

[0035] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0036] Because the present application uses the mutual cooperation of visual sensors and laser sensors, the tractor can obtain the visual information and feature information of the pallet truck, extract the feature points of the crossbeam on one side of the triangular arm installed on the pallet truck through a preset filtering algorithm, fit the feature points through a consistency algorithm to obtain fitting straight line data, and further process to obtain the heading angle; the tractor can make its own decisions, plan the route, and move towards the pallet truck. During the movement, due to the terrain, environment, and other reasons, the relative position of the tractor and the traction components may change. The tractor adjusts the relative position information and recalculates the heading angle, thereby realizing automatic towing with the pallet truck. This method can accurately obtain the information of the traction components of the pallet truck, realize automatic towing of the tractor and the pallet truck, and adapt to various terrains and environments, improve recognition efficiency, and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0038] Figure 1 This is a flow chart of a method for identifying the position of a pallet truck according to an example of this application;

[0039] Figure 2 This is a schematic diagram of the structure of a position identification device for a pallet truck according to an example of this application;

[0040] Figure 3A diagram showing the relationship between the components of a position identification device for a pallet truck according to an example of this application;

[0041] Figure 4 This is a schematic diagram of the heading angle of the device for identifying the position of a pallet truck according to an example of this application;

[0042] Figure 5 This is a schematic diagram of a position identification system for a pallet truck according to an example of this application. DETAILED DESCRIPTION

[0043] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0044] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0045] The embodiment of the present application provides a method for identifying the position of a pallet truck, which is applied to the fields of machine vision and autonomous driving, especially for accurately identifying a pallet truck by an airport tractor to realize automatic towing of the tractor and the pallet truck. Figure 1 As shown, a flow chart of an embodiment of the present application is provided, wherein the method at least includes the following steps S101 to S104:

[0046] Step S101 : collecting position data of a pallet truck, wherein the position data includes boundary data of the pallet truck.

[0047] In some examples of the present application, the tractor obtains raw data from the on-board visual sensor and laser sensor; the visual sensor automatically obtains the pallet truck position boundary data based on deep learning, wherein the pallet truck position boundary data is two-dimensional boundary data containing (x, y) based on the vehicle coordinate system, and the origin of the vehicle coordinate system is on the ground, below the midpoint of the rear axle, below the longitudinal and lateral centers of the vehicle, that is, the center of mass of the vehicle. The direction of vehicle movement is the x-axis direction, and the left side of the vehicle perpendicular to the x-axis is the y-axis direction. The position information in the vehicle coordinate system is expressed in world units. The values returned by the sensor are converted to the vehicle coordinate system so that they can be placed in a unified reference coordinate, and the steering angle of the vehicle is positive in the counterclockwise direction. This boundary data can be used to define the boundary of the effective point cloud extracted by the laser sensor.

[0048] Step S102, based on the pallet truck boundary data, obtaining the laser point cloud data of the pallet truck boundary and the boundary;

[0049] Based on the pallet truck boundary data obtained by the visual sensor, the laser point cloud data within the pallet truck boundary is obtained using but not limited to the CropBox algorithm. This laser point cloud data includes the point cloud data of the pallet truck itself; based on the two-dimensional boundary data containing (x, y) in the vehicle coordinate system, two-dimensional range filtering is used to extract the point cloud data of the laser sensor within the pallet truck boundary range.

[0050] Step S103: extracting feature data of preset pallet components on the pallet truck based on the laser point cloud data.

