Automatic path matching system based on dynamic object adaptive collaborative robot

Abstract

The invention discloses an autonomous path matching system based on a dynamic object adaptive collaborative robot. The autonomous path matching system comprises a data acquisition layer, a decision-making layer and an execution layer, the data acquisition layer is used for performing track data acquisition and image information acquisition, and the data acquisition layer comprises a laser radar and a visual camera which are arranged on the robot; the decision-making layer comprises a path planning algorithm module and a scheduling management module, the path planning algorithm module is used for path planning, and the scheduling management module is used for task scheduling; the execution layer comprises a walking driving unit and a communication unit, the walking driving unit is a driving motor of the robot and is used for driving the robot according to a planned path after receiving the scheduling task, and the communication unit is used for providing communication support for the robot. According to the invention, path planning of the robot can be carried out.

Description

Technical Field

[0001] The present invention relates to the field of path planning, and in particular to an autonomous path matching system based on a dynamic object adaptive collaborative robot. Background Art

[0002] At present, most electrolytic aluminum workshops use manual or electric tightening tools to tighten bolts, and generally require manual re-inspection with torque wrenches. This operation method is accompanied by safety hazards, as well as problems such as high labor intensity, low production efficiency, and poor process stability. Therefore, using robots for bolt tightening can greatly improve efficiency and reduce labor intensity. When the robot is tightening bolts, it will use the path autonomous matching system to plan the path to ensure the smooth completion of the bolt tightening task.

[0003] The existing autonomous path matching has great difficulty in path planning in complex environments, poor adaptability to dynamic environments, and lack of comprehensive task scheduling and path coordination, which has brought certain impacts on the use of safety protection systems. Therefore, an autonomous path matching system based on dynamic object adaptive collaborative robots is proposed. Summary of the invention

[0004] The technical problem to be solved by the present invention is: how to solve the problems of existing autonomous path matching, difficult path planning in complex environments, poor adaptability to dynamic environments, and lack of comprehensive task scheduling and path coordination, and provide a path autonomous matching system based on dynamic object adaptive collaborative robots.

[0005] The present invention solves the above technical problems through the following technical solutions, and the present invention comprises: a data collection layer, a decision layer and an execution layer; The data acquisition layer is used for track data acquisition and image information acquisition. The data acquisition layer includes a laser radar and a visual camera installed on the robot; The decision-making layer includes a path planning algorithm module and a scheduling management module, wherein the path planning algorithm module is used for path planning, and the scheduling management module is used for task scheduling; The execution layer includes a walking drive unit and a communication unit. The walking drive unit is the driving motor of the robot, which is used to drive the robot according to the planned path after receiving the scheduling task. The communication unit is used to provide communication support for the robot.

[0006] Furthermore, a cleaning device is provided outside the laser radar on the robot for cleaning the laser radar when a preset condition is triggered; After the robot is hoisted onto the gantry crane track and docked with the track, the laser radar and visual camera start the self-inspection program for self-inspection, and data collection is carried out after the self-inspection passes.

[0007] Furthermore, the process of triggering the preset condition is as follows: The robot is also equipped with a dust sensor and an optical contrast detection module to monitor the area near the laser emission and receiving windows; The dust sensor detects the concentration change of suspended particles in the air. When the dust concentration exceeds the preset slight pollution threshold, it determines that there may be dust impact, and controls the cleaning device to perform external cleaning operations on the lidar. After the optical contrast detection module emits a beam of low-power calibration light, it compares the contrast of the received light with the preset pure optical element reference contrast. If the contrast decreases by more than the preset value, it means that the exterior of the LiDAR may be contaminated, and the cleaning device is automatically started for cleaning; The self-test contents of the laser radar include: optical path calibration, signal strength and stability test, and scanning frequency verification; When the optical path calibration is completed, the signal strength and stability tests are passed, and the scanning frequency calibration is passed, it means that the LiDAR self-test has passed; The self-test of the visual camera includes image acquisition test, 3D camera depth calibration, panoramic vision camera lens stitching effect check, optical image stabilization function test and deep learning model initialization check; When the image acquisition test, 3D camera depth calibration, panoramic vision camera lens stitching effect check, optical image stabilization function test and deep learning model initialization check are all passed, it means that the vision camera system self-test has passed; Furthermore, the path planning algorithm module uses a dynamic path planning algorithm and a local obstacle avoidance algorithm improved based on the A* algorithm to perform path planning.

[0008] Furthermore, the process of path planning based on the dynamic path planning algorithm improved by the A* algorithm is as follows: First, map construction is performed: using the robot's pre-stored precise size and shape data of the truss crane track, as well as the surrounding fixed facility information collected and processed by the laser radar and visual camera, a high-resolution two-dimensional or three-dimensional grid map is constructed; The fineness of the grid is set according to the robot's operating accuracy requirements and the complexity of the environment; on the map, the gantry track area is marked with a specific logo, and a lower travel cost value is set for this area; Mark the grid cell where the fixed obstacle is located as inaccessible, and set the travel cost to infinity; At the same time, the starting position of the robot and the target position of each bolt to be inspected are accurately marked.

[0009] Then the list is initialized: create an open list (OpenList) and a closed list (ClosedList). The open list is used to temporarily store nodes whose surrounding conditions are to be further explored, and the closed list is used to record nodes that have been explored and whose surrounding information is known. Put the starting point as the first node in the open list and calculate its key attribute value: Actual cost g(n): The actual cost of moving from the starting point to the current node n. The initial value is set to 0. The moving cost here is measured by the distance the robot moves on the track and is calculated using the Euclidean distance formula. If the starting point coordinates are (x0, y0) and the current node coordinates are (x, y), then ; Estimated cost h(n): The estimated cost of moving from the current node n to the target point, calculated using a heuristic function, h(n)=|x−x target ∣+∣y− ytarget ∣, where (x target ,y target ) is the target bolt position coordinate; Evaluation function value f(n): f(n)=g(n)+h(n). This value determines the exploration priority of the node in the open list. The smaller the value, the higher the priority of exploration. Perform cyclic exploration: continuously select the node with the smallest evaluation function value f(n) from the open list, designate it as the current node, remove the node from the open list, and add it to the closed list; Check whether the current node completely coincides with the target bolt position. If so, it indicates that a feasible path from the starting point to the target point has been found. At this time, through the backtracking operation, follow the parent node pointer of each node recorded previously, starting from the target node, and backtracking to the starting node in sequence, the nodes are connected in series to form a complete travel path, and the path planning process ends; Adjacent node processing: If the current node is not the target node, explore its adjacent nodes. Adjacent nodes usually include neighboring nodes in the up, down, left, right, and diagonal directions, depending on the actual mobility of the robot and the discretization accuracy of the map.

