Tool changing robot arm extension path planning system based on 3D scanning in limited space

Abstract

The invention relates to the technical field of mechanical arm adjustment, and discloses a tool changing robot arm extension path planning system based on 3D scanning in a limited space, which comprises a sensing module, a scanning module and a path planning module, wherein the sensing module is used for identifying the type of an obstacle; the sensing module divides the working space of the tool changing robot into different sub-regions based on the types of obstacles; the scanning module obtains space scanning data of each sub-region based on 3D scanning; the sensing module is also used for selecting reference feature points; the scanning module carries out calibration of space scanning data based on the reference feature points; and the path planning module plans the arm extension path of the tool changing robot based on the space scanning data. Through fine path planning, the tool changing operation safety and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of robot arm adjustment, and in particular to a 3D scanning-based arm span path planning system for a tool-changing robot in a limited space. Background Art

[0002] When changing tools, tool-changing robots used in shield machines use a boom control mechanism to control the end effector's extension and movement within a confined space. Due to the varying sizes and operating environments of different shield machine models, the dimensions and obstacles within the confined space within which the boom structure can be extended vary. Current tool-changing robot technology still has many shortcomings.

[0003] The internal structure of a shield machine is complex, with various mechanical components intertwined. During tunneling, the machine is subject to interference from falling rock and soil, equipment vibration, and other factors, resulting in a dynamic operating environment. Existing detection methods, such as simple sensor combinations or low-precision scanning equipment, struggle to fully and accurately capture obstacle locations, shapes, and types. This prevents tool-changing robots from fully considering environmental factors when planning their paths, leading to the risk of collisions.

[0004] Traditional path planning fails to fully integrate the specific movements and constraints of tool changing operations into detailed planning. In actual tool changing, different actions, such as tool grasping, transporting, and installing, require varying degrees of freedom in the robot's arm's range of motion, posture, and force. Existing algorithms fail to optimize for these variations, resulting in less-than-smooth robot movements during tool changing, impacting accuracy and efficiency.

[0005] For example, Chinese patent application publication number CN116551688A discloses a shield machine operating method for a robot that detects or replaces cutterhead tools. The operating method includes: constructing a database of collision-free paths for the robot; obtaining the current posture of the robot's arm and obtaining the target posture of the robot arm; querying the database for a collision-free path from the current posture to the target posture and optimizing the path; and controlling the robot arm to move from the current posture to the target posture according to the optimized path. The operating method of this application effectively improves the robot's operating efficiency by calling the path in the database, but it still has the problem raised in the background technology of this application: it does not fully combine the specific actions and constraints of the tool change operation for detailed planning.

[0006] The information disclosed in this background section is only intended to enhance understanding of the overall background of the invention and should not be considered as an admission or any form of suggestion that the information constitutes the prior art already known to a person of ordinary skill in the art. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing technology and provide a 3D scanning-based arm span path planning system for tool changing robots in a limited space. Through precise path planning, the safety and efficiency of tool changing operations are improved. To solve the above technical problems, the present invention provides the following technical solutions: A 3D scanning-based arm span path planning system for a tool-changing robot in a limited space includes a perception module, a scanning module, and a path planning module; wherein: The perception module is used to identify obstacle types. Based on the types of obstacles, the perception module divides the tool changing robot's workspace into different sub-areas. The scanning module obtains spatial scanning data of each sub-area based on 3D scanning; The sensing module is further configured to select reference feature points; the scanning module calibrates the spatial scanning data based on the reference feature points; The path planning module performs arm span path planning of the tool changing robot based on the spatial scanning data.

[0008] As a preferred solution of the arm span path planning system of the tool changing robot based on 3D scanning in a limited space of the present invention, wherein: the perception module includes a recognition unit; The identification unit is used to identify the type of obstacles in the tool changing robot workspace, specifically including: Collecting an image of an obstacle in the workspace; the recognition unit is configured with a trained target detection model, inputting the obstacle image into the trained target detection model to identify the type of obstacle; The types of obstacles include intrusion obstacles and structural obstacles; the intrusion obstacles include obstacles that accidentally invade the working space of the tool changing robot; the structural obstacles include the internal structure of the robot working cabin.

