Truss robot automatic loading and unloading vehicle intelligent control method and system and truss robot

Abstract

The present application belongs to the field of transportation technology, and provides a truss robot automatic loading and unloading vehicle intelligent control method and system and a truss robot, the technical scheme is a loading control process and an unloading control process, when loading and unloading, through top 3D image visual detection and additional side 3D image visual detection, the truss robot is guided to accurately and quickly grab or fork, ensuring the safe loading and unloading of equipment and goods, when path planning, according to the loading and unloading planning scheme and the material fork position, the loading and unloading carrying path is planned, and all materials are unloaded according to the loading and unloading carrying path, specifically including: determining the position of the material carrying starting point and the end point in the loading and unloading track planning, calculating the three-dimensional safety distance in the material carrying process, combining the three-dimensional safety distance to determine the material taking track, the material carrying section track and the material placing track, and combining the material taking section track, the material carrying section track and the material placing track to draw a complete carrying track.

Description

Technical Field

[0001] This invention belongs to the field of gantry robot technology, and particularly relates to intelligent control methods, systems and gantry robots for automatic loading and unloading. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Currently, gantry robots typically use top-mounted LiDAR to pre-scan the loading / unloading area during loading and unloading. The scan results then determine the loading / unloading position, guiding the robot accordingly. This laser scanning guidance method requires relative movement between the laser and the truck, which is time-consuming and significantly impacts loading / unloading efficiency. Furthermore, this method lacks process monitoring; if any discrepancies occur in the cargo's position during loading / unloading, the gantry robot cannot detect them in time, posing a risk of equipment or cargo damage. Additionally, existing loading and unloading routes do not consider potential damage to materials at various stages of transport, failing to guarantee the integrity of the materials after handling. Summary of the Invention

[0004] To address at least one of the technical problems mentioned above, this invention provides an intelligent control method, system, and gantry robot for automated loading and unloading of gantry robots. By combining top 3D image visual detection with side 3D image visual detection, the gantry robot is guided to perform precise and rapid gripping or forking, ensuring the safe loading and unloading of equipment and goods.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides an intelligent control method for automatic loading of a gantry robot, comprising the following steps: Based on the acquired top-scan image, the loading compartment is detected to obtain the position and size information of the loading compartment; Based on the inspection results of the carriages, a loading plan is generated; Based on the acquired side-scan material 3D point cloud data, the material picking position is identified; Based on the loading plan and the location of the material forklift, the loading and handling path is planned. The gantry robot is controlled to complete the loading of the entire vehicle of materials according to the planned loading and handling path. Specifically, this includes: determining the starting and ending points of the material handling in the loading trajectory plan, calculating the three-dimensional safety distance during the material handling process, determining the material removal trajectory, the material handling section trajectory, and the material placement trajectory based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, the material handling section trajectory, and the material placement trajectory.

[0006] Furthermore, the detection of the loading compartment based on the acquired top-scan image to obtain the position and size information of the loading compartment includes: Initialize the carriage position detection algorithm and load its parameters; Acquire two-dimensional image data, and preprocess the acquired two-dimensional image data to obtain a preprocessed image; The preprocessed image is input into the carriage position detection algorithm, which outputs the three-dimensional coordinate information of the four corners of the carriage; The three-dimensional coordinate information of the output carriage is transformed by a rotation matrix to output the vehicle's coordinates in the world coordinate system. The dimensions and height of the carriage are calculated using the coordinate information of the four corners of the carriage.

[0007] Furthermore, the identification of the material pick-up position based on the acquired side-scanned 3D point cloud data includes: Initialize the material forklift position detection algorithm and load the parameters of the material forklift position detection algorithm; Two-dimensional image data and 3D point cloud image data are acquired respectively. The image data is preprocessed to obtain a format suitable for the material forklift position detection algorithm. The preprocessed image is input into the material forklift position detection algorithm. If the position detection is successful, the material forklift position is obtained. If the detection fails, the camera is moved appropriately by the material execution structure to continue collecting data and detecting until the material forklift position is obtained.

[0008] Furthermore, based on the inspection results of the carriage, a loading plan is generated, including the determination of the arrangement of materials loading and the order of loading and placement.

[0009] Furthermore, the three-dimensional safety zone during material handling is a cylinder centered on the Z-axis of the forklift's end, with a radius of... ,in, d This is a reserved safety distance. It is the maximum rotation radius at the end of the truss. The maximum rotation radius is calculated based on the size of the forklift end when the forklift end is unloaded, and based on the size of the loaded material and the size of the forklift end when fully loaded.

[0010] A second aspect of the present invention provides an intelligent control method for automatic unloading of a gantry robot, comprising the following steps: Material detection is performed based on the acquired top scan image to obtain the material detection results; Based on the material inspection results, an unloading plan is generated; Based on the acquired side-scan material 3D point cloud data, the material picking position is identified; Based on the unloading plan and the location of the material forklift, the unloading and handling path is planned. The gantry robot is controlled to complete the unloading of all materials according to the unloading and handling path. Specifically, this includes: determining the starting and ending points of the material handling in the unloading trajectory plan, calculating the three-dimensional safety distance during the material handling process, determining the material removal trajectory, the material handling section trajectory, and the material placement trajectory based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, the material handling section trajectory, and the material placement trajectory.

[0011] Furthermore, the step of generating an unloading plan based on the material inspection results includes: the position coordinates of the materials in the truck bed, determining the direction of unloading the materials, and arranging the order of unloading the materials.

[0012] Furthermore, the identification of the material pick-up position based on the acquired side-scanned 3D point cloud data includes: Initialize the material forklift position detection algorithm and load the parameters of the material forklift position detection algorithm; Two-dimensional image data and 3D point cloud image data are acquired respectively. The image data is preprocessed to obtain a format suitable for the material forklift position detection algorithm. The preprocessed image is input into the material forklift position detection algorithm. If the position detection is successful, the material forklift position is obtained. If the detection fails, the camera is moved appropriately by the material execution structure to continue collecting data and detecting until the material forklift position is obtained.