[0010] For each adjacent node m: first check whether it is within the valid range of the map and does not belong to the fixed obstacle area. If it does not meet the conditions, skip the node directly without further processing; If the conditions are met, calculate the new actual cost g′(m) from the starting point to the adjacent node m via the current node n, g′(m)=g(n)+cost(n,m), where cost(n,m) is the cost of moving from node n to node m, moving between adjacent nodes in the straight line area of ​​the track; Recalculate the estimated cost h(m) of the adjacent node m. The calculation method is the same as the previous calculation of h(n). Use a suitable heuristic function to estimate the remaining path length based on the target bolt position and the adjacent node position. Obtain the new evaluation function value f′(m)=g′(m)+h(m); If the adjacent node m is neither in the open list nor in the closed list, add it to the open list, set its parent node as the current node n, and update its g(m), h(m), and f(m) values to those calculated above.

[0011] If the adjacent node m is already in the open list, compare the newly calculated f′(m) value with the f(m) value of this node in the original open list: If f′(m)<f(m), it means that a better path to reach this node has been found. At this time, update the f(m) value, g(m) value, and parent node of this node in the open list to the current node n.

[0012] If the adjacent node m is already in the closed list, in a dynamic environment, if the original path is no longer optimal due to reasons such as obstacle movement or temporary environmental changes, decide whether to re-evaluate this node and its subsequent nodes according to the specific situation. If it is decided to re-evaluate, move this node from the closed list back to the open list and process it again according to the above process.

[0013] Continuously repeat the above loop exploration operation until the open list is empty, which means that starting from the starting point, no feasible path leading to the target point can be found based on the current map information, and the path planning fails; Or successfully locate the target node and smoothly backtrack the optimal path. At this time, the path planning is successfully completed.

[0014] Furthermore, the process of path planning by the local obstacle avoidance algorithm is as follows: Construct a potential field, including a gravitational potential field and a repulsive potential field; The construction process of the gravitational potential field is as follows: Use the position of the target bolt as the center of the gravitational source to construct the gravitational potential field function U att (q), where q is the current position of the robot; Uatt(q)=1 / 2k att (q−q target ) 2 , and katt is the gravitational coefficient; The construction process of the repulsive potential field is as follows: When dynamically detecting obstacles in real time through a lidar and a vision camera, use the actual position of each obstacle as the center of the repulsive source to construct the repulsive potential field function Urep(q, o i ), where o i is the position of the i-th obstacle; Adopt the following form of the repulsive potential field function: When the robot is at a distance d(q, o i )≤r0, U rep (q,o i )=1 / 2k rep (1 / d(q,o i )-1 / r0) 2 , k rep is the repulsion coefficient.

[0015] When the distance between the robot and the obstacle d(q, oi)>r0, U rep (q, oi) = 0, that is, after exceeding the influence radius of the obstacle, the repulsive force disappears, and the robot is not disturbed by the repulsive force of the obstacle. The direction of the repulsive force is from the obstacle to the robot, preventing the robot from approaching the obstacle; Determine the moving direction: At each decision moment (for example, every 0.1 seconds, depending on the real-time requirements of the robot's motion control and the computing resource affordability), the robot calculates the gravitational force F according to its current position q. att (q) and the repulsive force F from each obstacle rep (q,o i ); Gravity F att (q) By the gravitational potential field function U att (q) is derived, and in a two-dimensional plane, if q=(x,y), q target =(x target ,y target ), then F att The component form of (q) is F att,x = −k att (x− xtarget ), F att,y = −k att (y−y target ).

[0016] Repulsion F rep (q,o i ) by repulsive potential field function Urep(q,o i ) is derived, and in the two-dimensional plane, according to the distance formula , where (xoi,yoi) is the coordinate of the ith obstacle; When d(q,o i )≤r0: ; ; When d(q,o i )>r0, F rep,x =F rep,y =0; Calculate the resultant force F(q): vector sum the gravitational force and all repulsive forces, .

[0017] The direction of the robot's movement is determined according to the direction of the resultant force, that is, the robot moves in the direction of the resultant force. For example, if the component of the resultant force in the two-dimensional plane is F(q)=(Fx,Fy), then the robot's moving direction angle θ=arctan2(Fy,Fx); Dealing with local minima: Local minimum detection: During the movement of the robot, the robot continuously monitors its motion state and checks the robot's movement distance during this period at preset time intervals. If it is found that the robot moves very small distances in multiple consecutive such time intervals and the resultant force approaches zero, that is, |F(q)|<ϵ (ϵ is the set threshold, which is determined based on factors such as the robot's power accuracy and sensor accuracy, and is generally 1-2 times the robot's minimum perceptible force), then the robot is judged to be in a local minimum dilemma; Random perturbation strategy: When a local minimum is detected, in order to help the robot get out of trouble, the robot's moving direction or speed is randomly changed within a preset range, prompting the robot to find a feasible path again.

[0018] Furthermore, the functions of the scheduling management module include parsing after receiving the instruction and extracting key information, including task priority, bolt position sequence, tightening torque requirements and task time limit; Build and prioritize task queues; Combine environmental perception to carry out path planning and task adjustment; System coordination and command sending; Task completion and status feedback.

[0019] Furthermore, the specific process of task queue construction and priority sorting is as follows: According to the task information obtained by parsing, a task queue is constructed. The task queue is implemented using a priority queue data structure. High-priority tasks will be placed at the front of the queue and processed first; Prioritize by: The determination of task priority takes into account multiple factors, including the importance of the bolt, the urgency of the task and the time limit of the task; For tasks with the same priority, they are sorted according to the location of the bolts, giving priority to tasks that are closer to the current robot position; The process of path planning and task adjustment combined with environmental perception is as follows: Maintain real-time data interaction with the lidar, visual camera system and sensor fusion module of the perception layer to obtain dynamic information of the current environment, including the location, type and movement status of obstacles; Path planning and task allocation: Based on the current task queue and environmental perception data, the path planning algorithm module is called to plan the optimal path for each task; During the planning process, the movement trend of dynamic obstacles is considered and their future positions are predicted to avoid path conflicts; When a dynamic obstacle is detected on the path and is expected to stay for a long time, affecting the execution of the current task, the system determines whether to suspend the current path based on the task priority and execute the bolt maintenance task of the same or higher priority nearby; When an emergency occurs and the task cannot be executed as planned, the task scheduling and management module will start the task re-planning mechanism; First, the current task queue is re-evaluated, and the execution order of tasks is adjusted according to their priorities and remaining time, and then the path is re-planned.

[0020] The specific contents of task completion and status feedback are as follows: Task completion judgment: when the robot completes the inspection task of a bolt, the tightening system will feedback the task completion information, including the tightening result and the actual tightening time; The scheduling management module determines whether the task is successfully completed based on the task completion information; If the task is not completed successfully, the system will decide whether to retry or adjust the task strategy based on the specific situation; Status feedback: The task completion status and related data are fed back to the background monitoring system in real time through the communication system. At the same time, the task queue is updated and the completed tasks are removed from the queue. When there are remaining tasks in the task queue, the task scheduling and execution continue according to the above process until all maintenance tasks are completed.

[0021] Compared with the prior art, the present invention has the following advantages: the path autonomous matching system based on the dynamic object adaptive collaborative robot, the laser radar is equipped with a cleaning device, combined with the dust sensor and optical contrast detection module monitoring, and automatically cleans when the preset conditions are met to ensure the accuracy of the laser radar data collection; the laser radar and the visual camera perform a comprehensive self-inspection after the docking with the track, covering optical path calibration, signal testing, functional inspection and other aspects. Data collection is only carried out after the self-inspection is passed, further ensuring the reliability of the collected data, providing a solid foundation for subsequent decision-making and task execution.