[0051] Based on the laser point cloud data within the boundary of the pallet truck, the feature points on the side of the pallet truck where the traction component is installed are extracted by using, but not limited to, the passthrough filter algorithm. The traction component has different structures according to the characteristics of the pallet truck. The feature points on the side of the traction component are the parts that can be fitted into a straight line based on the outline of the pallet truck. In this example, Figure 3 As shown, the laser sensor of the tractor 100 extracts the characteristic points of the crossbeam 2 on one side of the triangular arm 1 of the pallet truck 200, and performs straight line fitting on the characteristic points to obtain the fitting line segment 3, as shown in FIG. Figure 4 As shown, the position of the crossbeam 2 on the side where the triangular arm 1 is installed is represented by a fitted straight line. According to the order of the laser point cloud in the y direction of the vehicle coordinate system, the maximum and minimum points of the fitted line segment 3 in the y direction are obtained, and then the coordinates of the two end points of the line segment 3, p1 (x1, y1) and p2 (x2, y2), are obtained. The origin of the vehicle coordinate system is on the ground, below the midpoint of the rear axle. The direction of the vehicle's movement is the x-axis direction, and the left side of the vehicle, perpendicular to the x-axis, is the y-axis direction. The values returned by the sensor are converted to the vehicle coordinate system so that they can be placed in a unified reference coordinate system. The extracted feature points of the crossbeam 2 on the side where the triangular arm 1 is installed on the pallet truck are based on the laser point cloud data. The feature point data is extracted and converted to the vehicle coordinate system.

[0052] Step S104: determining the position of the traction component of the pallet truck according to the characteristic data of the pallet component.

[0053] Based on the data for line segment 3 acquired in step S103, the coordinates p0 (x0, y0) of the midpoint of crossbeam 2 on the side of the pallet truck where jib 1 is mounted are calculated. The slope of line segment 3 in the vehicle coordinate system is calculated based on p1 and p2. The heading angle θ of crossbeam 2 on the side of the pallet truck where jib 1 is mounted can be calculated for subsequent automatic towing. Using the laser point cloud data of the characteristic components, the precise position of the pallet truck's towing components can be automatically determined based on the vehicle coordinate system.

[0054] In summary, traditional autonomous vehicles rely solely on visual sensors to identify objects and obtain the relative position of the vehicle and objects for obstacle avoidance. However, the present application combines visual sensors with laser sensors to not only obtain the relative position of the tractor to the pallet truck, but also the precise position based on the vehicle coordinate system. Through feature point extraction and line fitting, the vehicle's heading angle and precise information about the towing components can be accurately determined. This improves the efficiency of identifying the position of pallet trucks, especially the towing components of pallet trucks, and enhances the user experience.

[0055] In this application example, the tractor includes a visual sensor and a laser sensor. The visual sensor is used to obtain the location and boundary data of the pallet truck, while the laser sensor is used to collect laser point cloud data of the pallet truck boundary and the area within the boundary. The visual sensor and laser sensor provide raw data for subsequent processing.

[0056] In the examples of this application, based on the pallet truck boundary data acquired by the visual sensor and the laser point cloud data acquired by the laser sensor, the laser point cloud data of the pallet truck boundary and within the boundary is acquired. This includes acquiring the pallet truck boundary image data and image data of the target area within the boundary, including the pallet truck's structural data and feature point data, using the visual sensor. The pallet truck boundary image data is then input into a preset deep learning model to acquire the pallet truck boundary data and the pallet truck's boundary contour data. Thereafter, based on the image data of the target area within the boundary and the laser sensor, laser point cloud data within the boundary is acquired. The data primarily includes feature data of the pallet truck's characteristic components. The boundary and within-boundary laser point cloud data acquired in this process are primarily used for subsequent extraction of the pallet truck boundary and pallet truck feature information.

[0057] In the example of the present application, image data of the target area within the boundary is obtained by the visual sensor, and laser point cloud data within the boundary is obtained by the laser sensor, including obtaining two-dimensional boundary data containing (x, y) based on the vehicle coordinate system according to the boundary image data of the pallet truck, and adopting two-dimensional range filtering; then, two-dimensional image data within a preset boundary range is obtained according to the image data of the target area within the boundary; thereafter, based on the two-dimensional boundary data and the two-dimensional image data within the preset boundary range, laser point cloud data of the target area within the boundary is acquired by the laser sensor.

