A dynamic optimization method for robot's flexible operation space in complex scenarios

Abstract

The present invention discloses a method for dynamically optimizing the flexible operating space of a robot in complex scenarios. By acquiring point cloud information of scenes and objects through laser radars, depth cameras, etc., multi-algorithm fusion is used for denoising and optimization processing, and the center of mass is accurately extracted and the posture is dynamically adjusted. The Monte Carlo algorithm is used to calculate the flexible workspace of the robot arm, and the operation boundary is precisely described through the spatial envelope diagram, and the optimal operation path is achieved by combining inverse kinematics solution. By combining the inverse posture adjustment strategy with real-time collision judgment, high-degree-of-freedom safe operation in complex environments is ensured. This method significantly improves the adaptability and operation success rate of the robot in complex stacking scenarios, reduces dependence on high-cost sensors, and achieves flexible and precise grasping.

Description

Technical Field

[0001] The present invention relates to the field of robot operation optimization and automation control technology, and in particular to a method for dynamically optimizing a robot's flexible operation space in complex scenarios. Background Art

[0002] The ability of mobile robots to operate in complex scenarios is crucial for fields like industrial automation and warehousing and logistics. This is especially true when handling irregularly shaped and complexly stacked objects. Traditional static manipulation methods often struggle to meet the demands for efficient and precise operation. Typically, mobile robots perceive their environment through lidar, visual sensors, and other sensors, combined with path planning algorithms to enable positioning and grasping by robotic arms. However, existing technologies face the following challenges in complex scenarios:

[0003] 1. Limitations of path planning and operating space: Traditional robotic operations rely heavily on preset path planning and a static workspace. This approach lacks flexibility in the face of changing scenarios, resulting in limited operating points for the robotic arm and an inability to achieve optimal grasping in multiple degrees of freedom. This is particularly true when handling stacked, misplaced, or irregular objects, resulting in a low success rate.

[0004] 2. Point cloud data processing is complex and has limited accuracy: Existing technologies typically collect point cloud data using depth cameras and optimize it using RANSAC algorithms and filtering to remove noise. However, this process is easily affected by ambient lighting and noise, resulting in insufficient object recognition and positioning accuracy, making efficient operation difficult in complex scenarios.

[0005] 3. The conflict between robotic arm kinematics and collision avoidance: In complex scenarios, robotic arm operation requires multi-step inverse kinematics and obstacle avoidance strategies. Currently, common collision avoidance methods rely on static settings and are unable to dynamically adjust the robotic arm's posture and path in real time. This results in low operational efficiency, an inability to flexibly respond to environmental changes, and a high risk of collision.

[0006] 4. Existing optimization methods have poor adaptability and high costs: To cope with complex operations, the industry sometimes uses high-precision sensors or complex algorithms to improve recognition and operation accuracy. However, such methods not only increase the complexity and cost of the system, but also are difficult to popularize in large-scale practical applications.

[0007] Therefore, how to achieve dynamic optimization of the robot arm's operating space in complex scenarios, improve grasping accuracy and success rate, and reduce dependence on high-cost sensors has become the technical problem to be solved by the present invention. Summary of the Invention

[0008] The technical problem solved by the present invention is to address the defects existing in the above-mentioned existing technologies and provide a dynamic optimization method for the flexible operation space of robots in complex scenarios, so as to solve the problems proposed in the above-mentioned background technologies such as limited operation space, insufficient operation accuracy, poor obstacle avoidance ability and high system cost of the robotic arm in complex scenarios.

[0009] In order to solve the above technical problems, the technical solutions adopted by the present invention are as follows:

[0010] A method for dynamically optimizing a robot's flexible operating space in complex scenarios includes the following steps:

[0011] S1: Control the mobile robot to move to the position to be operated. The mobile robot includes the mobile chassis equipped with a laser radar. Based on the laser radar navigation and the visual system of the depth camera, the mobile robot autonomously avoids obstacles through the ROS system and moves to a feature scene and stops.