[0009] As a preferred solution of the arm span path planning system of the tool changing robot based on 3D scanning in a limited space of the present invention, the perception module further includes an evaluation unit; the evaluation unit is used to divide the working space of the tool changing robot into different sub-areas, specifically including: Obtaining the coordinate range of each obstacle; the recognition unit is further configured with a binocular vision device; the recognition unit calculates the coordinate range of each obstacle based on the binocular vision device and transmits it to the evaluation unit; Based on the coordinate range and obstacle type of each obstacle, the workspace is divided into different types of sub-areas, and the coordinate range of each sub-area is recorded; the types of sub-areas include safe passage areas, buffer areas, and core operating areas; the core operating area is divided with the cutter box of the shield machine as the center; outside the core operating area, the buffer area is divided with any structural obstacle or intrusion obstacle as the center; in the workspace, the area outside the buffer area and the core operating area is the safe passage area.

[0010] As a preferred solution of the tool-changing robot arm span path planning system based on 3D scanning in a limited space according to the present invention, the scanning module includes a scanning component unit; the scanning component unit is used to perform a 3D scan on each of the sub-areas to obtain spatial scanning data of each sub-area, specifically including: Set the scanning resolution for each type of sub-area; read the type and coordinate range of each sub-area; Perform 3D scanning of the tool-changing robot's workspace and detect the coordinates of the scanned points in real time; The type of the sub-region where the scanning point is located is identified based on the coordinates of the scanning point, and the scanning resolution is dynamically adjusted based on the type of the sub-region.

[0011] As a preferred solution of the arm span path planning system of the tool changing robot based on 3D scanning in a limited space of the present invention, wherein: the perception module further includes a feature selection unit; the scanning module further includes a calibration unit; The feature selection unit is used to select reference feature points in the workspace of the tool changing robot, specifically including: selecting no less than n reference feature points before starting 3D scanning; n is a positive integer; measuring the three-dimensional coordinates of each reference feature point and marking them as the actual coordinates of each reference feature point; The calibration unit performs calibration correction of the spatial scanning data based on the reference feature points, specifically including: Reading point cloud data formed by the spatial scanning data; extracting feature points from the point cloud data; Matching the extracted feature points with the reference feature points to obtain the measured coordinates of each reference feature point in the point cloud data; Based on the actual coordinates and measured coordinates of each reference feature point, the rotation matrix and translation vector of the point cloud data are calculated; Compensation correction is performed on each spatial scanning data in the point cloud data based on the rotation matrix and the translation vector.

[0012] As a preferred solution of the arm span path planning system of the tool changing robot based on 3D scanning in a limited space of the present invention, the path planning module includes an action decomposition unit; the action decomposition unit is used to decompose the task of the tool changing robot into multiple sub-actions and determine the target state and constraint conditions of each sub-action in combination with the spatial scanning data; The target state includes the starting coordinates and the ending coordinates of the end effector; the constraint conditions include space constraints, posture constraints, and force constraints.

[0013] As a preferred solution of the arm span path planning system of the tool changing robot based on 3D scanning in a limited space described in the present invention, the path planning module further includes a path exploration unit; the path exploration unit explores alternative paths for each sub-action based on the target state and constraint conditions of each sub-action, and generates an alternative path set for each sub-action; the alternative path set of any sub-action includes at least one alternative path for the corresponding sub-action; The path exploration unit explores alternative paths for each sub-action based on the target state and constraints of each sub-action, specifically including: Read the target state and obtain the starting and ending coordinates of each sub-action end effector; Based on the path planning algorithm, considering the constraints, each sub-action plans at least M alternative paths; M is a positive integer; any alternative path of any sub-action is the movement of the end effector from the starting coordinates of the corresponding sub-action to the end coordinates.

[0014] As a preferred solution of the arm span path planning system of the tool changing robot based on 3D scanning in a limited space of the present invention, the path planning module further includes a calculation unit; the calculation unit generates an arm span path based on the alternative path set of each sub-action; specifically, it includes: The calculation unit selects an alternative path from the alternative path set of each sub-action, and combines all the selected alternative paths of the sub-action into a pending arm span path; Performing a stability test on any two adjacent sub-movements in the pending arm span path; if all two adjacent sub-movements in the pending arm span path pass the stability test, marking the pending arm span path as one arm span path; The calculation unit generates no less than m arm span paths and calculates the risk of each arm span path; and outputs the arm span path with the minimum risk as the arm span path planning result of the tool changing robot.