[0022] Achieve efficient path planning and obstacle avoidance: The path planning algorithm module adopts a dynamic path planning algorithm and a local obstacle avoidance algorithm based on the improved A* algorithm. The former can quickly plan the optimal path from the starting point to the target point by constructing a high-resolution map, reasonably setting the travel cost, and using the open list and closed list for cyclic exploration; the latter constructs the gravitational potential field and the repulsive potential field, determines the moving direction according to the combined force, and adopts a random perturbation strategy to deal with local minima, so that the robot can adjust the path in time when encountering dynamic obstacles, ensuring the safe and efficient completion of tasks in complex and dynamic environments.

[0023] Optimize task scheduling management: The scheduling management module can parse the received instructions, extract key information to build and sort the task queue, and determine the priority by comprehensively considering the importance of the bolts, the urgency of the task and the time limit. Under the same priority, tasks with close distances are given priority to reduce the robot's movement time and energy consumption. At the same time, the path planning and task arrangement are adjusted in real time in combination with environmental perception, and the re-planning mechanism can be activated in case of emergencies; after the task is completed, the status is promptly fed back and the task queue is updated to ensure the efficient and orderly execution of the entire maintenance task. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is the overall structural block diagram of the present invention. DETAILED DESCRIPTION

[0025] The following is a detailed description of an embodiment of the present invention. This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given, but the protection scope of the present invention is not limited to the following embodiment.

[0026] like Figure 1 As shown, this embodiment provides a technical solution: a path autonomous matching system based on a dynamic object adaptive collaborative robot, including: a data acquisition layer, a decision layer and an execution layer; The data acquisition layer is used for track data acquisition and image information acquisition. The data acquisition layer includes a laser radar and a visual camera installed on the robot; The decision-making layer includes a path planning algorithm module and a scheduling management module, wherein the path planning algorithm module is used for path planning, and the scheduling management module is used for task scheduling; The execution layer includes a walking drive unit and a communication unit. The walking drive unit is the driving motor of the robot, which is used to drive the robot according to the planned path after receiving the scheduling task. The communication unit is used to provide communication support for the robot.

[0027] Furthermore, a cleaning device is provided outside the laser radar on the robot for cleaning the laser radar when a preset condition is triggered; After the robot is hoisted onto the gantry crane track and docked with the track, the laser radar and visual camera start the self-inspection program for self-inspection, and data collection is carried out after the self-inspection passes.

[0028] The process of triggering the preset condition is as follows: The robot is also equipped with a dust sensor and an optical contrast detection module to monitor the area near the laser emission and receiving windows; The dust sensor detects the concentration change of suspended particles in the air. When the dust concentration exceeds the preset slight pollution threshold (such as more than 100 particles with a particle size of 10μm or more per cubic meter of air), it determines that there may be dust impact, and controls the cleaning device to perform external cleaning operations on the lidar. After the optical contrast detection module emits a beam of low-power calibration light, it compares the contrast of the received light with the preset pure optical element benchmark contrast. If the contrast decreases by more than the preset value (such as 10%), it means that the exterior of the LiDAR may be contaminated, and the cleaning device is automatically started for cleaning; The self-test contents of the laser radar include: optical path calibration, signal strength and stability test, and scanning frequency verification; When the optical path calibration is completed, the signal strength and stability tests are passed, and the scanning frequency calibration is passed, it means that the LiDAR self-test has passed; Optical path calibration: When the internal calibration procedure is started, the lidar emits a laser beam of a specific wavelength (such as 905nm or 1550nm) and a known intensity. These laser beams will be reflected multiple times between the internal mirrors and optical elements and finally return to the receiving unit.

[0029] By analyzing the phase, intensity, time delay and other parameters of the reflected light, the built-in calibration algorithm is used to accurately calculate the deviation between the emission and reception angles. For example, if the emitted light should theoretically be perpendicular to a certain reference plane, but the angle of the received light deviates from the perpendicular direction by a certain threshold, adjustment is required. This adjustment process may involve fine-tuning the angle of the motor-driven reflector, with a motor step accuracy of up to 0.01°, to ensure that the scanning plane of the laser beam is precisely perpendicular to the robot coordinate system, ensuring the accuracy of subsequent environmental scanning data.

[0030] Optical component cleanliness inspection: The area around the laser transmitting and receiving windows is monitored using the built-in dust sensor or optical contrast detection module.

[0031] The dust sensor detects the concentration change of suspended particles in the air and indirectly determines whether there is dust attached to the surface of the optical component. When the dust concentration exceeds the preset slight pollution threshold (such as more than 100 particles with a diameter of 10μm or more per cubic meter of air), it is determined that there may be dust impact.

[0032] The optical contrast detection module emits a beam of low-power calibration light and then compares the contrast of the received light with the preset reference contrast of the pure optical element. If the contrast decreases by more than 10%, it also indicates that the optical element may be contaminated. Once dust contamination is detected, the cleaning device is automatically started for pre-cleaning.

[0033] Signal strength and stability test: In a closed standard test environment (such as no external strong light interference and reflective walls of known distance), the lidar continuously emits laser beams and receives reflected signals for continuous monitoring for 10 seconds.

[0034] Record the average and standard deviation of the reflected light signal intensity received per second. The average signal intensity should be within the normal working range of the equipment (calibrated according to different equipment models, such as 50-100mV), and the standard deviation should be less than the set fluctuation threshold (such as 5mV) to ensure that the signal is stable and reliable and is not affected by internal electronic component noise or slight jitter in the optical path.

[0035] Scan frequency calibration: The internal clock module accurately records the number of complete 360° scans completed by the LiDAR within 1 minute.

[0036] This number is compared with the preset lower limit of the scanning frequency (not less than 10Hz, i.e. 600 times per minute). The allowable error range is within ±0.5Hz, ensuring that the scanning frequency is stably maintained above the required standard and that dynamic changes in the environment can be captured in a timely manner.

[0037] The self-test of the visual camera includes image acquisition test, 3D camera depth calibration, panoramic vision camera lens stitching effect check, optical image stabilization function test and deep learning model initialization check; When the image acquisition test, 3D camera depth calibration, panoramic vision camera lens stitching effect check, optical image stabilization function test and deep learning model initialization check are all passed, it means that the vision camera system self-test has passed; Image acquisition test: Start the camera and collect 10 static images for the 3D camera and the high-definition panoramic vision camera respectively in a standard lighting environment (light intensity 500-1000lux, color temperature 5000-6000K), with an interval of 1 second between each image collection.

[0038] Compare with preset standard image templates, which include normal focus clear images, color block images with accurate color reproduction, calibration patterns with specific geometric shapes, etc. Use image similarity algorithms, such as the structural similarity index (SSIM), to calculate the similarity between the captured image and the standard template. For 3D cameras, additional attention should be paid to the integrity and consistency of the depth map, and the accuracy and continuity of the depth value should be checked by placing standard objects at different distances.