[0012] S2: Use the depth camera to obtain point cloud information of the feature scene and the item to be operated, suppress and denoise the object point cloud information, remove irrelevant scene point clouds, and obtain high-quality point cloud information;

[0013] S3: Construct the scene using the RANSAC algorithm and the minimization of project squares method, obtain the point cloud information of the scene, calculate the center of mass of the project point cloud and define it as the operation target;

[0014] S4: Calculate the approach workspace of the manipulator using the Monte Carlo algorithm, obtain the operating points of the flexible workspace through inverse kinematics, sample the flexible workspace and calculate its spatial envelope;

[0015] S5: Maximize the intersection of the flexible workspace and the object point cloud, calculate the position transformation of the mobile robot based on the maximum intersection, and guide the point cloud of the object to be operated into the flexible workspace;

[0016] S6: Based on the optimal posture transformation information, the mobile structure is controlled to move to the optimal operation space position, so that the flexible workspace of the robot arm and the point cloud information of the feature scene are optimally coupled, thereby achieving a high success rate of operation.

[0017] As a further solution of the present invention, the point cloud optimization algorithm in step S2 includes suppression and noise removal to remove irrelevant point clouds, improve computational efficiency, and generate a maximum spatial envelope diagram.

[0018] As a further solution of the present invention, the scene plane in step S3 includes obtaining a plane equation using a RANSAC algorithm, and performing vertical calculation on the algorithm support of the plane as the Z axis to segment the scene plane and the project point cloud.

[0019] As a further solution of the present invention, the flexible workspace calculation in step S4 includes:

[0020] Monte Carlo sampling of the robot's adjacent workspace;

[0021] Monte Carlo sampling is performed on the adjacent workspace of the robot arm. The operation point position is fixed and rotated around the x, y, and z axes in steps of 30°. For each posture, it is verified whether an inverse kinematic solution exists. The solution is the operation point in the flexible workspace.

[0022] As a further solution of the present invention, the posture transformation in step S5 includes:

[0023] Based on the calculation of the object point cloud centroid, guide the object point cloud centroid to move along the preset path to the center point of the robot arm base coordinate system;

[0024] Adjust the project point cloud layout according to the optimized intersection, so that the project can fully enter the flexible workspace.

[0025] As a further solution of the present invention, step S5 also includes workspace adaptation adjustment. When the project point cloud cannot fully adapt to the flexible workspace, the posture of the mobile robot structure is adjusted to achieve partial intersection between the project point cloud and the robotic arm workspace.

[0026] As a further solution of the present invention, step S5 further includes collision parameters and adjustments. When the robotic arm moves to the collision parameter limit, it stops moving and adjusts its position to maximize the coverage of the workspace.

[0027] As a further solution of the present invention, the optimized operating space position in step S6 is obtained by inverse posture adjustment calculation, and the adjustment enables the robotic arm to maintain multi-degree-of-freedom flexibility in complex scenes, thereby achieving the best operating effect.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. Flexible workspace optimization based on spatial envelope diagram: This invention specifically introduces the calculation and application of spatial envelope diagram in the calculation of the flexible workspace of the robot arm. This method is not limited to simple accessibility verification, but also describes the morphological boundary of the entire flexible workspace through the envelope diagram, providing more accurate data support for subsequent operation optimization. Compared with the traditional single workspace description method, the introduction of the spatial envelope diagram can intuitively reflect the operating boundary of the robot arm, making the adjustment of the flexible workspace more refined and dynamic, thereby completing tasks more flexibly in complex scenarios.

[0030] 2. Precise coordination of point cloud centroid guidance and robotic arm pose transformation: This invention calculates the center of mass of the object's point cloud and uses its pose to guide the robotic arm's operating position. This strategy is rare in the prior art. It particularly addresses the challenge of optimizing the operating position when grasping irregular objects. By dynamically adjusting the center of mass, the robotic arm's pose changes, placing the object within the optimal grasping area, significantly improving the grasping success rate. This precise coordination mechanism avoids the limitations of traditional path planning when handling complex objects.