[0013] A third aspect of the present invention provides an intelligent control method for automatic loading and unloading of gantry robots, comprising: a loading control process and an unloading control process; The loading control process includes: Based on the acquired top-scan image, the loading compartment is detected to obtain the position and size information of the loading compartment; Based on the inspection results of the carriages, a loading plan is generated; Based on the acquired side-scan material 3D point cloud data, the material picking position is identified; Based on the loading plan and the location of the material forklift, a loading and handling path is planned. The gantry robot is then controlled to complete the loading of the entire vehicle of materials according to the planned loading and handling path. Specifically, this includes: determining the starting and ending points of the material handling in the loading trajectory plan; calculating the three-dimensional safety distance during the material handling process; determining the material removal trajectory, the material handling section trajectory, and the material placement trajectory based on the three-dimensional safety distance; and drawing a complete handling trajectory by combining the material removal section trajectory, the material handling section trajectory, and the material placement trajectory. The unloading control process includes: Material detection is performed based on the acquired top scan image to obtain information on the location, size, and quantity of the material; Based on the material inspection results, an unloading plan is generated; Based on the acquired side-scan material 3D point cloud data, the material picking position is identified; Based on the unloading plan and the location of the material forklift, the unloading and handling path is planned. The gantry robot is controlled to complete the unloading of all materials according to the unloading and handling path. Specifically, this includes: determining the starting and ending points of the material handling in the unloading trajectory plan, calculating the three-dimensional safety distance during the material handling process, determining the material removal trajectory, the material handling section trajectory, and the material placement trajectory based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, the material handling section trajectory, and the material placement trajectory.

[0014] A fourth aspect of the present invention provides an intelligent control system for automated loading of gantry robots, comprising: The carriage detection module is used to detect the loading carriage based on the acquired top scan image, and obtain the position and size information of the loading carriage; The loading planning module is used to generate loading planning schemes based on the inspection results of the wagon compartments; The forklift position detection module is used to identify the forklift position of the material based on the acquired side-scan material 3D point cloud data. The loading path planning module is used to plan the loading and handling path according to the loading plan and the material forklift position. It controls the gantry robot to complete the loading of the entire vehicle of materials according to the planned loading and handling path. Specifically, it includes: determining the starting and ending points of material handling in the loading trajectory planning, calculating the three-dimensional safety distance in the material handling process, determining the material removal trajectory, material handling section trajectory and material placement trajectory respectively based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, material handling section trajectory and material placement trajectory.

[0015] A fifth aspect of the present invention provides an intelligent control system for automated unloading of gantry robots, comprising: The material inspection module is used to inspect materials based on the acquired top scan image and obtain the material inspection results; The unloading planning module is used to generate unloading planning schemes based on the material inspection results. The forklift position detection module is used to identify the forklift position of the material based on the acquired side-scan material 3D point cloud data. The unloading path planning module is used to plan the unloading and handling path based on the unloading plan and the material forklift position. It controls the gantry robot to complete the unloading of all materials according to the unloading and handling path. Specifically, it includes: determining the starting and ending points of material handling in the unloading trajectory planning, calculating the three-dimensional safety distance during the material handling process, determining the material removal trajectory, material handling section trajectory and material placement trajectory based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, material handling section trajectory and material placement trajectory.

[0016] A sixth aspect of the present invention provides an automated loading and unloading system for a gantry robot, comprising a loading control module and an unloading control module; The loading control module is configured to: detect the loading compartment based on the acquired top-scan image to obtain the position and size information of the loading compartment; generate a loading planning scheme based on the compartment detection results; identify the material forklift position based on the acquired side-scan material 3D point cloud data; plan the loading and handling path according to the loading planning scheme and the material forklift position; and control the gantry robot to complete the loading of the entire vehicle of materials according to the planned loading and handling path. Specifically, this includes: determining the positions of the starting point and ending point of material handling in the loading trajectory planning; calculating the three-dimensional safety distance during the material handling process; determining the material removal trajectory, material handling segment trajectory, and material placement trajectory based on the three-dimensional safety distance; and drawing a complete handling trajectory by combining the material removal segment trajectory, material handling segment trajectory, and material placement trajectory. The unloading control module is configured to: perform material detection based on the acquired top-scan image to obtain the position, size, and quantity information of the material; generate an unloading planning scheme based on the material detection results; identify the material forklift position based on the acquired side-scan material 3D point cloud data; plan the unloading and handling path according to the unloading planning scheme and the material forklift position; and control the gantry robot to complete the unloading of all materials according to the unloading and handling path. Specifically, this includes: determining the positions of the material handling start point and end point in the unloading trajectory planning; calculating the three-dimensional safety distance during the material handling process; determining the material removal trajectory, material handling segment trajectory, and material placement trajectory based on the three-dimensional safety distance; and drawing a complete handling trajectory by combining the material removal segment trajectory, material handling segment trajectory, and material placement trajectory.

[0017] A seventh aspect of the present invention provides a gantry robot, including the intelligent control system for automatic loading and unloading of the gantry robot described in the sixth aspect.

[0018] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention innovatively proposes an automatic loading and unloading technology based on image visual detection. It develops an automatic loading and unloading system based on image visual detection, which guides a gantry robot to perform precise and rapid grasping or forking through top 3D image visual detection and additional side 3D image visual detection, ensuring the safe loading and unloading of equipment and goods, solving the problem of equipment or goods damage risk, and improving the efficiency of loading and unloading.

[0019] 2. This invention innovatively proposes a planning method for loading and unloading vehicle transport paths. By combining three-dimensional safety distances, the material retrieval trajectory, the material transport section trajectory, and the material placement trajectory are determined separately. A complete transport trajectory is then drawn by combining these three trajectories. This ensures the integrity of the materials after transport and prevents potential damage to the materials at any stage of the transport process.