[0015] As a preferred solution of the arm span path planning system of the tool changing robot based on 3D scanning in a limited space of the present invention, the stability detection is specifically as follows: The acceleration change rate of each joint of the robot in two adjacent sub-actions is calculated; the calculation unit is configured with an acceleration change rate threshold; if the acceleration change rate of each joint is less than the acceleration change rate threshold, the two adjacent sub-actions pass the stability test.

[0016] As a preferred solution of the arm span path planning system of the tool changing robot based on 3D scanning in a limited space of the present invention, the calculation unit calculates the risk of each arm span path, specifically including: Calculate the length of each alternative path included in any arm span path and sum them up to get the total length of the arm span path; Based on the alternative paths of each sub-action in the arm span path, the movement amount of each joint of the tool changing robot when executing each sub-action is calculated; based on the movement amount of each joint, the motion trajectory of each joint is calculated; Read the coordinate range of each buffer zone and core operation area in the workspace; calculate the total number of times all joints pass through the buffer zone and core operation area based on the motion trajectory of each joint, and record the total number as the risk number; The total length of the arm span path and the number of risk events are normalized and then weighted summed to obtain the risk degree of the arm span path.

[0017] Compared with the prior art, the present invention has the following beneficial effects: This application effectively avoids the risk of the robot colliding with various obstacles during operation by sensing and analyzing obstacles in the tool changing robot's workspace, ensuring the safety of tool changing operations and reducing the probability of equipment damage.

[0018] This application fully combines the complex needs of tool changing operations, comprehensively considers the requirements of arm span movement in terms of space, posture and force, and realizes highly refined path planning, making tool changing operations smoother and more efficient.

[0019] By strictly calibrating and correcting the scanned data of the workspace, the impact of factors such as internal vibration of the shield machine and interference from complex environments on data accuracy is effectively overcome, providing accurate and reliable data support for path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them: Figure 1 A schematic diagram of the structure of the arm span path planning system for a tool-changing robot based on 3D scanning in a limited space provided by the present invention; Figure 2 A flow chart of calibration correction of spatial scanning data by the calibration unit provided by the present invention; Figure 3 A flow chart of the scanning component unit provided by the present invention acquiring spatial scanning data of each sub-area; Figure 4 The present invention provides a flow chart of the calculation unit for calculating the risk of each arm span path. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0022] This embodiment introduces a tool changing robot arm span path planning system based on 3D scanning in a limited space. Figure 1 The system includes a perception module, a scanning module, and a path planning module; wherein: The perception module is used to identify obstacle types. Based on the types of obstacles, the perception module divides the tool changing robot's workspace into different sub-areas. The perception module includes a recognition unit and an evaluation unit; The identification unit is used to identify the type of obstacles in the tool changing robot workspace, specifically including: Obstacle images in the workspace are captured; the recognition unit, equipped with a trained target detection model, inputs the obstacle images into the trained target detection model to identify the obstacle type. For example, target detection algorithms such as FasterR-CNN and the YOLO series can accurately identify different obstacles. Model training focuses on various structures within different shield machines, such as curved cutterhead supports and irregularly distributed grouting pipes. This enables the target detection model to quickly and accurately identify these structures, avoiding misidentification as traversable space. This allows for more precise determination of the actual spatial range within which the arm span mechanism can move, reducing scanning errors and improving the safety of the tool changer operation.

[0023] The types of obstacles include intrusion obstacles and structural obstacles; the intrusion obstacles include obstacles that accidentally invade the working space of the tool changing robot; the structural obstacles include the internal structure of the robot working cabin, such as hydraulic pipes, cabin doors, etc.