[0031] 3. Innovative Design Combining a Reverse Posture Adjustment Strategy with Real-Time Collision Detection: The combination of the reverse posture adjustment strategy and real-time collision parameter detection in this invention is a key innovation in ensuring operational safety and flexibility. When adjusting the robot's operating path, real-time collision detection dynamically corrects the operating posture, avoiding potential collisions between the robot and the environment. This combination is particularly advantageous in complex scenarios, enabling precise manipulation with a high degree of freedom. This represents a significant breakthrough in static obstacle avoidance methods, ensuring both flexibility and safety.

[0032] 4. Efficient Point Cloud Denoising and Optimization in Complex Stacked Scenes: For point cloud data in complex stacked scenes, this invention uses a depth camera to acquire multi-viewpoint point cloud information and combines it with unique denoising techniques to effectively remove irrelevant point clouds, improving computational efficiency and data quality. Traditional point cloud processing often suffers from significant noise interference, while this invention's denoising and optimization process ensures the integrity of point cloud information while significantly reducing the impact of invalid data on operational path planning, enhancing the system's adaptability in complex scenarios.

[0033] 5. Multi-step joint optimization achieves high-degree-of-freedom adaptability to multiple scenarios: This invention utilizes a multi-step optimization design, encompassing the entire process from initial positioning, workspace sampling, posture adjustment, to final operation. This enables the system to flexibly cope with various uncertainties in complex scenarios. In particular, it can dynamically adjust operational strategies to improve success rates when handling objects of varying sizes and shapes. Compared to existing fixed-process operation methods, this approach offers greater operational freedom and adaptability to various scenarios.

[0034] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 4 is a flowchart of a software recommendation method in an embodiment of the present invention.

[0037] Figure 2 2 is a schematic diagram of the structure of a software recommendation system in an embodiment of the present invention.

[0038] In the figure: 1. LiDAR; 2. Mobile chassis; 3. Robotic arm; 4. Camera; 5. Gripper; 6. Feature scene; 7. Object to be operated. DETAILED DESCRIPTION

[0039] The following is a clear and complete description of the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present invention.

[0040] See also Figure 1 —2. In an embodiment of the present invention, a method for dynamically optimizing a robot's flexible operating space in a complex scenario includes the following steps:

[0041] S1: Control the mobile robot to move to the position to be operated. The mobile robot includes the mobile chassis equipped with a laser radar. Based on the laser radar navigation and the visual system of the depth camera, the mobile robot autonomously avoids obstacles through the ROS system and moves to a feature scene and stops.

[0042] S2: Use the depth camera to obtain point cloud information of the feature scene and the item to be operated, suppress and denoise the object point cloud information, remove irrelevant scene point clouds, and obtain high-quality point cloud information;

[0043] S3: Construct the scene using the RANSAC algorithm and the minimization of project squares method, obtain the point cloud information of the scene, calculate the center of mass of the project point cloud and define it as the operation target;

[0044] S4: Calculate the approach workspace of the manipulator using the Monte Carlo algorithm, obtain the operating points of the flexible workspace through inverse kinematics, sample the flexible workspace and calculate its spatial envelope;

[0045] S5: Maximize the intersection of the flexible workspace and the object point cloud, calculate the position transformation of the mobile robot based on the maximum intersection, and guide the point cloud of the object to be operated into the flexible workspace;

[0046] S6: Based on the optimal posture transformation information, the mobile structure is controlled to move to the optimal operation space position, so that the flexible workspace of the robot arm and the point cloud information of the feature scene are optimally coupled, thereby achieving a high success rate of operation.

[0047] As a further solution of the present invention, the point cloud optimization algorithm in step S2 includes suppression and noise removal to remove irrelevant point clouds, improve computational efficiency, and generate a maximum spatial envelope diagram.