[0020] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0021] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0022] Figure 1 This is a flowchart of the automatic loading method for gantry robots provided in an embodiment of the present invention; Figure 2 This is a flowchart of the outbound top-scanning process provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of material loading planning provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the loading route planning provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the construction of a three-dimensional security area provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the trajectory path between transition points provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the optimized safe handling trajectory provided in the embodiments of the present invention; Figure 8 This is a flowchart of the automatic unloading method for a gantry robot provided in an embodiment of the present invention; Figure 9 This is a flowchart of the top-scanning process for warehousing provided in an embodiment of the present invention; Figure 10 This is a schematic diagram of the material unloading plan provided in an embodiment of the present invention; Figure 11This is a schematic diagram of unloading route planning provided in an embodiment of the present invention. Detailed Implementation

[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0025] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0026] Example 1 like Figure 1 As shown, this embodiment provides an intelligent control method for automatic loading of a gantry robot, including the following steps: In the loading and unloading of materials, such as power materials, gantry robots use AI technology to achieve accurate object recognition and environmental perception. Gantry robots can use multimodal sensors to monitor and collect data on the site environment in real time, and can effectively identify the position of the loading compartment and the precise position of the material forklift in complex power material scenarios, thereby optimizing the material handling path of the gantry robot.

[0027] This invention combines a visual recognition system with deep learning algorithms to process image data, extract key features of loading and unloading targets, and achieve precise positioning and motion planning of objects. Specifically, the gantry robot loading includes two parts: top scanning and side scanning and handling. During the top scanning process, the position of the loading compartment is detected by scanning with a binocular camera. During the side scanning and handling process, a 3D camera is used to scan and identify the precise position of the material forklift, plan the material handling trajectory, and finally complete the material handling. The specific process is as follows: Step 1: Obtain top-scan images according to the issued vehicle top-scan task; The principle behind the material outbound top-scanning process is the same as that of the inbound top-scanning process. The main difference lies in the visual analysis process during top-scanning. Inbound top-scanning identifies the materials to be unloaded, while outbound top-scanning identifies the cargo compartment of the loading truck. The execution process of the outbound top-scanning task mainly includes: the initial preparation and inspection phase, moving the gantry to the top-scanning area, top-scanning visual analysis, and return of result data, etc. Figure 2 As shown, the specific steps are as follows: Step 101: During the preparation and inspection phase of the outbound top scan, inspect the equipment and each module to see if they are ready. Step 102: After the preparation and inspection work is completed normally, move the truss to the top sweeping area; Step 103: Start calling the vision subsystem to perform top scan analysis. The process includes turning on the binocular camera to collect image data, the coordinates and dimensions of the loading compartment, etc. If the top scan fails (e.g., there are no trucks in the actual unloading area or other external factors affecting the process), the top scan failure is returned, and the top scan outbound task ends. Step 104: Top scan successful, data returned (carriage position coordinates, dimensions, etc.), the outbound top scan task is complete; Step 2: Detect the loading compartment based on the acquired top scan image to obtain the position and size information of the loading compartment; During the loading and unloading of materials, a top scan is required to detect the position of the truck bed. The top scan truck bed detection process includes the following steps: Step 201: Initialize the carriage position detection algorithm and load the parameters of the carriage position detection algorithm; In this embodiment, the carriage position detection algorithm adopts a deep learning-based binocular target 6D pose recognition algorithm.

[0028] Step 202: Acquire two-dimensional image data from the binocular camera, and perform preprocessing such as rotation on the acquired two-dimensional image data to obtain the preprocessed image; It should be noted that, in order to make the calculations more accurate, the image acquisition from both cameras must be carried out synchronously to obtain 2D image data from the binocular cameras.

[0029] Step 203: Input the preprocessed image into the carriage position detection algorithm and output the three-dimensional coordinate information of the four corners of the carriage; It should be noted that this 3D coordinate information uses the camera coordinate system; Step 204: Transform the three-dimensional coordinate information of the output carriage using a rotation matrix to output the vehicle's coordinates in the world coordinate system. The dimensions and height of the carriage can be calculated using the coordinate information of the four corners of the carriage. Step 205: The top-scanning visual detection of the carriage position is completed. Release resources and output all calculation results as input parameters for the loading task.

[0030] This invention combines a visual recognition system with deep learning algorithms to process image data, extract key features of the carriage, and achieve precise identification of the carriage.

[0031] Step 3: Based on the inspection results of the carriages, plan the layout and order of loading materials; like Figure 3As shown, loading planning is the process of planning the arrangement of materials in the wagon before loading, calculating the specific placement coordinates of the materials, and determining the loading direction and order of materials at each location.

[0032] The method for determining the loading and layout plan of materials is as follows: the rows and columns of the loading and layout of materials and the maximum quantity of materials to be accommodated are determined by combining the dimensions of the car body, the dimensions of the materials and the safe placement distance, as well as the coordinates of the placement of each material in each car body. For example, the dimensions of the carriage: length L ,Width W ,high H (Assuming a rectangular carriage, the height may limit the number of stacking layers), the length of each type of material. ,Width ,high ( i =1,2,…, n ).