[0039] 3D Camera Depth Calibration: Within the range of 0.5-2 meters from the camera, place 5 standard objects of known shape and size (such as a cube with a side length of 10 cm) equidistantly along the camera optical axis, and the surface of the objects has a high-contrast texture.

[0040] The 3D camera collects images containing these objects and uses its own depth measurement algorithm to obtain the depth value of the object. The measured depth value is compared with the actual distance of the object, and the absolute error of the depth measurement of each object is calculated. The average absolute error should be less than the preset depth accuracy requirement (±0.5mm). If the error exceeds the range, the internal parameters of the camera (such as baseline distance, focal length, etc.) are fine-tuned and corrected according to the built-in calibration model. The correction step can reach 0.01mm depending on the camera accuracy.

[0041] Panoramic vision camera lens stitching effect inspection: In an open space, the panoramic vision camera slowly rotates around its central axis (at a speed of about 10° / second) to collect a continuous sequence of images.

[0042] Use image stitching algorithms to stitch these images in real time and check whether the pixel differences and color transitions at the stitching are natural. By calculating the average pixel difference of the stitching area (e.g. less than 10 gray levels) and edge detection algorithms to determine the smoothness of the stitching edges, ensure seamless connection of the panoramic image without obvious stitching gaps, misalignment or color inconsistency.

[0043] Optical image stabilization function test: The camera is fixed on a simulated vibration platform, which can generate vibrations of different frequencies (such as 5-50Hz) and amplitudes (such as 0.1-1mm) to simulate the vibration environment of the robot during operation.

[0044] Before and after the vibration platform is turned on, 5 images are collected to compare the position offset of specific target objects in the images. Under normal circumstances, after the optical image stabilization function is turned on, the position offset of the target object in the image should be less than 50% when it is not turned on, ensuring that the image jitter can be effectively reduced during the movement of the robot and the image quality can be guaranteed.

[0045] Deep learning model initialization check: For deep learning-based object detection and classification models, load the pre-trained model weights during self-check and input a set of 20 test images containing common dynamic objects (such as people, vehicles, tools, etc.).

[0046] The monitoring model output results require the model to accurately identify at least 90% of the dynamic object categories in the image within 1 second, and provide relatively accurate position coordinates (the error is within ±10 pixels of the image pixel coordinates), movement direction (the deviation from the actual direction is less than 30°) and speed estimation (relative error is less than 30%) to ensure that the model can work normally and quickly and accurately identify the type of dynamic objects and related information.

[0047] Self-test passing criteria: In the image acquisition test, the average SSIM value of 10 static images and the standard template is greater than 0.9 (full score 1.0). For the 3D camera, the average absolute error of the depth map is less than ±0.5mm.

[0048] The average pixel difference at the stitching point of the panoramic vision camera lens is less than 10 gray levels, and the stitching edge is smooth without obvious gaps, misalignment or color inconsistency.

[0049] In the optical image stabilization function test, the position offset of the target object after image stabilization is turned on is less than 50% when it is not turned on.

[0050] During the initialization check of the deep learning model, at least 90% of the dynamic object categories in the test image can be accurately identified within 1 second, and the errors in position coordinates, movement direction and speed estimation are within the specified range.

[0051] When all the above conditions are met, the visual camera system self-test is judged to have passed, and then the data collection stage can be entered; Ensure accurate data collection of LiDAR: The cleaning device works with the dust sensor and optical contrast detection module to promptly detect and remove external contaminants of the LiDAR. In a dusty environment, dust easily adheres to the surface of the LiDAR, affecting the quality of its transmission and reception signals. The dust sensor can monitor the concentration of suspended particles in the air in real time. Once the concentration exceeds the standard, the cleaning device is immediately activated to prevent dust accumulation from interfering with the work of the LiDAR. The optical contrast detection module starts from the perspective of optical performance and accurately determines whether the LiDAR is contaminated by comparing the contrast of the received light, ensuring that the environmental data obtained by the LiDAR is true and reliable, and providing an accurate basis for the robot's path planning and environmental perception.

[0052] Ensure stable operation of the LiDAR: The self-test of the LiDAR covers several key aspects. Optical path calibration ensures the accuracy of the laser beam emission and reception angles, so that the robot can accurately perceive the distance and position information of the surrounding environment; the signal strength and stability test ensures that the reflected light signal strength and stability are within the normal range to avoid data errors caused by signal fluctuations; the scanning frequency calibration maintains the scanning frequency stable and captures the dynamic changes of the environment in a timely manner. Only when all self-tests are passed can the LiDAR be ensured to operate stably in complex environments and provide continuous and reliable environmental data support for the robot.

[0053] Improve the performance reliability of visual cameras: The self-inspection of visual cameras is comprehensive, involving multiple key links such as image acquisition, depth calibration, lens stitching, anti-shake function and deep learning model. Image acquisition test ensures that the camera can obtain clear and accurate images; 3D camera depth calibration ensures that the depth measurement data is accurate, which helps the robot perceive the spatial position of objects; panoramic vision camera lens stitching effect inspection ensures seamless connection of panoramic images and provides a more comprehensive environmental view; optical anti-shake function test reduces image jitter when the robot moves and improves image quality; deep learning model initialization check ensures that the model can quickly and accurately identify dynamic objects. These self-inspection processes ensure the performance reliability of the visual camera system under different environments and working conditions, and enhance the robot's ability to perceive and understand the environment.

[0054] Improve the overall operational reliability of the system: As important sensing components of the robot, the cleaning and self-checking mechanisms of LiDAR and visual cameras effectively reduce system errors caused by sensor failure or inaccurate data. In the process of robot execution, accurate environmental perception data is the basis for path planning, obstacle avoidance and task execution. The cleaning and self-checking mechanisms ensure that the sensors work stably and reliably, enabling the robot to accurately judge its own position and surrounding environment, and then plan a reasonable path, effectively avoid obstacles and successfully complete the task, thus improving the operational reliability and stability of the entire path autonomous matching system based on dynamic object adaptive collaborative robots.

[0055] The path planning algorithm module uses a dynamic path planning algorithm and a local obstacle avoidance algorithm improved based on the A* algorithm for path planning.

[0056] The process of path planning based on the dynamic path planning algorithm improved by the A* algorithm is as follows: First, map construction is performed: using the robot's pre-stored precise size and shape data of the truss crane track, as well as the information of surrounding fixed facilities (such as columns, walls, large equipment bases, etc.) collected and processed by LiDAR and visual cameras, a high-resolution two-dimensional or three-dimensional grid map is constructed; The fineness of the grid is set according to the robot's operational accuracy requirements and the complexity of the environment; for example, every 0.05 meter × 0.05 meter of actual space is divided into a grid unit.

[0057] On the map, a specific sign is used to mark the gantry track area. A lower travel cost value is set for this area. For example, it is set to 1, which means that the robot can move relatively conveniently and consumes less energy in this area. Mark the grid cells where fixed obstacles are located as inaccessible and set the travel cost to infinity to ensure that the planned path will not pass through these areas; At the same time, the starting position of the robot and the target position of each bolt to be inspected are accurately marked.