[0048] As a further solution of the present invention, the scene plane in step S3 includes obtaining a plane equation using a RANSAC algorithm, and performing vertical calculation on the algorithm support of the plane as the Z axis to segment the scene plane and the project point cloud.

[0049] As a further solution of the present invention, the flexible workspace calculation in step S4 includes:

[0050] Monte Carlo sampling of the robot's adjacent workspace;

[0051] Monte Carlo sampling is performed on the adjacent workspace of the robot arm. The operation point position is fixed and rotated around the x, y, and z axes in steps of 30°. For each posture, it is verified whether an inverse kinematic solution exists. The solution is the operation point in the flexible workspace.

[0052] As a further solution of the present invention, the posture transformation in step S5 includes:

[0053] Based on the calculation of the object point cloud centroid, guide the object point cloud centroid to move along the preset path to the center point of the robot arm base coordinate system;

[0054] Adjust the project point cloud layout according to the optimized intersection, so that the project can fully enter the flexible workspace.

[0055] As a further solution of the present invention, step S5 also includes workspace adaptation adjustment. When the project point cloud cannot fully adapt to the flexible workspace, the posture of the mobile robot structure is adjusted to achieve partial intersection between the project point cloud and the robotic arm workspace.

[0056] As a further solution of the present invention, step S5 further includes collision parameters and adjustments. When the robotic arm moves to the collision parameter limit, it stops moving and adjusts its position to maximize the coverage of the workspace.

[0057] As a further solution of the present invention, the optimized operating space position in step S6 is obtained by inverse posture adjustment calculation, and the adjustment enables the robotic arm to maintain multi-degree-of-freedom flexibility in complex scenes, thereby achieving the best operating effect.

[0058] Example 1:

[0059] See also Figure 1 and Figure 2 , Figure 1 It is a flow chart of a method for optimizing the operating space of a mobile robot in a complex scene. Figure 2 middle, is the world coordinate system; is the camera coordinate system; is the car coordinate system; is the table screen characteristic coordinate system; is the coordinate system of the object point cloud centroid; the method includes:

[0060] S1: Control the mobile robot to move to the position to be operated.

[0061] Mobile chassis 2 is equipped with a laser radar 1. The ROS system controls the mobile robot for navigation, allowing it to autonomously avoid obstacles and stop in front of a feature scene 6. During this process, its position deviates from the ideal operating position due to the accumulated errors of laser navigation and the drift of the inertial navigation unit. This deviation ensures that the field of view of the depth camera 4 at the end of the robotic arm 3 includes the feature scene 6 and the object to be manipulated 7 on it.

[0062] S2: Obtain the point cloud information of the operation plane and the objects to be operated in the scene.

[0063] The depth camera 4 is used to collect point cloud information of some feature scenes 6 and objects to be operated 7. The point cloud information is filtered and denoised using a point cloud optimization algorithm to remove irrelevant scene point clouds, improve computing efficiency, and obtain high-quality point cloud information. The point cloud information is then used as a maximum spatial envelope diagram.

[0064] S3. Fit the scene plane and extract the point cloud information of objects above the scene.

[0065] Use RANSAC and the least squares method to fit the feature scene plane 6 information, obtain the fitted plane equation, calculate the normal vector perpendicular to this plane, define it as the z-axis, and segment the point cloud information on the scene plane 6 where z>0, leaving only the point cloud of the object 7 to be operated.

[0066] S4. Calculate the flexible workspace of the robotic arm;

[0067] First, use the Monte Carlo algorithm to calculate the reachable workspace of robot arm 3. Then adjust the posture of the midpoint of the reachable workspace to verify whether its inverse kinematics has a solution. If a solution is found, it is the operating point of the flexible workspace. After the flexible workspace is sampled, its spatial envelope is calculated.

[0068] S5. Maximize the intersection of the flexible workspace and the object point cloud, and calculate the mobile robot's pose transformation based on the maximum intersection;

[0069] The point cloud of the object to be operated 7 is subjected to an offset and other posture transformations from the initial position toward the direction of the flexible workspace of the robot arm 3. When this point cloud just completely enters the flexible workspace, it is defined as the optimal intersection.