[0033] Safe distance: The minimum distance between supplies d Including left and right, front and back, and top and bottom spacing; After considering the safety distance, the actual space occupied by each item is: , Along the length of the carriage (rows): Maximum number of rows: , Along the width of the carriage (columns): the maximum number of columns is: , No. r OK, c The center coordinates of the materials (assuming the origin is at the bottom left corner of the carriage, i.e., (0,0)): , The purpose of setting safety distance parameters in the loading plan is to avoid collisions between materials and between materials and the railings of the wagon during loading, so as to ensure loading safety. The method for determining the loading and placement sequence is as follows: Determine the direction of loading each material onto the truck, whether to place the material on the left or right side of the truck bed. Compare the placement of the material with the central axis of the truck bed. If the placement is on the side of the central axis, then the material should be loaded from that side. When loading, please confirm the loading order according to the loading layout and the direction of loading for each position. The loading order includes row priority and column priority modes. In row priority mode, load materials sequentially from the front of the truck to the back, based on their loading positions. In column priority mode, load materials sequentially from the front of the truck to the back, based on their loading positions. For example... Figure 3 The Z-shaped dotted arrows in the image indicate the loading order of materials 1-6 in the priority mode.

[0034] Step 4: Based on the acquired 3D point cloud data of the side-scanned materials, identify the material pick-up position; The control gantry moves to the side-scanning position for transporting materials. A 3D camera scans the 3D point cloud data of the materials from the side, identifying the precise coordinates of the material being picked up by the forklift. Picking up materials is the most difficult step in material handling, requiring precise coordinates of the picking point. Otherwise, accidents such as the forklift failing to pick up the material, materials tilting, or even collisions and falls can easily occur. To accurately detect the picking position, a 3D camera acquires 3D point cloud data of the material's side. A 3D vision detection algorithm then precisely locates the coordinates of the picking position. The material picking position identification process is as follows: Step 401: Initialize the material forklift position detection algorithm and load the parameters of the material forklift position detection algorithm; In this embodiment, the material forklift position detection algorithm adopts a 6D pose recognition algorithm based on deep learning in RGBD images.

[0035] Step 402: Acquire two-dimensional image data and 3D point cloud image data from the 3D camera respectively, preprocess the image data to obtain a format suitable for the material forklift position detection algorithm; Step 403: Input the preprocessed image into the material forklift position detection algorithm. If the position detection is successful, obtain the material forklift position. If the detection fails, move the camera appropriately through the material execution structure and repeat steps 402-403 to continue collecting data and detecting until the material forklift position is obtained. It is understandable that the detection may fail, for example, due to external light, obstruction, or the object being out of the camera's field of view. It should be noted that the location of the material pick-up point is based on the camera coordinate system; Step 404: Transform the coordinates of the material pick-up position using a rotation matrix, and output the coordinates of the material pick-up point in the world coordinate system; Step 405: Material forklift location detection ends, resources are released, and all calculation results are output. The data serves as the basis for material forklift path planning. The gantry robot of this invention combines top 3D image visual detection with side 3D image visual detection, enabling real-time monitoring of the loading and unloading process. This avoids the problem of the gantry robot failing to detect any discrepancies in the cargo position during loading and unloading, which could lead to equipment or cargo damage. Step 5: Plan the loading and handling path based on the material loading arrangement, loading order, and material forklift positions; The loading and unloading path planning utilizes AI algorithms to calculate the optimal operating path and dynamically adjusts the robot's movement route in real time based on the site environment and task requirements. During operation, the gantry robot not only executes tasks according to pre-set programs but also makes real-time decisions based on data feedback from sensors. Loading path planning, during loading and unloading, involves planning a safe and optimal transport path based on the starting point of material handling, the ending point of material placement, and the environment of the loading area, enabling the transport execution structure to complete the transport task in the shortest possible time.

[0036] like Figure 4 The diagram shown illustrates the loading trajectory, which includes the following steps: Step 501: Determine the key points in the loading trajectory planning; The key points identified in the loading trajectory planning include four important points: A, B, C, and D. Points A and D are the starting and ending points of material handling, respectively. Points B and C are the side-scan points and transition points between material removal and placement. During the loading process, the starting point for materials is the warehouse exit. The exit gate number and coordinates are determined based on the task requirements. The precise coordinates of the material forklift position are calculated in step 3 using side-scan analysis. The endpoint for material placement is located in the truck bed. Based on the top-scan detection of the truck bed's position and dimensions, and considering the material dimensions, safety margins, and material arrangement rules, the coordinates of the endpoint are calculated. Figure 4 As shown, in the loading trajectory, point A is the starting point for picking up materials from the warehouse exit, point D is the point where materials are placed in the truck bed, point B is the side scan point before material picking and the transition point for material removal, and point C is the transition point before material placement. At points B and C, the forklift end can adjust its posture, such as adjusting the side scan end camera angle and aligning the posture before material placement.

[0037] Step 502: Determine the material retrieval trajectory, material handling trajectory, and material placement trajectory respectively, and draw a complete handling trajectory by combining the material retrieval trajectory, material handling trajectory, and material placement trajectory; Specifically, the steps include the following: Step 5021: Determine the trajectory of the material retrieval; The material retrieval process involves first lifting the material to a certain safe height, then horizontally removing it from the outlet and moving it to point B. Point B requires establishing a three-dimensional safe space area based on the outlet coordinates, material dimensions, and forklift end dimensions to ensure it does not interfere with the outlet line.

[0038] The establishment of a three-dimensional safety zone is to determine the transition point before the materials are taken out or placed, and to serve as the basis for confirming the safety trajectory in the material handling trajectory planning, so as to ensure that collisions with surrounding objects (warehouse entrance and exit lines, carriages, etc.) are avoided during the end movement and posture adjustment of materials handling.

[0039] Specifically, a three-dimensional safety space area is established based on the coordinates of the exit point, the dimensions of the materials, and the dimensions of the forklift end effector. This includes: The three-dimensional safety zone is a cylinder centered on the Z-axis of rotation at the end of the forklift, such as... Figure 5 The diagram shows the establishment of a three-dimensional safety zone as follows: Radius of three-dimensional safety zone , in, It is the maximum radius of rotation at the end of the truss. d This is a reserved safety distance. Based on the dimensions of the forklift's end (which are known and fixed) and the dimensions of the goods being picked up, the vertical distance from each key point (such as the corners of the box, the ends of the picks, the outer shell, etc.) to the center is calculated. ; The maximum vertical distance from each key point to the center is used as the maximum radius of rotation; When the forklift is unloaded, the maximum rotation radius can be calculated based on the size of the forklift end. When fully loaded, the maximum rotation radius can be calculated based on the size of the loaded material and the size of the forklift end. Finally, a three-dimensional safety zone is established.