[0024] The evaluation unit is used to divide the working space of the tool changing robot into different sub-areas, specifically including: Obtain the coordinate range of each obstacle; the recognition unit is also equipped with a binocular vision device; the recognition unit calculates the coordinate range of each obstacle based on the binocular vision device and transmits it to the evaluation unit; the binocular vision device uses different images of the same obstacle captured by two cameras to find corresponding feature points in different images through a stereo matching algorithm, and then calculates the position difference between these corresponding points, and infers the three-dimensional coordinates of the feature points based on the position difference. As a preferred embodiment of the present application, firstly, edge detection is performed on the obstacle image to extract the edge information of the obstacle, and then the obstacle edges are connected into the obstacle outline through a contour extraction algorithm, thereby determining the approximate shape boundary of the obstacle; based on the binocular vision device, the coordinates of the feature points on the obstacle outline are obtained to determine the coordinate range of each obstacle.

[0025] Based on the coordinate range and obstacle type of each obstacle, the workspace is divided into different types of sub-areas, and the coordinate range of each sub-area is recorded; the types of sub-areas include safe passage areas, buffer areas, and core operating areas; the core operating area is divided with the cutter box of the shield machine as the center; outside the core operating area, the buffer area is divided with any structural obstacle or intrusion obstacle as the center; in the workspace, the area outside the buffer area and the core operating area is the safe passage area. For example, in the embodiment of the present application, it is preferred that a spherical or rectangular area with the cutter box as the center and 3m uniformly extended outward in all directions is the core operating area; the core operation is the area where the tool change operation is directly operated, and the installation and removal of the tool and bolts are all carried out in this area. Furthermore, in the embodiment of the present application, it is also preferred that a buffer area is divided with the rock layer as the center and 3m uniformly extended outward in all directions, or a buffer area is divided with the hatch of the shield machine as the center and 0.5m uniformly extended outward in all directions. When performing subsequent spatial scanning and arm span path planning, special attention should be paid to the core operating area and buffer zone to prevent the tool changing robot and the tool it holds from colliding with obstacles.

[0026] The scanning module obtains spatial scanning data of each sub-area based on 3D scanning; The scanning module includes a scanning component unit; Figure 3 The scanning component unit is used to perform 3D scanning on each of the sub-areas to obtain spatial scanning data of each sub-area, specifically including: Set the scanning resolution for each type of sub-area; read the type and coordinate range of each sub-area; Perform 3D scanning of the tool-changing robot's workspace and detect the coordinates of the scanned points in real time; The type of the sub-region where the scanning point is located is identified based on the coordinates of the scanning point, and the scanning resolution is dynamically adjusted based on the type of the sub-region.

[0027] In the embodiment of the present application, the scanning resolution of the core operating area is preferably at the millimeter level, the scanning resolution of the buffer zone is at the centimeter level, and the scanning resolution of the safe passage zone is at the decimeter level. For example, for the core operating area, the scanning resolution is 5mm×5mm×5mm, that is, the side length of the scanned voxel is 5mm; for any buffer zone, the scanning resolution is 3cm×3cm×3cm, that is, the side length of the scanned voxel is 3cm; for any safe passage zone, the scanning resolution is 10cm×10cm×10cm, that is, the side length of the scanned voxel is 10cm. When scanning the safe passage zone, the scanning resolution of the scanning component is 10cm×10cm×10cm. If it is detected that the buffer zone is being scanned, the scanning resolution of the scanning component is switched to 3cm×3cm×3cm. The present application adopts a multi-resolution scanning strategy, using high-resolution scanning in the critical core operating area to obtain fine structural information, and using low-resolution scanning in the non-critical safe passage area to increase the scanning speed; while ensuring the scanning accuracy, the overall scanning time is greatly shortened.

[0028] The spatial scanning data includes the coordinates of all obstacles in the tool-changing robot's workspace, as well as the inner walls of closed or semi-enclosed workspaces, for each scan point. This coordinate data is stored as a point cloud. Based on this point cloud data, the spatial range within which the tool-changing robot can navigate can be identified.