[0070] Point cloud centroid calculation and pose guidance: Based on the point cloud data of the object to be grasped, the object's center of mass is calculated and moved along a predetermined path toward the center of the robot's base coordinate system. During this movement, the pose of the object's point cloud is adjusted to gradually fit into the robot's flexible workspace. Once it fits perfectly into the flexible workspace, its pose transformation is calculated and becomes the optimal pose transformation.

[0071] Workspace Adaptive Adjustment: When the point cloud of the object to be grasped is too large to fit completely within the flexible workspace of the robotic arm, the mobile robot's chassis position is adjusted to its maximum extent. The robot's chassis is moved along a predetermined path to allow a portion of the object's point cloud to fit within the robotic arm's workspace.

[0072] Collision parameter limit and stop: When the robot's chassis moves close to the preset collision parameter limit, the chassis stops moving. At this point, the intersection of the object's point cloud and the robot's workspace reaches its maximum, ensuring that the robot can flexibly grasp the object while avoiding collisions.

[0073] Assume that the point cloud pose is adjusted: Assume that the center of mass of the point cloud of the object to be grasped moves along a predetermined path to the base coordinate system of the robot arm, and gradually guide the point cloud into the flexible workspace of the robot arm.

[0074] Inverse pose adjustment: Based on the assumed point cloud pose adjustment results, the inverse pose transformation that the robot chassis needs to perform is calculated. By performing inverse translation and rotation operations, the robot chassis is moved, allowing the robot arm to approach the object while maintaining flexible degrees of freedom.

[0075] Collision parameter limit determination: During reverse pose adjustment, the distance between the robot arm and its surroundings is monitored in real time. When the robot chassis approaches the preset collision parameter limit, further movement is halted. This ensures that the robot arm can maximize coverage of the object's point cloud and achieve grasping without collision.

[0076] S6. Control the mobile chassis 2 to move to the optimal operating space position based on the posture transformation information.

[0077] According to the inverse transformed posture information, the mobile chassis 2 moves to the optimal grasping candidate point, where the flexible workspace of the robot arm 3 and the point cloud information of the feature scene 6 are optimally coupled, thereby achieving multi-degree-of-freedom and high-success-rate operations.

[0078] Among them, the key points of the present invention are:

[0079] S1: Control the mobile robot to move to the position to be operated.

[0080] Mobile chassis 2 is equipped with a laser radar 1. The ROS system controls the mobile robot for navigation, allowing it to autonomously avoid obstacles and stop in front of a feature scene 6. During this process, its position deviates from the ideal operating position due to the accumulated errors of laser navigation and the drift of the inertial navigation unit. This deviation ensures that the field of view of the depth camera 4 at the end of the robotic arm 3 includes the feature scene 6 and the object to be manipulated 7 on it.

[0081] In this step, a depth camera is introduced for target recognition and positioning to solve the problems of cumulative error and inertial navigation unit drift during the mobile chassis navigation process, which improves the accuracy and stability of mobile chassis navigation, ensures that the robotic arm can accurately stop near the target position, and provides a reliable foundation for subsequent operations.

[0082] S2: Obtain the point cloud information of the operation plane and the objects to be operated in the scene.

[0083] The depth camera 4 is used to collect point cloud information of some feature scenes 6 and objects to be operated 7. The point cloud information is filtered and denoised using a point cloud optimization algorithm to remove irrelevant scene point clouds, improve computing efficiency, and obtain high-quality point cloud information. The point cloud information is then used as a maximum spatial envelope diagram.

[0084] By filtering and denoising the point cloud data, scene features are effectively extracted, and making the maximum spatial envelope diagram also saves computing resources.

[0085] S3. Fit the scene plane and extract the point cloud information of objects above the scene.