[0040] Step 5022: Determine the trajectory of the material handling section; A 2D virtual map is constructed to show the space of the loading and unloading area and the location of the wagons, such as... Figure 6 and Figure 7 As shown, In a virtual map, the RRT (Rapidly-exploring Random Tree) algorithm is used to find trajectory paths between transition points, such as... Figure 6 As shown; To optimize the generated path, first filter key points from the sequence of trajectory points in the path, such as... Figure 7 As shown by the dashed line, the safety trajectory is then calculated based on the trajectory formed by the key points and the three-dimensional safety space, as follows. Figure 7 The solid line trajectory shows the optimized safe handling trajectory; Finally, the three planned transport routes were merged into a single complete material transport route.

[0041] Step 5023: Determine the placement trajectory of the materials; The material placement process involves first moving the material horizontally to the top of the truck bed, and then placing the material downwards into the truck bed. At point C, a three-dimensional safety space needs to be established based on the dimensions of the truck bed, the dimensions of the material, and the dimensions of the forklift end to ensure that the material does not collide with the truck bed during placement.

[0042] Step 5024: Finally, based on the three-dimensional safe space area for transporting materials, establish a complete transport trajectory. Figure 4 In the diagram, AB represents the trajectory for retrieving materials, and CD represents the trajectory for placing materials. During the loading and transportation of materials, materials are sequentially retrieved from point A, taken to point B, moved to point C, and finally placed at point D, thus completing one loading process.

[0043] Step 6: Complete the transportation of materials according to the planned route; Step 7: After the handling is completed, report that the loading and handling task is completed. If there are multiple materials to be loaded, repeat steps 1-6 to complete the loading of the entire truckload of materials.

[0044] During the handling of materials, damage may occur at various stages. Therefore, the gantry robot of this invention can quickly make judgments and adjust the handling path in real time during loading and unloading. It has autonomous decision-making capabilities to avoid damage to materials at various stages during handling and ensure the integrity of materials after handling is completed.

[0045] Example 2 like Figure 8 As shown, this embodiment provides an intelligent control method for automatic unloading of a gantry robot, including the following steps: The unloading and loading methods of the gantry robot are based on the same principle, including two parts: top scanning and side scanning for material handling. During the top scanning process, a binocular camera scans and detects the position of the materials being unloaded in the truck bed. During the side scanning process, a 3D camera scans and identifies the precise location of the materials to be picked up by the forks, plans the material handling trajectory, and finally completes the material handling. The specific steps include the following: Step 1: Obtain top-scan images according to the issued unloading top-scan task; like Figure 9 As shown, the inbound top-scan task process mainly includes the initial preparation and inspection phase, moving the truss to the top-scan area, top-scan visual analysis, and return of result data. The specific steps are as follows: Step 101: Before starting the top scan task, check whether each device is working properly and whether the functional modules are ready, such as checking the top scan camera, checking the readiness of the visual algorithm, and checking the working status of external hardware devices. If the check fails, return the top scan failure and end the top scan task for data entry. Step 102: After the preparation and inspection work is completed normally, move the truss to the top sweeping area; Step 103: Start calling the vision subsystem to perform top scan analysis. The process includes turning on the binocular camera to collect image data, detecting the type of materials on the vehicle, and calculating information such as the location coordinates, quantity, and size of the materials. If the top scan fails (e.g., there are no materials in the actual unloading area or other external factors), the top scan failure is returned, and the top scan warehousing task ends. Step 104: Top scan successful, data returned (material type, quantity, coordinates, dimensions, etc.), the top scan task for warehousing is complete.

[0046] Step 2: Detect materials based on the acquired top-scan image to obtain information such as the location, size, and quantity of the materials; During the unloading process of materials from the warehouse, top scanning is required to detect relevant information about the materials. The top scanning material detection process specifically includes the following steps: Step 201: Initialize the material location detection algorithm and load its parameters; In this embodiment, the material location detection algorithm adopts a deep learning-based binocular target 6D pose recognition algorithm.

[0047] Step 202: Acquire two-dimensional image data from the binocular camera, and perform preprocessing such as rotation on the acquired two-dimensional image data to obtain the preprocessed image; It should be noted that, in order to make the calculations more accurate, the image acquisition from both cameras must be carried out synchronously to obtain 2D image data from the binocular cameras.

[0048] Step 203: Input the preprocessed image into the material location detection algorithm, and output information such as the location, size and quantity of the material; Step 3: Based on the material inspection results, plan the unloading scheme; In this embodiment, unloading planning involves detecting and calculating the position coordinates of the materials in the truck bed, determining the direction of unloading, and arranging the order of unloading before unloading.

[0049] The process of determining the direction for unloading materials includes: The main basis for unloading planning is the top-scan material detection algorithm outputting information such as the location coordinates, size and quantity of materials in the car. Under normal circumstances, material unloading is carried out from both sides of the car. Based on the location of the material in the car (left area and right area), it is determined which side to unload the material from. The unloading sequence planning follows the same principles as loading, using row-first and column-first modes. In row-first mode, unloading proceeds row-by-row from the rear of the vehicle to the front; in column-first mode, unloading proceeds column-by-column from the rear of the vehicle to the front. Figure 10The Z-shaped dashed arrows shown indicate the order in which materials 1-6 are unloaded, following a column-priority pattern.