[0058] Then the list is initialized: create an open list (OpenList) and a closed list (ClosedList). The open list is used to temporarily store nodes whose surrounding conditions are to be further explored, and the closed list is used to record nodes that have been explored and whose surrounding information is known. Put the starting point as the first node in the open list and calculate its key attribute value: Actual cost g(n): The actual cost of moving from the starting point to the current node n. The initial value is set to 0. The moving cost here is measured by the distance the robot moves on the track and is calculated using the Euclidean distance formula. If the starting point coordinates are (x0, y0) and the current node coordinates are (x, y), then ; Estimated cost h(n): The estimated cost of moving from the current node n to the target point, calculated using a heuristic function, h(n)=|x−x target ∣+∣y−y target ∣, where (x target ,y target ) is the target bolt position coordinate. The estimated cost is a conservative estimate of the remaining path length, which is required to be always less than or equal to the actual remaining path length to ensure that the algorithm can find the optimal path. Evaluation function value f(n): f(n)=g(n)+h(n). This value determines the exploration priority of the node in the open list. The smaller the value, the higher the priority of exploration. Perform cyclic exploration: Continue to select the node with the smallest evaluation function value f(n) from the open list, designate it as the current node, and remove the node from the open list and add it to the closed list, which means that the node and its surrounding information have been fully mastered; Check whether the current node exactly coincides with the target bolt position. If it coincides, it indicates that a feasible path from the starting point to the target point has been found. At this time, through backtracking operations, starting from the target node, follow the parent node pointers of each previously recorded node in sequence and backtrack to the starting node. The nodes are concatenated to form a complete travel path, and the path planning process ends here; Processing of adjacent nodes: If the current node is not the target node, explore its adjacent nodes. Adjacent nodes usually cover neighbor nodes in the up, down, left, right, and diagonal directions, depending on the actual movement ability of the robot and the map discretization accuracy.

[0059] For each adjacent node m: First, check whether it is within the valid range of the map and does not belong to the fixed obstacle area. If it does not meet the conditions, directly skip this node and do not process it further; If it meets the conditions, calculate the new actual cost g′(m) from the starting point through the current node n to the adjacent node m, g′(m)=g(n)+cost(n, m), where cost(n, m) is the movement cost from node n to node m. When moving between adjacent nodes in the straight area of the track, cost(n, m) can be simply equivalent to the Euclidean distance between the two nodes; If it involves situations such as track turning and crossing different regions, appropriately increase the movement cost according to the actual situation to reflect the difference in movement difficulty; Recalculate the estimated cost h(m) of the adjacent node m. The calculation method is the same as the previous calculation of h(n). Use a suitable heuristic function to estimate the remaining path length based on the target bolt position and the adjacent node position; Obtain the new evaluation function value f′(m)=g′(m)+h(m); If the adjacent node m is neither in the open list nor in the closed list, add it to the open list, set its parent node as the current node n, and update its g(m), h(m), and f(m) values to the calculated values above.

[0060] If the adjacent node m is already in the open list, compare the newly calculated f′(m) value with the f(m) value of this node in the original open list: If f′(m)<f(m), it means that a better path to reach this node has been found. At this time, update the f(m) value, g(m) value, and parent node of this node in the open list to the current node n.

[0061] If the adjacent node m is already in the closed list, in a dynamic environment, if the original path is no longer optimal due to reasons such as obstacle movement and temporary environmental changes, decide whether to re-evaluate this node and its subsequent nodes according to the specific situation (such as the change range of obstacles and the degree of blockage of the original path). If it is decided to re-evaluate, move this node from the closed list back to the open list and process it again according to the above process.

[0062] The above loop exploration operation is repeated until the open list is empty, which means that starting from the starting point, a feasible path to the target point cannot be found based on the current map information, and the planning fails; Or the target node is successfully located and the optimal path is successfully traced back. At this time, the path planning is successfully completed.

[0063] Furthermore, the process of path planning performed by the local obstacle avoidance algorithm is as follows: Construct potential fields, including gravitational potential fields and repulsive potential fields; The construction process of the gravitational potential field is as follows: Taking the position of the target bolt as the center of the gravitational source, construct the gravitational potential field function U att (q), where q is the current position of the robot; Uatt(q)=1 / 2k att (q−q target ) 2 , katt is the gravitational coefficient, and its value is determined based on the robot's dynamic performance, the expected approach speed and other factors to ensure that the gravitational strength is moderate, which can effectively guide the robot to move toward the target, and will not cause the robot to lose control of its speed when approaching the target due to excessive gravity. The direction of gravity always points to the target point. As the distance between the robot and the target point decreases, the gravitational potential field strength increases, prompting the robot to accelerate toward the target; The construction process of the repulsive potential field is as follows: When the dynamic obstacles are detected in real time by the laser radar and the visual camera, the actual position of each obstacle is taken as the center of the repulsive source to construct the repulsive potential field function Urep(q, o i ), where o i is the position of the i-th obstacle; The repulsive potential field function adopts the following form: When the robot is at a distance d(q, o i )≤r0 (r0 is the obstacle impact radius, which is set according to the robot's overall dimensions and safety buffer distance requirements, and is generally 1.5-2 times the robot's maximum overall dimensions), U rep (q,o i )=1 / 2k rep (1 / d(q,o i )-1 / r0) 2 , k rep is the repulsion coefficient, and its value is related to factors such as the robot's mass and the maximum tolerable collision force. It ensures that a sufficiently strong repulsion force can be generated when the robot comes into close contact with an obstacle, so that the robot can quickly move away and avoid collision.

[0064] When the distance between the robot and the obstacle d(q, oi)>r0, U rep(q, oi) = 0, that is, after exceeding the influence radius of the obstacle, the repulsive force disappears, and the robot is not disturbed by the repulsive force of the obstacle. The direction of the repulsive force is from the obstacle to the robot, preventing the robot from approaching the obstacle; Determine the moving direction: At each decision moment (for example, every 0.1 seconds, depending on the real-time requirements of the robot's motion control and the computing resource affordability), the robot calculates the gravitational force F according to its current position q. att (q) and the repulsive force F from each obstacle rep (q,o i ); Gravity F att (q) By the gravitational potential field function U att (q) is derived, and in a two-dimensional plane, if q=(x,y), q target =(x target ,y target ), then F att The component form of (q) is F att,x = −k att (x− xtarget ), F att,y = −k att (y−y target ).

[0065] Repulsion F rep (q,o i ) by repulsive potential field function Urep(q,o i ) is derived, and in the two-dimensional plane, according to the distance formula , where (xoi,yoi) is the coordinate of the ith obstacle; When d(q,o i )≤r0: ; ; When d(q,o i )>r0, F rep,x =F rep,y =0; Calculate the resultant force F(q): vector sum the gravitational force and all repulsive forces, .