[0029] The sensing module is further configured to select reference feature points; the scanning module calibrates the spatial scanning data based on the reference feature points; The perception module further includes a feature selection unit; the scanning module further includes a calibration unit; The feature selection unit is used to select reference feature points in the workspace of the tool changing robot, specifically including: selecting no less than n reference feature points before starting 3D scanning; n is a positive integer; measuring the three-dimensional coordinates of each reference feature point and marking them as the actual coordinates of each reference feature point; In the embodiments of this application, reference feature points are preferably selected from stable locations within the shield machine, such as the cutterhead support frame and fixed beams within the shield. These reference feature points can be corners, circular hole centers, and other locations. High-precision measuring equipment is used to accurately measure and record the three-dimensional coordinates of these reference feature points.

[0030] Reference Figure 2 The calibration unit performs calibration correction of the spatial scanning data based on the reference feature points, specifically including: Reading point cloud data formed by the spatial scanning data; extracting feature points from the point cloud data; The extracted feature points are matched with the reference feature points to obtain the measured coordinates of each reference feature point in the point cloud data. This embodiment of the application extracts feature points from real-time scan data using image recognition and point cloud processing algorithms. The extracted feature points are matched with pre-selected reference feature points, using an efficient matching algorithm such as the iterative closest point algorithm to identify which feature point in the point cloud each reference feature point corresponds to.

[0031] Based on the actual coordinates and measured coordinates of each reference feature point, the rotation matrix and translation vector of the point cloud data are calculated; the embodiment of the present application preferably uses at least 3 reference feature points to calculate the rotation matrix and translation vector of the point cloud data relative to the reference coordinate system, and the rotation matrix and translation vector respectively describe the posture deviation and position deviation of the point cloud data relative to the reference coordinate system.

[0032] Based on the rotation matrix and translation vector, each spatial scanning data in the point cloud data is compensated and corrected. Each spatial scanning data is a three-dimensional coordinate; the three-dimensional coordinate is multiplied by the rotation matrix and then added with the translation vector to obtain the corrected spatial scanning data. The present application calibrates and corrects the spatial scanning data of real-time 3D scanning through the collaborative processing of the feature selection unit and the calibration unit, thereby ensuring the accuracy of the spatial scanning data and avoiding the adverse effects of the position offset of the scanning component caused by internal vibration interference of the shield machine or tool changing robot or other environmental interference on the accuracy of the spatial scanning data.

[0033] The path planning module performs arm span path planning of the tool changing robot based on the spatial scanning data.

[0034] The path planning module includes an action decomposition unit, a path exploration unit, and a calculation unit; The action decomposition unit is used to decompose the task of the tool changing robot into multiple sub-actions, and determine the target state and constraint conditions of each sub-action in combination with the spatial scanning data; The target state includes the start and end coordinates of the end effector. The start coordinates are the coordinates or an optional range of coordinates of the end effector when the sub-action begins execution, and the end coordinates are the coordinates or an optional range of coordinates of the end effector when the sub-action completes. The start and end coordinates are selected within the traversable space range determined based on the spatial scan data. The constraints include spatial constraints, posture constraints, and force constraints. Spatial constraints are also implemented based on obstacles or inner walls of the space determined by the spatial scan data.