[0050] Step 4: Based on the acquired 3D point cloud data of the side-scanned materials, identify the material pick-up position; The control gantry moves to the side-scanning position for transporting materials. A 3D camera scans the 3D point cloud data of the materials from the side, identifying the precise coordinates of the material being picked up by the forklift. Picking up materials is the most difficult step in material handling, requiring precise coordinates of the picking point. Otherwise, accidents such as the forklift failing to pick up the material, materials tilting, or even collisions and falls can easily occur. To accurately detect the picking position, a 3D camera acquires 3D point cloud data of the material's side. A 3D vision detection algorithm then precisely locates the coordinates of the picking position. The material picking position identification process is as follows: Step 401: Initialize the material forklift position detection algorithm and load the parameters of the material forklift position detection algorithm; In this embodiment, the material forklift position detection algorithm adopts a 6D pose recognition algorithm based on deep learning in RGBD images.

[0051] Step 402: Acquire two-dimensional image data and 3D point cloud image data from the 3D camera respectively, preprocess the image data to obtain a format suitable for the material forklift position detection algorithm; Step 403: Input the preprocessed image into the material forklift position detection algorithm. If the position detection is successful, obtain the material forklift position. If the detection fails, move the camera appropriately through the material execution structure and repeat steps 402-403 to continue collecting data and detecting until the material forklift position is obtained. It is understandable that the detection may fail, for example, due to external light, obstruction, or the object being out of the camera's field of view. It should be noted that the location of the material pick-up point is based on the camera coordinate system; Step 404: Transform the coordinates of the material pick-up position using a rotation matrix, and output the coordinates of the material pick-up point in the world coordinate system; Step 405: Material forklift location detection ends, resources are released, and all calculation results are output. The data serves as the basis for material forklift path planning. Step 5: Based on the unloading plan and the location of the materials forklifts, plan the unloading and handling route; Unloading route planning involves planning a safe and optimal transport route based on the starting point of material handling, the ending point of material placement, and the environment of the unloading area during the unloading process, so that the transport execution structure can complete the transport task in the shortest possible time.

[0052] like Figure 11The diagram shown illustrates the unloading trajectory, which includes the following steps: Step 501: Determine the important points in the unloading track planning; During the unloading process, the final destination of the materials is the warehouse exit. The warehouse exit number is determined according to the task, and the warehouse exit location coordinates are determined (the warehouse exit location coordinates are fixed). The starting point for material removal is in the truck compartment. Based on the information such as the type, location and size of the materials output by the top scan, the material removal location coordinates are calculated (the materials are removed before being removed by the top scan to calculate the precise material forklift position information). Figure 11 In the diagram, point A is the starting point for material handling, point D is the area where materials are placed at the warehouse entrance, point B is the transition point before material placement, and point C is the transition point for material removal. At points B and C, the forklift end can adjust its position. Step 502: Determine the material retrieval trajectory, material handling trajectory, and material placement trajectory respectively, and draw a complete handling trajectory by combining the material retrieval trajectory, material handling trajectory, and material placement trajectory; Specifically, the steps include the following: Step 5021: Determine the trajectory of the material retrieval; The material retrieval process involves first picking up the material based on the coordinates output by the side scan, lifting the material to a certain safe height, and then horizontally removing the material from the truck bed and moving it to point B. Point B requires the establishment of a three-dimensional safe space area based on the truck bed location and size, the material size, and the forklift end size to ensure that there is no interference with the truck bed during handling.

[0053] Step 5022: Determine the trajectory of the material handling section; In this embodiment, the process of establishing the three-dimensional safety space area and the trajectory of the material handling section are the same as in Embodiment 1. The specific establishment process can be found in Embodiment 1, and will not be repeated here.

[0054] Step 5023: Determine the placement trajectory of the materials; The material placement process involves first moving the material horizontally to the area above the inlet, and then placing the material downwards onto the inlet. Point C needs to be positioned to establish a three-dimensional safety space based on the inlet line position, material size, and forklift end dimensions to ensure that the material does not collide with the inlet line during placement.

[0055] Step 5024: Finally, based on the three-dimensional safe space area for transporting materials, establish a complete transport trajectory.

[0056] During the unloading and handling of materials, materials are picked up sequentially from point A, moved to point B, then moved to point C, and finally placed at point D, thus completing one unloading process.

[0057] Step 6: Control the truss to complete the material handling according to the planned handling path; Step 7: After the unloading is completed, report that the unloading task is complete. If there are multiple materials to be unloaded, repeat steps 1-6 to complete the unloading of all materials.

[0058] Example 3 This embodiment provides an intelligent control method for automatic loading and unloading of gantry robots, including: loading control process and unloading control process; The loading process includes: Based on the acquired top-scan image, the loading compartment is detected to obtain the position and size information of the loading compartment; Based on the inspection results of the carriages, a loading plan is generated; Based on the acquired side-scan material 3D point cloud data, the material picking position is identified; Based on the loading plan and the location of the material forklift, the loading and handling path is planned. The gantry robot is controlled to complete the loading of the entire vehicle of materials according to the planned loading and handling path. Specifically, this includes: determining the location of the starting point and the ending point of the material handling in the loading trajectory plan, calculating the three-dimensional safety distance during the material handling process, determining the material removal trajectory, the material handling section trajectory and the material placement trajectory based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, the material handling section trajectory and the material placement trajectory. The unloading control process includes: Material detection is performed based on the acquired top scan image to obtain information on the location, size, and quantity of the material; Based on the material inspection results, an unloading plan is generated; Based on the acquired side-scan material 3D point cloud data, the material picking position is identified; Based on the unloading plan and the location of the material forklift, the unloading and handling path is planned. The gantry robot is controlled to complete the unloading of all materials according to the unloading and handling path. Specifically, this includes: determining the starting and ending points of the material handling in the unloading trajectory plan, calculating the three-dimensional safety distance during the material handling process, determining the material removal trajectory, the material handling section trajectory, and the material placement trajectory based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, the material handling section trajectory, and the material placement trajectory.