[0066] The direction of the robot's movement is determined according to the direction of the resultant force, that is, the robot moves in the direction of the resultant force. For example, if the component of the resultant force in the two-dimensional plane is F(q)=(Fx,Fy), then the robot's moving direction angle θ=arctan2(Fy,Fx). Based on this angle, the robot adjusts its own moving direction to ensure that it avoids obstacles while approaching the target; Dealing with local minima: Local minimum detection: During the movement of the robot, the robot continuously monitors its motion state and checks the robot's movement distance during this period at preset time intervals (for example, every 3 seconds, which is reasonably selected according to the robot's motion characteristics and the complexity of the environment). If it is found that the robot moves a very small distance (for example, less than 0.05 meters) in multiple consecutive such time intervals, and the resultant force approaches zero, that is, |F(q)|<ϵ (ϵ is the set threshold, which is determined based on factors such as the robot's power accuracy and sensor accuracy, and is generally 1-2 times the robot's minimum perceptible force), then the robot is judged to be in a local minimum dilemma; Random perturbation strategy: When a local minimum is detected, the robot's moving direction or speed is randomly changed within a preset range to help the robot get out of trouble. For example, a new moving direction angle θnew=θ+random(−10,10) is randomly generated within the range of ±10∘, and the moving speed vnew=v+random(−5,5) can be randomly adjusted within the range of ±5mm / s, where θ and \v) are the robot's current moving direction angle and speed, and random(−10,10) means generating a random number between -10 and 10. This random perturbation breaks the deadlock and prompts the robot to find a feasible path again.

[0067] Setting a virtual target point: If the random perturbation strategy does not work well and it is difficult to get out of trouble quickly, set a virtual target point. Select a point that is far away from the current position and unobstructed as the virtual target point. For example, within the robot's visual range, based on the map information, select a point that is located in an open area and at least 1 meter away from the current position. Re-follow the above-mentioned potential field construction and resultant force calculation methods to guide the robot to the virtual target point first, and then gradually approach the real target to achieve flexible obstacle avoidance, ensuring that the robot can continue to move towards the target and avoid being trapped in the local minimum area.

[0068] The A* algorithm is used for global path planning to provide the robot with a macroscopic optimal path from the starting position to the target bolt position. The local obstacle avoidance algorithm (artificial potential field method) is used to adjust the local path when the robot encounters dynamic obstacles and faces the risk of immediate collision. The two complement each other to ensure that the robot can complete maintenance tasks safely and efficiently in a complex and dynamic truss crane track environment. Improve path planning efficiency and accuracy: The dynamic path planning algorithm based on the improved A* algorithm provides an accurate environmental model for path planning by constructing a high-resolution map, accurately marking the track area, fixed obstacles, starting position and target position. By using the open list and closed list, combined with the evaluation function f(n) to filter nodes, the nodes with low cost are explored first, which greatly reduces the search range and improves planning efficiency. At the same time, the backtracking mechanism ensures that the optimal path from the starting point to the target point is found, ensuring that the robot can efficiently reach the target position and reduce unnecessary movement and energy consumption.

[0069] Enhanced environmental adaptability and dynamic adjustment capabilities: In a dynamic environment, when obstacles move or the environment changes temporarily, the algorithm can re-evaluate the explored nodes and move the potentially affected nodes from the closed list back to the open list for reprocessing, enabling the robot to adjust the path in time to adapt to environmental changes, ensuring that the path is always optimal, avoiding path planning failure due to environmental changes, and improving the robot's adaptability and reliability in complex dynamic environments.

[0070] Realize real-time obstacle avoidance and safe operation: The local obstacle avoidance algorithm constructs gravitational potential field and repulsive potential field to sense dynamic obstacles in real time. The gravitational potential field guides the robot to move toward the target bolt, and the repulsive potential field generates a reverse force when the robot approaches the obstacle to prevent it from approaching. By calculating the combined force of gravity and repulsion to determine the direction of movement, the robot can avoid dynamic obstacles in real time, ensure its own safety, and successfully complete the task.

[0071] Solve the local minimum problem: During the local obstacle avoidance process, the robot may fall into the local minimum dilemma, that is, the resultant force approaches zero and the robot cannot move further. The local obstacle avoidance algorithm detects local minima by continuously monitoring the robot's motion state. Once detected, a random perturbation strategy is used to randomly change the robot's movement direction or speed to break the deadlock, prompting the robot to find a feasible path again, avoiding the robot from being trapped in the local minimum area and ensuring that it can continue to move towards the target.

[0072] The functions of the scheduling management module include parsing after receiving the instruction and extracting key information, including task priority, bolt position sequence, tightening torque requirements and task time limit; Build and prioritize task queues; Combine environmental perception to carry out path planning and task adjustment; System coordination and command sending; Task completion and status feedback.

[0073] Furthermore, the specific process of task queue construction and priority sorting is as follows: According to the task information obtained by parsing, a task queue is constructed. The task queue is implemented using a priority queue data structure, such as using a heap sort algorithm to maintain the priority order of the queue. High-priority tasks will be placed at the front of the queue and processed first; Prioritize by: The determination of task priority takes into account multiple factors, including the importance of bolts (bolts on key equipment have a higher priority), the urgency of the task (bolt maintenance tasks with impending failure warnings have a higher priority) and the time limit of the task; For tasks with the same priority, they are sorted according to the location of the bolts, and tasks closer to the current robot position are prioritized to reduce the robot's movement time and energy consumption; The process of path planning and task adjustment combined with environmental perception is as follows: Maintain real-time data interaction with the lidar, visual camera system and sensor fusion module of the perception layer to obtain dynamic information of the current environment, including the location, type and movement status of obstacles; this information will be used for path planning and dynamic adjustment of tasks; Path planning and task allocation: Based on the current task queue and environmental perception data, call the path planning algorithm module (such as the dynamic path planning algorithm improved based on the A* algorithm) to plan the optimal path for each task; During the planning process, the movement trend of dynamic obstacles is considered and their future positions are predicted to avoid path conflicts; When a dynamic obstacle is detected on the path and is expected to stay for a long time, affecting the execution of the current task, the system determines whether to suspend the current path based on the task priority and execute a nearby bolt maintenance task of the same or higher priority instead; When an unexpected situation occurs that makes it impossible to execute a task as planned, such as an obstacle or equipment failure, the task scheduling and management module will start the task re-planning mechanism; First, the current task queue is re-evaluated, and the execution order of tasks is adjusted according to their priority and remaining time. Then, the path is re-planned to ensure that the robot can complete the remaining tasks efficiently.

[0074] The specific contents of task completion and status feedback are as follows: Task completion judgment: When the robot completes the inspection task of a bolt, the tightening system will feedback the task completion information, including the tightening result (whether the specified torque is reached) and the actual tightening time; The scheduling management module determines whether the task is successfully completed based on the task completion information; If the task is not completed successfully, the system will decide whether to retry or adjust the task strategy based on the specific situation; Status feedback: the task completion status and related data are fed back to the background monitoring system in real time through the communication system. At the same time, the task queue is updated and the completed tasks are removed from the queue. If there are still tasks remaining in the task queue, the task scheduling and execution will continue according to the above process until all maintenance tasks are completed. The truss crane track maintenance robot integrates drive system, communication system, tightening device, visual recognition, background monitoring, information processing, etc. It has the characteristics of strong mobility and high accuracy. It not only meets the requirements of Baiyinhua Aluminum and Electricity Company for truss crane bolt maintenance operations, but also reduces the daily work intensity of truss crane maintenance workers. It realizes the observation and monitoring of the bolt status on the truss crane, which can greatly reduce the use risks and safety hazards of equipment, reduce the long-term high-altitude operations of maintenance workers, and avoid maintenance workers working in high-dust environments for a long time, thereby improving the personal safety and occupational health of workers.