[0058] In the example of the present application, based on two-dimensional boundary data and two-dimensional image data within a preset boundary range, laser point cloud data of the target area within the boundary is obtained by collecting data through a laser sensor. It also includes obtaining laser point cloud data of the target area within the boundary of the current position of the pallet truck by cropping, wherein the laser point cloud data of the target area within the boundary includes the laser point cloud data of the pallet truck itself, and its main function is to extract feature point information of the pallet truck.

[0059] In the example of the present application, the position of the traction component of the pallet truck is determined according to the characteristic data of the pallet component, including extracting the characteristic points of the crossbeam 2 on the side where the pallet truck is installed with the triangular arm 1 based on the laser point cloud data within the boundary by using but not limited to the passthrough filter algorithm, such as Figure 3 As shown. According to the random sampling consistency algorithm, the feature points are fitted to obtain the fitted straight line data. Here, the fitted straight line is used to represent the position of the crossbeam 2 on the side where the triangular arm 1 is installed. According to the sorting of the laser point cloud in the y dimension, the maximum and minimum points in the y direction are obtained, and then the coordinates of the two end points p1 (x1, y1) and p2 (x2, y2) of the straight line segment 3 are obtained. Among them, the feature points of the crossbeam 2 on the side where the triangular arm 1 is installed on the pallet truck are extracted based on the vehicle coordinate system. According to the fitted line segment data, the midpoint coordinates of the line segment and the slope of the line segment are determined, that is, according to the obtained data of the line segment 3, the midpoint coordinates p0 (x0, y0) of the crossbeam 2 on the side where the triangular arm 1 is installed on the pallet truck are calculated, and the slope of the straight line segment 3 in the vehicle coordinate system is obtained according to p1 and p2; the heading angle of the vehicle is obtained according to the midpoint coordinates of the line segment and the slope of the line segment, that is, the slope of the straight line segment 3 in the vehicle coordinate system is obtained according to p1 and p2. The heading angle θ of the crossbeam 2 on the side where the triangular arm 1 is installed on the pallet truck can be calculated for subsequent automatic towing.

[0060] In the example of the present application, after determining the position of the pallet truck traction component based on the characteristic data of the pallet component, it also includes the tractor adjusting the vehicle to move to the traction component according to the heading angle θ. During the movement, the tractor continuously calibrates the heading angle θ to achieve automatic towing of the vehicle and the pallet truck.

[0061] According to an embodiment of the present application, a position identification device 200 for a pallet truck is provided. Figure 2 As shown, the device 200 at least includes: a data acquisition module 201, a boundary determination module 202, a feature extraction module 203, and a component position confirmation module 204, wherein:

[0062] Data acquisition module 201, the tractor obtains raw data from the on-board visual sensor and laser sensor; the visual sensor automatically obtains the pallet truck position boundary data based on deep learning, where the pallet truck position boundary data is based on the two-dimensional boundary data containing (x, y) in the vehicle coordinate system. This boundary data can be used by the laser sensor to extract the effective point cloud to define the boundary.

[0063] The boundary determination module 202 obtains the boundary value of the pallet truck obtained by the visual sensor and obtains the laser point cloud data within the boundary of the pallet truck position by using but not limited to the cropbox algorithm. This laser point cloud data includes the point cloud data of the pallet truck itself; based on the two-dimensional boundary data containing (x, y) in the vehicle coordinate system, two-dimensional range filtering is used to extract the point cloud data of the laser sensor within the boundary range.

[0064] The feature extraction module 203 extracts the feature points of the crossbeam 2 on the side where the triangular arm 1 is installed on the pallet truck based on the laser point cloud data within the boundary by using but not limited to the passthrough filter algorithm; wherein, the feature points are fitted with a straight line to obtain the data of the fitted straight line segment 3, and the fitted straight line is used to represent the position of the crossbeam 2 on the side where the triangular arm 1 is installed. According to the sorting of the laser point cloud in the y dimension, the maximum point and the minimum point in the y direction are obtained, and then the coordinates p1 (x1, y1) and p2 (x2, y2) of the two end points of the straight line segment 3 are obtained. The extracted feature points of the crossbeam 2 on the side where the triangular arm 1 is installed on the pallet truck are based on the vehicle coordinate system.