[0086] Use RANSAC and the least squares method to fit the feature scene plane 6 information, obtain the fitted plane equation, calculate the normal vector perpendicular to this plane, define it as the z-axis, segment the point cloud information on the scene plane 6, that is, where z>0, leaving only the point cloud of the object to be operated 7, and use the point cloud processing algorithm to extract its center of mass.

[0087] S4. Calculating the flexible workspace of the robotic arm

[0088] First, use the Monte Carlo algorithm to calculate the reachable workspace of robot arm 3. Then adjust the posture of the midpoint of the reachable workspace to verify whether its inverse kinematics has a solution. If a solution is found, it is the operating point of the flexible workspace. After the flexible workspace is sampled, its spatial envelope is calculated.

[0089] S5. Maximize the intersection of the flexible workspace and the object point cloud, and calculate the mobile robot's pose transformation based on the maximum intersection.

[0090] The point cloud of the object to be operated 7 is subjected to an offset and other posture transformations from the initial position toward the direction of the flexible workspace of the robot arm 3. When this point cloud just completely enters the flexible workspace, it is defined as the optimal intersection.

[0091] Specifically in S4-S5:

[0092] The first expression:

[0093] Point cloud centroid calculation and pose guidance: Based on the point cloud data of the object to be grasped, the object's center of mass is calculated and moved along a predetermined path toward the center of the robot's base coordinate system. During this movement, the pose of the object's point cloud is adjusted to gradually fit into the robot's flexible workspace. Once it fits perfectly into the flexible workspace, its pose transformation is calculated and becomes the optimal pose transformation.

[0094] Workspace Adaptive Adjustment: When the point cloud of the object to be grasped is too large to fit completely within the flexible workspace of the robotic arm, the mobile robot's chassis position is adjusted to its maximum extent. The robot's chassis is moved along a predetermined path to allow a portion of the object's point cloud to fit within the robotic arm's workspace.

[0095] Collision parameter limit and stop: When the chassis of the robot moves close to the preset collision parameter limit, the chassis movement operation is stopped. At this time, the intersection of the object point cloud and the robot workspace reaches the maximum, ensuring that the robot can flexibly grasp the object while avoiding collisions

[0096] The second expression:

[0097] Assume that the point cloud pose is adjusted: Assume that the center of mass of the point cloud of the object to be grasped moves along a predetermined path to the base coordinate system of the robot arm, and gradually guide the point cloud into the flexible workspace of the robot arm.

[0098] Inverse pose adjustment: Based on the assumed point cloud pose adjustment results, the inverse pose transformation that the robot chassis needs to perform is calculated. By performing inverse translation and rotation operations, the robot chassis is moved, allowing the robot arm to approach the object while maintaining flexible degrees of freedom.

[0099] Collision parameter limit determination: During reverse pose adjustment, the distance between the robot arm and its surroundings is monitored in real time. When the robot chassis approaches the preset collision parameter limit, further movement is halted. This ensures that the robot arm can maximize coverage of the object's point cloud and achieve grasping without collision.

[0100] S6. Control the mobile chassis 2 to move to the optimal operating space position based on the posture transformation information.

[0101] According to the inverse transformed posture information, the mobile chassis 2 moves to the optimal grasping candidate point, where the flexible workspace of the robot arm 3 and the point cloud information of the feature scene 6 are optimally coupled, thereby achieving multi-degree-of-freedom and high-success-rate operations.

[0102] The present invention adopts the above-mentioned method for optimizing the operating space of mobile robots in complex scenes. By processing scene point cloud information, obtaining the flexible working space of the robotic arm, and then performing space optimization, it realizes efficient positioning operation of the mobile robot in complex stacking scenes. It has the advantages of multi-degree-of-freedom operation, high-quality feature extraction, precise posture calculation and high success rate operation.

[0103] Example 2:

[0104] In automated warehousing and logistics, mobile robots are often used for grasping and handling objects in complex environments. However, traditional path planning and static operation methods are ineffective in scenarios with irregularly stacked objects, densely packed objects, or misplaced objects, resulting in high grasping failure rates and low efficiency. This embodiment, combined with the above-mentioned technical solutions, specifically describes how to achieve efficient and accurate grasping operations in such complex scenarios by dynamically optimizing the operating space.