[0035] Preferably, the embodiment of the present application breaks down the task of installing a new knife into the following sub-actions: tool grasping, transport posture adjustment, tool transportation, installation posture calibration, and tool installation. Among them, the spatial constraint for tool grasping is that the distance between the end effector and the obstacle is not less than 2 cm; the posture constraint is that the posture deviation of the tool before and after being grasped is within ±3° to ensure stable grasping; the force constraint is that the clamping force is controlled within 18000-20000N to ensure that the tool does not fall off (taking the tool mass of 150kg and the friction coefficient of 0.25 as an example, a clamping force of at least 18000N can ensure a safety factor of 3 times the minimum clamping force). The spatial constraint for transport posture adjustment is that the minimum distance between the tool and the arm span and the surrounding obstacles is not less than 5 cm to ensure transportation safety; the posture constraint is that the posture change range of the tool is within ±5°, which meets the subsequent installation requirements; the force constraint is that the force to maintain the stability of the tool is controlled within 800-1200N to prevent the tool from shaking (the force to maintain the stability of the tool here is used to overcome inertia, centrifugal force, vibration interference, etc.). The spatial constraints for tool transportation are that the distance between the tool and the arm and any obstacles along the path must be no less than 3cm. The posture constraint is that the tool's posture fluctuation during transportation must be within ±2°. The force constraint is that the arm's driving force must be stable during transportation, with fluctuations not exceeding 10% of the rated torque, ensuring the tool does not shake. The spatial constraints for installation posture calibration are that the arm must not touch any obstacles within a 5cm radius around the tool holder mounting hole. The posture constraint is that the posture deviation between the tool axis and the tool holder mounting hole axis must be within ±1°, and the position deviation must be within ±2mm. The force constraint is that the fine-tuning force must be controlled within 50-80N to achieve precise calibration. The spatial constraints for tool installation are that the distance between the tool and any obstacles around the tool holder must be no less than 1cm during installation. The posture constraint is that the tool must be inserted vertically into the tool holder, with a verticality deviation within ±1°. The force constraint is that the fixed torque error must be within ±0.5%. This application breaks down the tool changing process in detail, splits the tool changing robot's task into multiple sub-actions, and fully considers the space, posture and force requirements of each sub-action on the robot's arm movement. Combined with spatial scanning data, it adaptively sets target states and constraints for each sub-action, thereby achieving refined arm path planning. Compared with traditional path planning solutions that only consider the overall movement path, this application can more accurately control the arm movement of the tool changing robot and reduce the risks of collision and tool falling.

[0036] The path exploration unit explores alternative paths for each sub-action based on the target state and constraints of each sub-action, and generates an alternative path set for each sub-action; the alternative path set of any sub-action contains at least one alternative path for the corresponding sub-action; The path exploration unit explores alternative paths for each sub-action based on the target state and constraints of each sub-action, specifically including: Read the target state and obtain the starting and ending coordinates of each sub-action end effector; Based on the path planning algorithm, considering the constraints, each sub-action plans at least M alternative paths; M is a positive integer; any alternative path of any sub-action is the movement of the end effector from the starting coordinates of the corresponding sub-action to the end coordinates; the embodiment of the present application preferably uses any one of the A* algorithm, Dijkstra algorithm, and rapidly exploring random tree (RRT) algorithm as the path planning algorithm.

[0037] The calculation unit generates an arm span path based on the candidate path set of each sub-action, specifically including: The calculation unit selects an alternative path from the alternative path set of each sub-action, and combines all the selected alternative paths of the sub-action into a pending arm span path; Performing a stability test on any two adjacent sub-movements in the pending arm span path; if all two adjacent sub-movements in the pending arm span path pass the stability test, marking the pending arm span path as one arm span path; The stability test is specifically as follows: Calculate the acceleration rate of each joint of the robot during two adjacent sub-actions; the calculation unit is configured with an acceleration rate threshold; if the acceleration rate of each joint is less than the acceleration rate threshold, then the two adjacent sub-actions pass the smoothness test; the acceleration rate is the instantaneous change in acceleration of any joint when adjacent sub-actions are connected, divided by the time interval. For rotational joints, the acceleration of interest is angular acceleration; for translational joints, the acceleration of interest is linear acceleration. The acceleration rate reflects the smoothness of the tool-changing robot's switching movements. If the acceleration rate of each joint is small, it indicates that there are no obvious sudden changes in the robot's motion state, avoiding mechanical vibration caused by excessive acceleration and deceleration, and ensuring the continuity of the tool-changing movement.

[0038] The calculation unit generates no fewer than m arm span paths and calculates the risk of each arm span path. The arm span path with the lowest risk is output as the arm span path planning result for the tool changing robot. This embodiment first uses 3D scanning to quickly determine the space available for the tool changing robot's arm span mechanism to extend. Then, through path planning within the confined space, the arm span mechanism is controlled to drive the end effector along the optimal path to complete the tool changing action, thereby improving the efficiency of the tool changing robot used in shield machines.