[0065] The component position confirmation module 204 calculates the coordinates p0 (x0, y0) of the midpoint of the crossbeam 2 on the side where the pallet truck is installed with the triangular arm 1, based on the line segment 3 data obtained in the feature extraction module. Figure 3 As shown. Based on p1 and p2, the slope of the straight line segment 3 in the vehicle coordinate system can be calculated, and the heading angle θ of the crossbeam 2 on the side where the pallet truck is installed with the triangular arm 1 can be calculated, as shown in the figure below. Figure 4 As shown. This is used for subsequent automatic towing. Using the laser point cloud data of characteristic components and based on the vehicle coordinate system, the precise position of the pallet truck towing component can be automatically determined.

[0066] In summary, through the combined processing of the above four modules in this application, not only the relative position of the tractor to the pallet truck can be obtained, but also the precise position based on the vehicle coordinate system can be obtained. Through feature point extraction and straight line fitting, the vehicle's heading angle and the precise information of the traction components can be accurately determined, which improves the recognition efficiency of the pallet truck, especially the traction components of the pallet truck, and improves the user experience.

[0067] Schematic diagram of the sensor installation locations for the pallet truck position identification device in this application example. Because the relative positions of the tractor and pallet truck cannot be determined in the initial state, visual sensors and laser sensors are installed in at least four directions on the tractor to confirm their relative positions and the locations of their characteristic components. To better achieve accurate identification of the pallet truck's position in this application, the number and location of the visual sensors can be adjusted according to actual needs.

[0068] In other embodiments of the present application, after a tractor recognizes the position of a pallet truck, particularly its towing components, and confirms its heading angle, it makes its own decisions and plans its route based on the acquired data, adjusting the tractor's movement toward the pallet truck, thereby enabling automatic towing of the tractor and pallet truck. During the tractor's movement, the heading angle may vary due to road conditions. The pallet truck position recognition device automatically adjusts the heading angle according to the method described in Example 1, thereby enabling automatic towing of the tractor and pallet truck. This improves towing accuracy and efficiency, and enhances the user experience.

[0069] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions for pallet truck position identification and detection can also be stored in a computer readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which is implemented in the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0073] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0074] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0075] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The 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 disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic 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 transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0076] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, commodity, or apparatus that includes the element.

[0077] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] The foregoing is merely 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 modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

[0079] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement the embodiments.

[0080] According to the embodiments of the present application, some or all of the functions of some or all of the components of the pallet truck position identification and detection device. The present application can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for performing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0081] For example, Figure 5 The present invention illustrates a device for identifying the location of a pallet truck according to one embodiment of the present invention. The pallet truck location identification device 500 includes a processor 501 and a memory 502 configured to store computer-executable instructions (computer-readable program code). The memory 502 can be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk, or a ROM. The memory 502 has a storage space 5021 for storing computer-readable program code 50211 for executing any of the method steps described above. For example, the storage space 5021 for storing computer-readable program code can include individual computer-readable program codes 50211 for implementing various steps in the method described above. The computer-readable program code 5021 can be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a compact disk (CD), a memory card, or a floppy disk. The computer-readable program code 50211 can be compressed in any suitable format.

[0082] It should be noted that the above embodiments illustrate rather than limit the present application, and that a person skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbols placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A method for identifying the position of a pallet truck, characterized in that: The method is applied to a tractor, and comprises: Collecting pallet truck position data, wherein the position data includes pallet truck boundary data; Based on the pallet truck boundary data, obtaining laser point cloud data of the pallet truck boundary and within the boundary; Extracting feature data of a preset pallet component on the pallet truck based on the laser point cloud data; determining the position of the traction component of the pallet truck according to the characteristic data of the pallet component; The determining the position of the traction component of the pallet truck according to the characteristic data of the pallet component includes: Extracting feature points of the crossbeam on one side of the pallet truck where the triangular arm is installed based on the laser point cloud data within the boundary according to a preset filtering algorithm; Fitting the characteristic points according to a random sampling consistency algorithm to obtain fitting straight line data; According to the fitted straight line data, the fitted line segment data of the crossbeam on one side of the triangular arm of the pallet truck is obtained; Determine the midpoint coordinates and the slope of the line segment according to the fitted line segment data; The vehicle heading angle is obtained according to the midpoint coordinates of the line segment and the slope of the line segment.