[0105] In a typical automated warehouse environment, robots need to grasp multiple randomly stacked packages of varying sizes and in disorganized locations. Traditional robotic arm operation methods struggle to effectively operate in such a complex scenario. To overcome these difficulties, this embodiment employs a dynamic optimization method for a flexible operating space, enabling the robotic arm to flexibly adjust within irregularly stacked environments and achieve efficient grasping.

[0106] First, the mobile robot uses its LiDAR and depth camera to acquire real-time point cloud data of the area to be operated. The depth camera data is filtered and denoised to remove irrelevant background interference. The resulting optimized point cloud clearly displays the outlines and relative positions of the stacked objects. This process not only improves point cloud quality but also significantly reduces data processing complexity, laying a solid foundation for subsequent operations.

[0107] Then, the RANSAC algorithm and the least squares method are used to perform plane fitting on the scene to accurately identify the surface features of the manipulated object. The calculated center of mass of the object point cloud is used as the target position for grasping. Unlike the limitations of traditional methods that rely on fixed path grasping, this embodiment dynamically adjusts the position of the robot arm through a center of mass guidance strategy, so that the object point cloud gradually adjusts its position within the flexible workspace of the robot arm to ensure that the object is in the optimal grasping position. In this process, the Monte Carlo algorithm is used to sample the reachable workspace of the robot arm, and the reachability of each operating point is verified by inverse kinematics solution to ensure that the robot arm can smoothly reach the target in multiple degrees of freedom.

[0108] To avoid potential collision risks during the grasping process, this embodiment further introduces a real-time adjustment mechanism for collision parameters. During operation, the robotic arm continuously monitors its relative position to the surrounding environment, adjusting its grasping path and posture in real time. Specifically, when the robotic arm reaches a preset collision parameter limit, the system immediately stops adjustments and recalculates the optimal grasping path and posture to ensure safety during the grasping process.

[0109] Through the above steps, this embodiment effectively overcomes the traditional challenges of limited robotic arm operating space, insufficient grasping accuracy, and poor obstacle avoidance in complex scenarios. In this automated warehousing environment, the robotic arm's operational success rate is significantly improved, avoiding operational failures caused by static path planning. Furthermore, the innovative application of dynamic workspace adjustment eliminates the system's reliance on expensive high-precision sensors. Through intelligent algorithm optimization, it achieves accuracy and efficiency unattainable with traditional methods, reducing overall costs.

[0110] In summary, this embodiment demonstrates the superiority of the present invention in complex scenarios. By flexibly adjusting the workspace, optimizing the grasping path in real time, and implementing an intelligent obstacle avoidance mechanism, it achieves efficient and precise operations that are difficult to achieve with traditional technologies, providing a new and significantly improved solution for application areas such as automated warehousing and logistics.

[0111] Example 3:

[0112] In industrial production lines, robots are often used for complex assembly and inspection tasks, especially in confined, heavily obstructed, or stacked work environments. Traditional operation methods struggle to ensure efficient and precise results. Existing robotic arms typically rely on instructional operations or static path planning, unable to adaptively adjust their workspace, limiting operational flexibility and success rates. To address this issue, this embodiment proposes a method for optimizing the operating space in complex scenarios, combining multiple sensors and dynamic posture adjustment strategies to achieve flexible and efficient industrial robot operation.

[0113] In the assembly area of ​​a certain production line, parts of various shapes and sizes must be grasped, positioned, and assembled. In this scenario, parts are chaotically stacked and obstructed, making traditional path planning and fixed operation strategies difficult to handle. To address this, the robot is equipped with a lidar and a depth camera. By acquiring real-time point cloud data of the work area and combining it with an autonomous navigation system, the robot can accurately locate the location to be operated. The combination of lidar and depth cameras enables the system to maintain high-precision scene perception despite environmental interference, providing reliable data support for subsequent operations.