[0075] The robot uses the on-site truss crane track as a walking track and runs on a single track. When the robot is needed for operation, it is hoisted to the required position. After the robot is docked with the track manually, the clamping mechanism clamping button is pressed. After the clamping wheel is clamped, the robot is started to start the bolt maintenance operation. The robot moves along the track, and after the 3D camera recognizes and locates the bolt, it controls the tightening mechanism on the robot to tighten the nut.

[0076] The robot is controlled by autonomous / wireless remote control. After the robot is hoisted on the gantry track, communication can be established between the robot and the tablet computer, and the robot can be started by real-time remote control. After starting, the robot will automatically run and perform automatic maintenance according to the preset maintenance operation plan.

[0077] The robot has obstacle avoidance detection and automatic collision avoidance functions. Double safety protection is built by installing a buffer energy absorption limit device and a laser distance measurement device on the robot.

[0078] The robot is equipped with a lifting interface, and the robot can be placed on and removed from the track by lifting with the help of a truck crane.

[0079] The robot consists of an electric control system, a tightening system, an obstacle avoidance system, a walking system, a clamping system and a visual inspection system. It adopts an integrated body structure and is compact. The robot is 668mm wide and the distance from the center of the device to the outermost side of the device is 334mm, which meets the requirements of the narrow working space on site (the distance between the center of the track and the wall column is 420mm). Due to the high-intensity magnetic field on site, the robot's anti-magnetic shell structure and the electrical component shielding box mechanism are designed. The robot's electrical components are installed in the anti-magnetic box, and the whole is protected by an anti-magnetic shell, which can adapt to the strong magnetic and high dust environment of 0-600GS on site.

[0080] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0081] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0082] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. The autonomous path matching system based on dynamic object adaptive collaborative robot is characterized by: include: Data collection layer, decision-making layer and execution layer; The data acquisition layer is used for track data acquisition and image information acquisition. The data acquisition layer includes a laser radar and a visual camera installed on the robot; The decision-making layer includes a path planning algorithm module and a scheduling management module, wherein the path planning algorithm module is used for path planning, and the scheduling management module is used for task scheduling; The execution layer includes a walking drive unit and a communication unit. The walking drive unit is the driving motor of the robot, which is used to drive the robot according to the planned path after receiving the scheduling task. The communication unit is used to provide communication support for the robot.

2. The path autonomous matching system based on the dynamic object adaptive collaborative robot according to claim 1 is characterized in that: A cleaning device is provided outside the laser radar on the robot, which is used to clean the laser radar when a preset condition is triggered; After the robot is hoisted onto the gantry crane track and docked with the track, the laser radar and visual camera start the self-inspection program for self-inspection, and data collection is carried out after the self-inspection passes.

3. The path autonomous matching system based on the dynamic object adaptive collaborative robot according to claim 2 is characterized in that: The process of triggering the preset condition is as follows: The robot is also equipped with a dust sensor and an optical contrast detection module to monitor the area near the laser emission and receiving windows; The dust sensor detects the concentration change of suspended particles in the air. When the dust concentration exceeds the preset slight pollution threshold, it determines that there may be dust impact, and controls the cleaning device to perform external cleaning operations on the lidar. After the optical contrast detection module emits a beam of low-power calibration light, it compares the contrast of the received light with the preset pure optical element reference contrast. If the contrast decreases by more than the preset value, it means that the exterior of the LiDAR may be contaminated, and the cleaning device is automatically started for cleaning; The self-test contents of the laser radar include: optical path calibration, signal strength and stability test, and scanning frequency verification; When the optical path calibration is completed, the signal strength and stability tests are passed, and the scanning frequency calibration is passed, it means that the LiDAR self-test has passed; The self-test of the visual camera includes image acquisition test, 3D camera depth calibration, panoramic vision camera lens stitching effect check, optical image stabilization function test and deep learning model initialization check; When the image acquisition test, 3D camera depth calibration, panoramic vision camera lens stitching effect check, optical image stabilization function test and deep learning model initialization check are all passed, it means that the vision camera system self-test has passed.

4. The path autonomous matching system based on the dynamic object adaptive collaborative robot according to claim 1 is characterized in that: The path planning algorithm module uses a dynamic path planning algorithm and a local obstacle avoidance algorithm improved based on the A* algorithm for path planning.

5. The path autonomous matching system based on dynamic object adaptive collaborative robot according to claim 1, characterized in that: The process of path planning based on the dynamic path planning algorithm improved by the A* algorithm is as follows: First, map construction is performed: using the robot's pre-stored precise size and shape data of the truss crane track, as well as the surrounding fixed facility information collected and processed by the laser radar and visual camera, a high-resolution two-dimensional or three-dimensional grid map is constructed; The fineness of the grid is set according to the robot's operational accuracy requirements and the complexity of the environment; On the map, the truss track area is marked with a specific symbol, and a lower travel cost value is set for this area; Mark the grid cell where the fixed obstacle is located as inaccessible, and set the travel cost to infinity; At the same time, the robot's starting position and the target position of each bolt to be inspected are accurately marked; After that, perform list initialization: create an open list and a closed list. The open list is used to temporarily store nodes whose surrounding situations need to be further explored, and the closed list is used to record nodes that have completed exploration and whose surrounding information is known; Take the starting point as the first node and put it into the open list, and calculate its key attribute values: Actual cost g(n): The actual cost of moving from the starting point to the current node n. The initial value is set to 0. The moving cost here is measured by the distance the robot moves on the track and is calculated using the Euclidean distance formula. If the starting point coordinates are (x0, y0) and the current node coordinates are (x, y), then ; Estimated cost h(n): The estimated cost of moving from the current node n to the target point, calculated using a heuristic function, h(n)=|x−x target ∣+∣y−y target ∣, where (x target ,y target ) is the target bolt position coordinate; Evaluation function value f(n): f(n)=g(n)+h(n). This value determines the exploration priority of nodes in the open list. The smaller the value, the more优先 explored; Perform loop exploration: Continuously select the node with the smallest evaluation function value f(n) from the open list, designate it as the current node, remove this node from the open list, and add it to the closed list; Check whether the current node completely coincides with the target bolt position. If it coincides, it means that a feasible path from the starting point to the target point has been found. At this time, through backtracking operations, starting from the target node, follow the parent node pointers of each previously recorded node in turn and backtrack to the starting node. The nodes are concatenated to form a complete travel path, and the path planning process ends; Adjacent node processing: If the current node is not the target node, explore its adjacent nodes. Adjacent nodes usually include neighbor nodes in the up, down, left, right, and diagonal directions, depending on the actual movement ability of the robot and the map discretization accuracy; For each adjacent node m: First, check whether it is within the valid range of the map and does not belong to the fixed obstacle area. If it does not meet the conditions, directly skip this node and do not process it further; If it meets the conditions, calculate the new actual cost g′(m) from the starting point through the current node n to the adjacent node m, g′(m)=g(n)+cost(n, m), where cost(n, m) is the movement cost from node n to node m, moving between adjacent nodes in the straight track area; Recalculate the estimated cost h(m) of the adjacent node m. The calculation method is the same as the previous calculation of h(n). Use a suitable heuristic function to estimate the remaining path length based on the target bolt position and the adjacent node position; Obtain the new evaluation function value f′(m)=g′(m)+h(m); If the adjacent node m is neither in the open list nor in the closed list, add it to the open list, set its parent node as the current node n, and update its g(m), h(m), and f(m) values to the above calculated values; If the adjacent node m is already in the open list, compare the newly calculated f′(m) value with the f(m) value of this node in the original open list: If f′(m)<f(m), it means that a better path to reach this node has been found. At this time, update the f(m) value, g(m) value, and parent node of this node in the open list to the current node n; If the adjacent node m is already in the closed list, in a dynamic environment, if the original path is no longer optimal due to obstacle movement or temporary environmental changes, decide whether to re-evaluate this node and its subsequent nodes according to the specific situation. If it is decided to re-evaluate, move this node from the closed list back to the open list and reprocess it according to the above process; The above loop exploration operation is repeated until the open list is empty, which means that starting from the starting point, a feasible path to the target point cannot be found based on the current map information, and the planning fails; Or the target node is successfully located and the optimal path is successfully traced back. At this time, the path planning is successfully completed.