2. The method according to claim 1, wherein The tractor includes a visual sensor and a laser sensor. The visual sensor is used to obtain the position and boundary data of the pallet truck; The laser sensor is used to collect laser point cloud data of the pallet truck boundary and within the boundary.

3. The method according to claim 2, wherein The step of obtaining the laser point cloud data of the pallet truck boundary and the boundary thereof based on the pallet truck boundary data includes: Acquire the boundary image data of the pallet truck and the image data of the target area within the boundary according to the visual sensor; Inputting the pallet truck boundary image data into a preset deep learning model to obtain the pallet truck boundary data; The laser sensor acquires laser point cloud data within the boundary based on the image data of the target area within the boundary.

4. The method according to claim 3, wherein The step of acquiring laser point cloud data within the boundary using the laser sensor based on the image data of the target area within the boundary includes: Obtaining two-dimensional boundary data based on the vehicle coordinate system according to the pallet truck boundary image data; Obtaining two-dimensional image data within a preset boundary range based on the image data of the target area within the boundary; Based on the two-dimensional boundary data and the two-dimensional image data within the preset boundary range, laser point cloud data of the target area within the boundary is acquired by collecting through the laser sensor.

5. The method according to claim 4, wherein The laser point cloud data of the target area within the boundary is obtained by collecting the laser point cloud data by the laser sensor based on the two-dimensional boundary data and the two-dimensional image data within the preset boundary range, further comprising: The laser point cloud data of the target area within the boundary of the current position of the pallet truck is obtained by clipping, wherein the laser point cloud data of the target area within the boundary includes the laser point cloud data of the pallet truck itself.

6. The method according to claim 1, wherein After determining the position of the traction component of the pallet truck according to the characteristic data of the pallet component, the method further includes: When the self-vehicle adjusts the vehicle according to the heading angle and moves to the towing component, the self-vehicle continuously calibrates the heading angle to achieve automatic towing of the self-vehicle and the pallet truck.

7. A pallet truck position identification device, characterized in that: The device is applied to a tractor, and comprises: Data acquisition module, used to obtain pallet truck boundary data and laser point cloud data; A boundary determination module is used to process the acquired pallet truck boundary data and laser point cloud data to obtain the pallet truck boundary and the laser point cloud data within the boundary; A feature extraction module, configured to extract feature data of a preset pallet component on the pallet truck based on the laser point cloud data; A component position confirmation module, configured to determine the position of the pallet truck traction component based on characteristic information of the pallet component; The determining the position of the traction component of the pallet truck according to the characteristic data of the pallet component includes: Extracting feature points of the crossbeam on one side of the pallet truck where the triangular arm is installed based on the laser point cloud data within the boundary according to a preset filtering algorithm; Fitting the characteristic points according to a random sampling consistency algorithm to obtain fitting straight line data; According to the fitted straight line data, the fitted line segment data of the crossbeam on one side of the triangular arm of the pallet truck is obtained; Determine the midpoint coordinates and the slope of the line segment according to the fitted line segment data; The vehicle heading angle is obtained according to the midpoint coordinates of the line segment and the slope of the line segment.

8. A pallet truck position identification device, characterized in that: The device for identifying the position of a pallet truck comprises: a memory, a processor, and a program for identifying the position of a pallet truck stored and running on the processor. When the program for identifying the position of a pallet truck is executed by the processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program for identifying and detecting the position of a pallet truck. When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images