[0059] It should be noted that the specific implementation of the loading control process in this embodiment of the invention is the same as that in Embodiment 1 of the invention, and the specific implementation of the unloading control process in this embodiment of the invention is the same as that in Embodiment 2 of the invention. Please refer to the description in the method section for details. In order to reduce redundancy, it will not be described again here.

[0060] Example 4 This embodiment provides an intelligent control system for automated loading of gantry robots, including: The carriage detection module is used to detect the loading carriage based on the acquired top scan image, and obtain the position and size information of the loading carriage; The loading planning module is used to generate loading planning schemes based on the inspection results of the wagon compartments; The forklift position detection module is used to identify the forklift position of the material based on the acquired side-scan material 3D point cloud data. The loading path planning module is used to plan the loading and handling path according to the loading plan and the material forklift position. It controls the gantry robot to complete the loading of the entire vehicle of materials according to the planned loading and handling path. Specifically, it includes: determining the starting and ending points of material handling in the loading trajectory planning, calculating the three-dimensional safety distance in the material handling process, determining the material removal trajectory, material handling section trajectory and material placement trajectory respectively based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, material handling section trajectory and material placement trajectory.

[0061] It should be noted that the specific implementation of the gantry robot automatic loading system in this embodiment of the invention is similar to the specific implementation of the gantry robot automatic loading method in this embodiment of the invention. Please refer to the description in the method section for details. In order to reduce redundancy, it will not be repeated here.

[0062] Example 5 This embodiment provides an intelligent control system for automatic unloading of gantry robots, including: The material inspection module is used to inspect materials based on the acquired top scan image and obtain the material inspection results; The unloading planning module is used to generate unloading planning schemes based on the material inspection results. The forklift position detection module is used to identify the forklift position of the material based on the acquired side-scan material 3D point cloud data. The unloading path planning module is used to plan the unloading and handling path based on the unloading plan and the material forklift position. It controls the gantry robot to complete the unloading of all materials according to the unloading and handling path. Specifically, it includes: determining the starting and ending points of material handling in the unloading trajectory planning, calculating the three-dimensional safety distance during the material handling process, determining the material removal trajectory, material handling section trajectory and material placement trajectory based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, material handling section trajectory and material placement trajectory.

[0063] It should be noted that the specific implementation of the gantry robot automatic unloading system in this embodiment of the invention is similar to the specific implementation of the gantry robot automatic unloading method in this embodiment of the invention. Please refer to the description in the method section for details. In order to reduce redundancy, it will not be repeated here.

[0064] Example 6 This embodiment provides an intelligent control system for automatic loading and unloading of gantry robots, including a loading control module and an unloading control module; The loading module is configured to: detect the loading compartment based on the acquired top-scan image to obtain the position and size information of the loading compartment; generate a loading planning scheme based on the compartment detection results; identify the material forklift position based on the acquired side-scan material 3D point cloud data; plan the loading and handling path according to the loading planning scheme and the material forklift position; and control the gantry robot to complete the loading of the entire vehicle's materials according to the planned loading and handling path. Specifically, this includes: determining the positions of the starting and ending points of material handling in the loading trajectory planning; calculating the three-dimensional safety distance during the material handling process; determining the material removal trajectory, material handling segment trajectory, and material placement trajectory based on the three-dimensional safety distance; and drawing a complete handling trajectory by combining the material removal segment trajectory, material handling segment trajectory, and material placement trajectory. The unloading control module is configured to: perform material detection based on the acquired top-scan image to obtain the position, size, and quantity information of the material; generate an unloading planning scheme based on the material detection results; identify the material forklift position based on the acquired side-scan material 3D point cloud data; plan the unloading and handling path according to the unloading planning scheme and the material forklift position; and control the gantry robot to complete the unloading of all materials according to the unloading and handling path. Specifically, this includes: determining the positions of the material handling start point and end point in the unloading trajectory planning; calculating the three-dimensional safety distance during the material handling process; determining the material removal trajectory, material handling segment trajectory, and material placement trajectory based on the three-dimensional safety distance; and drawing a complete handling trajectory by combining the material removal segment trajectory, material handling segment trajectory, and material placement trajectory.

[0065] It should be noted that the specific implementation of the intelligent control system for automatic loading and unloading of gantry robots in this embodiment of the invention is similar to the specific implementation of the intelligent control method for automatic loading and unloading of gantry robots in this embodiment of the invention. Please refer to the description in the method section for details. In order to reduce redundancy, it will not be repeated here.

[0066] Example 7 This embodiment provides a gantry robot, including the gantry robot automatic loading intelligent control system described in Embodiment 4, or the gantry robot automatic unloading intelligent control system described in Embodiment 5, or the gantry robot automatic loading and unloading intelligent control system described in Embodiment 6.

[0067] Example 8 This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps described in Embodiment 1, Embodiment 2, or Embodiment 3 above.

[0068] Example 9 This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps described in Embodiment 1, Embodiment 2, or Embodiment 3 above.