[0039] Reference Figure 4 The calculation unit calculates the risk of each arm span path, specifically including: Calculate the length of each alternative path included in any arm span path and sum them up to get the total length of the arm span path; Based on the alternative paths of each sub-action in the arm span path, the movement amount of each joint of the tool changing robot when executing each sub-action is calculated; based on the movement amount of each joint, the motion trajectory of each joint is calculated; Read the coordinate range of each buffer zone and core operation area in the workspace; calculate the total number of times all joints pass through the buffer zone and core operation area based on the motion trajectory of each joint, and record the total number as the risk number; Given the end effector's trajectory (i.e., the span path), inverse kinematics can be used to calculate the timing and amount of movement required for each joint to execute each sub-action along the span path. The joint's movement amount can be used to calculate the range of the joint's coordinates in the workspace, i.e., the joint's trajectory. If a joint's trajectory intersects the buffer zone or core workspace, the joint passes through the buffer zone or core workspace.

[0040] The total length of the arm span path and the number of risk events are normalized and then weighted summed to obtain the risk degree of the arm span path.

[0041] This application considers both the total arm span path length and the number of risk factors to calculate the risk level for each arm span path. On the one hand, this encourages the shortest total arm span path length to improve tool change efficiency; on the other hand, it ensures that the tool changer's joints pass through the buffer zone and core working area as little as possible to minimize collision risk.

[0042] Those skilled in the art will appreciate 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 aspects. 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.

[0043] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the purpose and scope of protection of the present invention, which are all protected by the present invention.

Claims

1. A 3D scanning-based arm span path planning system for tool changing robots in confined spaces, characterized by: It includes perception module, scanning module and path planning module; among them: The perception module is used to identify the type of obstacles. Based on the type of obstacles, the perception module divides the working space of the tool changing robot into different sub-areas. The types of sub-areas include safe passage area, buffer area, and core operation area. The scanning module obtains spatial scanning data of each sub-area based on 3D scanning; The sensing module is further configured to select reference feature points; the scanning module calibrates the spatial scanning data based on the reference feature points; The path planning module performs arm span path planning of the tool changing robot based on the spatial scanning data, specifically including: Decompose the tool changing robot's task into multiple sub-actions; generate an alternative path set for each sub-action; Generate arm span paths based on the candidate path set for each sub-action; The risk of each arm span path is calculated based on the number of times the tool changing robot's joints pass through different types of sub-areas, and the arm span path with the minimum risk is selected as the planning result.

2. The arm span path planning system for a tool changing robot based on 3D scanning in a limited space according to claim 1, characterized in that: The perception module includes a recognition unit; The identification unit is used to identify the type of obstacles in the tool changing robot workspace, specifically including: Collecting an image of an obstacle in the workspace; the recognition unit is configured with a trained target detection model, inputting the obstacle image into the trained target detection model to identify the type of obstacle; The types of obstacles include intrusion obstacles and structural obstacles; the intrusion obstacles include obstacles that accidentally invade the working space of the tool changing robot; the structural obstacles include the internal structure of the robot working cabin.

3. The arm span path planning system for a tool changing robot based on 3D scanning in a limited space according to claim 2, characterized in that: The perception module further includes an evaluation unit; the evaluation unit is used to divide the working space of the tool changing robot into different sub-areas, specifically including: Obtaining the coordinate range of each obstacle; the recognition unit is further configured with a binocular vision device; the recognition unit calculates the coordinate range of each obstacle based on the binocular vision device and transmits it to the evaluation unit; Based on the coordinate range and obstacle type of each obstacle, the workspace is divided into different types of sub-areas, and the coordinate range of each sub-area is recorded; specifically, the following steps are performed: A core operation area is divided with the cutter box of the shield machine as the center; outside the core operation area, a buffer zone is divided with any structural obstacle or intrusion obstacle as the center; in the workspace, the area outside the buffer zone and the core operation area is a safe passage area.

4. The arm span path planning system for a tool changing robot based on 3D scanning in a limited space as claimed in claim 3, characterized in that: The scanning module includes a scanning component unit; the scanning component unit is used to perform 3D scanning on each of the sub-areas to obtain spatial scanning data of each sub-area, specifically including: Set the scanning resolution for each type of sub-area; read the type and coordinate range of each sub-area; Perform 3D scanning of the tool-changing robot's workspace and detect the coordinates of the scanned points in real time; The type of the sub-region where the scanning point is located is identified based on the coordinates of the scanning point, and the scanning resolution is dynamically adjusted based on the type of the sub-region.