6. The path autonomous matching system based on the dynamic object adaptive collaborative robot according to claim 4 is characterized in that: The process of path planning by the local obstacle avoidance algorithm is as follows: Construct potential fields, including gravitational potential fields and repulsive potential fields; The construction process of the gravitational potential field is as follows: Taking the position of the target bolt as the center of the gravitational source, construct the gravitational potential field function U att (q), where q is the current position of the robot; Uatt(q)=1 / 2k att (q−q target ) 2 , katt is the gravitational coefficient; The construction process of the repulsive potential field is as follows: When the dynamic obstacles are detected in real time by the laser radar and the visual camera, the actual position of each obstacle is taken as the center of the repulsive source to construct the repulsive potential field function Urep(q, o i ), where o i is the position of the i-th obstacle; The repulsive potential field function adopts the following form: When the robot is at a distance d(q, o i )≤r0, U rep (q,o i )=1 / 2k rep (1 / d(q,o i )-1 / r0) 2 , k rep is the repulsion coefficient; When the distance between the robot and the obstacle d(q, oi)>r0, U rep (q, oi) = 0, that is, after exceeding the influence radius of the obstacle, the repulsive force disappears, and the robot is not disturbed by the repulsive force of the obstacle. The direction of the repulsive force is from the obstacle to the robot, preventing the robot from approaching the obstacle; Determine the moving direction: At each decision moment, the robot calculates the gravitational force F according to its current position q att (q) and the repulsive force F from each obstacle rep (q,o i ); Gravity F att (q) By the gravitational potential field function U att (q) is derived, and in a two-dimensional plane, if q=(x,y), q target =(x target ,y target ), then F att The component form of (q) is F att,x = −k att (x− xtarget ), F att,y = −k att (y−y target ); Repulsion F rep (q,o i ) by repulsive potential field function Urep(q,o i ) is derived, and in the two-dimensional plane, according to the distance formula , where (xoi,yoi) is the coordinate of the ith obstacle; When d(q,o i )≤r0: ; ; When d(q,o i )>r0, F rep,x =F rep,y =0; Calculate the resultant force F(q): vector sum the gravitational force and all repulsive forces, ; The moving direction of the robot is determined according to the direction of the resultant force, that is, the robot moves in the direction of the resultant force; If the component of the resultant force in the two-dimensional plane is F(q)=(Fx,Fy), then the robot's moving direction angle θ=arctan2(Fy,Fx); Dealing with local minimum: Local minimum detection: The robot continuously monitors its motion status during movement, and checks the robot's movement distance during this period at preset time intervals; If it is found that the robot moves a very small distance in multiple consecutive such time intervals and the resultant force approaches zero, that is, |F(q)|<ϵ, then it is judged that the robot is trapped in a local minimum dilemma; Random perturbation strategy: When a local minimum is detected, in order to help the robot get out of trouble, the robot's moving direction or speed is randomly changed within a preset range, prompting the robot to find a feasible path again.

7. The path autonomous matching system based on dynamic object adaptive collaborative robot according to claim 1, characterized in that: The functions of the scheduling management module include parsing after receiving the instruction and extracting key information, including task priority, bolt position sequence, tightening torque requirements and task time limit; Build and prioritize task queues; Combine environmental perception to carry out path planning and task adjustment; System coordination and command sending; Task completion and status feedback.

8. The path autonomous matching system based on the dynamic object adaptive collaborative robot according to claim 7 is characterized in that: The specific process of task queue construction and priority sorting is as follows: According to the task information obtained by parsing, a task queue is constructed. The task queue is implemented using a priority queue data structure. High-priority tasks will be placed at the front of the queue and processed first. Prioritize by: The determination of task priority takes into account multiple factors, including the importance of the bolt, the urgency of the task and the time limit of the task; For tasks with the same priority, they are sorted according to the location of the bolts, giving priority to tasks that are closer to the current robot position; The process of path planning and task adjustment combined with environmental perception is as follows: Maintain real-time data interaction with the lidar, visual camera system and sensor fusion module of the perception layer to obtain dynamic information of the current environment, including the location, type and movement status of obstacles; Path planning and task allocation: Based on the current task queue and environmental perception data, the path planning algorithm module is called to plan the optimal path for each task; During the planning process, the movement trend of dynamic obstacles is considered and their future positions are predicted to avoid path conflicts; When a dynamic obstacle is detected on the path and is expected to stay for a long time, affecting the execution of the current task, the system determines whether to suspend the current path based on the task priority and execute the bolt maintenance task with the same or higher priority nearby; When an emergency occurs and the task cannot be executed as planned, the task scheduling and management module will start the task re-planning mechanism; First, re-evaluate the current task queue, adjust the execution order of tasks according to their priorities and remaining time, and then re-plan the path; The specific contents of task completion and status feedback are as follows: Task completion judgment: when the robot completes the inspection task of a bolt, the tightening system will feedback the task completion information, including the tightening result and the actual tightening time; The scheduling management module determines whether the task is successfully completed based on the task completion information; If the task is not completed successfully, the system will decide whether to retry or adjust the task strategy based on the specific situation; Status feedback: The task completion status and related data are fed back to the background monitoring system in real time through the communication system. At the same time, the task queue is updated and the completed tasks are removed from the queue. When there are remaining tasks in the task queue, the task scheduling and execution continue according to the above process until all maintenance tasks are completed.

Images