[0069] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0070] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0071] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0073] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0074] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An intelligent control method for automatic loading of gantry robots, characterized in that, Includes the following steps: Based on the acquired top-scan image, the loading compartment is detected to obtain the position and size information of the loading compartment; Based on the inspection results of the carriages, a loading plan is generated; Based on the acquired side-scan material 3D point cloud data, the material picking position is identified; Based on the loading plan and the location of the material forklift, a loading and handling path is planned. The gantry robot is then controlled to complete the loading of the entire vehicle's materials according to the planned path. Specifically, this includes: determining the starting and ending points of the material handling in the loading trajectory plan; calculating the three-dimensional safety distance during the material handling process; determining the material removal trajectory, the material handling segment trajectory, and the material placement trajectory based on the three-dimensional safety distance; and drawing a complete handling trajectory by combining the material removal segment trajectory, the material handling segment trajectory, and the material placement trajectory. The step of detecting the loading compartment based on the acquired top-scan image to obtain the position and size information of the loading compartment includes: Initialize the carriage position detection algorithm and load its parameters; Acquire two-dimensional image data, and preprocess the acquired two-dimensional image data to obtain a preprocessed image; The preprocessed image is input into the carriage position detection algorithm, which outputs the three-dimensional coordinate information of the four corners of the carriage; The 3D coordinates of the output carriage are transformed using a rotation matrix to output the vehicle's coordinates in the world coordinate system. Using the coordinates of the four corners of the carriage, the dimensions and height of the carriage are calculated. The step of identifying the material pick-up position based on the acquired side-scan material 3D point cloud data includes: Initialize the material forklift position detection algorithm and load the parameters of the material forklift position detection algorithm; Two-dimensional image data and 3D point cloud image data are acquired respectively. The image data is preprocessed to obtain a format suitable for the material forklift position detection algorithm. The preprocessed image is input into the material forklift position detection algorithm. If the position detection is successful, the material forklift position is obtained. If the detection fails, the camera is moved appropriately by the material execution structure to continue collecting data and detecting until the material forklift position is obtained.

2. The intelligent control method for automatic loading of a gantry robot as described in claim 1, characterized in that, Based on the inspection results of the carriage, a loading plan is generated, including the determination of the arrangement of materials loading and the order of loading and placement.

3. The intelligent control method for automatic loading of a gantry robot as described in claim 1, characterized in that, The three-dimensional safety zone during material handling is a cylinder centered on the Z-axis of the forklift's end, with a radius of... ,in, d This is a reserved safety distance. It is the maximum rotation radius at the end of the truss. The maximum rotation radius is calculated based on the size of the forklift end when the forklift end is unloaded, and based on the size of the loaded material and the size of the forklift end when fully loaded.

4. An intelligent control method for automatic unloading of gantry robots, characterized in that, Includes the following steps: Material detection is performed based on the acquired top scan image to obtain the material detection results; Based on the material inspection results, an unloading plan is generated; Based on the acquired side-scan material 3D point cloud data, the material picking position is identified; Based on the unloading plan and the location of the material forklift, plan the unloading and handling path, and complete the unloading of all materials according to the unloading and handling path. Specifically, this includes: determining the location of the starting point and ending point of the material handling in the unloading trajectory plan, calculating the three-dimensional safety distance during the material handling process, determining the material removal trajectory, the material handling section trajectory and the material placement trajectory respectively based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, the material handling section trajectory and the material placement trajectory. The identification of the material pick-up position based on the acquired side-scan material 3D point cloud data includes: Initialize the material forklift position detection algorithm and load the parameters of the material forklift position detection algorithm; Two-dimensional image data and 3D point cloud image data are acquired respectively. The image data is preprocessed to obtain a format suitable for the material forklift position detection algorithm. The preprocessed image is input into the material forklift position detection algorithm. If the position detection is successful, the material forklift position is obtained. If the detection fails, the camera is moved appropriately by the material execution structure to continue collecting data and detecting until the material forklift position is obtained.

5. The intelligent control method for automatic unloading of a gantry robot as described in claim 4, characterized in that, The process of generating an unloading plan based on the material inspection results includes: the position coordinates of the materials in the truck bed, determining the direction of unloading the materials, and arranging the order of unloading the materials.

6. A smart control method for automatic loading and unloading of gantry robots, characterized in that, include: The loading control process and the unloading control process; the loading control process includes the intelligent control method for automatic loading of the gantry robot as described in any one of claims 1-3, and the unloading control process includes the intelligent control method for automatic unloading of the gantry robot as described in any one of claims 4-5.

7. An intelligent control system for automatic loading of gantry robots, characterized in that, The intelligent control method for automatic loading of gantry robots as described in any one of claims 1-3 includes: The carriage detection module is used to detect the loading carriage based on the acquired top scan image, and obtain the position and size information of the loading carriage; The loading planning module is used to generate loading planning schemes based on the inspection results of the wagon compartments; The forklift position detection module is used to identify the forklift position of the material based on the acquired side-scan material 3D point cloud data. The loading path planning module is used to plan the loading and handling path according to the loading plan and the material forklift position. It controls the gantry robot to complete the loading of the entire vehicle of materials according to the planned loading and handling path. Specifically, it includes: determining the starting and ending points of material handling in the loading trajectory planning, calculating the three-dimensional safety distance in the material handling process, determining the material removal trajectory, material handling section trajectory and material placement trajectory respectively based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, material handling section trajectory and material placement trajectory.

8. An intelligent control system for automatic unloading of gantry robots, characterized in that: The intelligent control method for automatic unloading of a gantry robot as described in any one of claims 4-5 includes: The material inspection module is used to inspect materials based on the acquired top scan image and obtain the material inspection results; The unloading planning module is used to generate unloading planning schemes based on the material inspection results. The forklift position detection module is used to identify the forklift position of the material based on the acquired side-scan material 3D point cloud data. The unloading path planning module is used to plan the unloading and handling path based on the unloading plan and the material forklift position. It controls the gantry robot to complete the unloading of all materials according to the unloading and handling path. Specifically, it includes: determining the starting and ending points of material handling in the unloading trajectory planning, calculating the three-dimensional safety distance during the material handling process, determining the material removal trajectory, material handling section trajectory and material placement trajectory based on the three-dimensional safety distance, and drawing the complete handling trajectory by combining the material removal section trajectory, material handling section trajectory and material placement trajectory.

9. An intelligent control system for automatic loading and unloading of gantry robots, characterized in that, It includes the intelligent control system for automatic loading of gantry robots as described in claim 7 and the intelligent control system for automatic unloading of gantry robots as described in claim 8.

10. A gantry robot, characterized in that, Including the intelligent control system for automatic loading and unloading of gantry robots as described in claim 9.

Images