5. The arm span path planning system for a tool changing robot based on 3D scanning in a limited space according to claim 4, characterized in that: The perception module further includes a feature selection unit; the scanning module further includes a calibration unit; The feature selection unit is used to select reference feature points in the workspace of the tool changing robot, specifically including: selecting no less than n reference feature points before starting 3D scanning; n is a positive integer; measuring the three-dimensional coordinates of each reference feature point and marking them as the actual coordinates of each reference feature point; The calibration unit performs calibration correction of the spatial scanning data based on the reference feature points, specifically including: Reading point cloud data formed by the spatial scanning data; extracting feature points from the point cloud data; Matching the extracted feature points with the reference feature points to obtain the measured coordinates of each reference feature point in the point cloud data; Based on the actual coordinates and measured coordinates of each reference feature point, the rotation matrix and translation vector of the point cloud data are calculated; Compensation correction is performed on each spatial scanning data in the point cloud data based on the rotation matrix and the translation vector.

6. The arm span path planning system for a tool changing robot based on 3D scanning in a limited space according to claim 5, characterized in that: The path planning module includes an action decomposition unit; the action decomposition unit is used to decompose the task of the tool changing robot into multiple sub-actions, and determine the target state and constraint conditions of each sub-action in combination with the spatial scanning data; The target state includes the starting coordinates and the ending coordinates of the end effector; the constraint conditions include space constraints, posture constraints, and force constraints.

7. The arm span path planning system for a tool changing robot based on 3D scanning in a limited space according to claim 6, characterized in that: The path planning module further includes a path exploration unit; the path exploration unit explores alternative paths for each sub-action based on the target state and constraints of each sub-action, and generates an alternative path set for each sub-action; the alternative path set of any sub-action includes at least one alternative path for the corresponding sub-action; The path exploration unit explores alternative paths for each sub-action based on the target state and constraints of each sub-action, specifically including: Read the target state and obtain the starting and ending coordinates of each sub-action end effector; Based on the path planning algorithm, considering the constraints, each sub-action plans at least M alternative paths; M is a positive integer; any alternative path of any sub-action is the movement of the end effector from the starting coordinates of the corresponding sub-action to the end coordinates.

8. The arm span path planning system for a tool changing robot based on 3D scanning in a limited space according to claim 7, characterized in that: The path planning module further includes a calculation unit; the calculation unit generates an arm span path based on a set of candidate paths for each sub-action; specifically, the calculation unit includes: The calculation unit selects an alternative path from the alternative path set of each sub-action, and combines all the selected alternative paths of the sub-action into a pending arm span path; Performing a stability test on any two adjacent sub-movements in the pending arm span path; if all two adjacent sub-movements in the pending arm span path pass the stability test, marking the pending arm span path as one arm span path; The calculation unit generates no less than m arm span paths and calculates the risk of each arm span path; and outputs the arm span path with the minimum risk as the arm span path planning result of the tool changing robot.

9. The arm span path planning system for a tool changing robot based on 3D scanning in a limited space according to claim 8, characterized in that: The stability test is specifically as follows: The acceleration change rate of each joint of the robot in two adjacent sub-actions is calculated; the calculation unit is configured with an acceleration change rate threshold; if the acceleration change rate of each joint is less than the acceleration change rate threshold, the two adjacent sub-actions pass the stability test.

10. The arm span path planning system for a tool changing robot based on 3D scanning in a limited space according to claim 9, characterized in that: The calculation unit calculates the risk of each arm span path, specifically including: Calculate the length of each alternative path included in any arm span path and sum them up to get the total length of the arm span path; Based on the alternative paths of each sub-action in the arm span path, the movement amount of each joint of the tool changing robot when executing each sub-action is calculated; based on the movement amount of each joint, the motion trajectory of each joint is calculated; Read the coordinate range of each buffer zone and core operation area in the workspace; calculate the total number of times all joints pass through the buffer zone and core operation area based on the motion trajectory of each joint, and record the total number as the risk number; The total length of the arm span path and the number of risk events are normalized and then weighted summed to obtain the risk degree of the arm span path.

Images