[0114] First, the robot uses a depth camera to collect point cloud information of the object to be manipulated. A point cloud optimization algorithm performs denoising and filtering to remove irrelevant scene data. This optimized, high-quality point cloud generates a maximum spatial envelope diagram, laying the foundation for subsequent workspace optimization. Subsequently, the RANSAC algorithm and the least squares method are used to fit the action plane of the characteristic scene and extract the object's center of mass. This center of mass information is used to guide the robot's adjustment of the action space, achieving efficient matching between the object and the robot arm.

[0115] During operation, this embodiment places particular emphasis on the calculation and optimization of a flexible workspace. Using a Monte Carlo algorithm, the robot's accessible workspace is calculated, and inverse kinematics is performed on the sampling points to determine the accessibility and flexibility of each operating point. The robot's workspace is maximized in intersection with the object's point cloud, and the position transformation is performed based on the intersection result. By continuously adjusting the position and posture of the object's point cloud, ensuring that it gradually enters the robot's optimal grasping area—that is, the optimal intersection area—the success rate of the operation is significantly improved.

[0116] To prevent collision risks during operation, the system employs real-time collision parameter limits and adjustments. While the robotic arm is in motion, the system monitors the distance between the arm and its surroundings. When approaching a preset collision limit, the system stops movement and readjusts the grasping path and posture to ensure a safe grasp. For larger parts, the robot chassis can perform reverse posture adjustments, enabling flexible chassis movement and posture corrections to maximize adaptability to changing scenarios and object sizes.

[0117] The optimization method of this embodiment significantly improves the robot's operational efficiency and grasping success rate in complex assembly scenarios. This method not only overcomes the limitations of traditional teaching methods but also achieves adaptive operation of various component shapes through the integration and real-time adjustment of multiple algorithms. Especially when handling irregular, heavily obscured, or complexly stacked objects, the robot can flexibly adjust its operating space to achieve fast and precise grasping and assembly, significantly improving the overall efficiency and flexibility of industrial production lines.

[0118] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations that come within the meaning and range of equivalents of the claims be embraced therein.

Claims

1. A method for dynamically optimizing a robot's flexible operating space in complex scenarios, characterized by the following steps: S1: Control the mobile robot to move to the position to be operated. The mobile robot includes a mobile chassis equipped with a lidar, a vision system based on lidar navigation and a depth camera, and autonomously avoids obstacles through the ROS system and moves to a stop in front of a feature scene. S2: Use the depth camera to obtain point cloud information of the feature scene and the item to be operated, suppress and denoise the object point cloud information, remove irrelevant scene point clouds, and obtain high-quality point cloud information; S3: Construct the scene using the RANSAC algorithm and the minimization of project squares method, obtain the point cloud information of the scene, calculate the center of mass of the project point cloud and define it as the operation target; S4: Calculate the approach workspace of the manipulator using the Monte Carlo algorithm, obtain the operating points of the flexible workspace through inverse kinematics, sample the flexible workspace and calculate its spatial envelope; S5: Maximize the intersection of the flexible workspace and the object point cloud, calculate the position transformation of the mobile robot based on the maximum intersection, and guide the point cloud of the object to be operated into the flexible workspace; S6: Based on the optimal posture transformation information, the mobile structure is controlled to move to the optimal operation space position, so that the flexible workspace of the robot arm and the point cloud information of the feature scene are optimally coupled, thereby achieving a high success rate of operation.

2. The method for dynamic optimization of robot flexible operation space in complex scenarios according to claim 1 is characterized in that: The point cloud optimization algorithm in step S2 includes suppression and noise removal to remove irrelevant point clouds, improve computational efficiency, and generate a maximum spatial envelope diagram.

3. The method for dynamic optimization of robot flexible operation space in complex scenarios according to claim 1 is characterized in that: The scene plane in step S3 includes obtaining a plane equation using a RANSAC algorithm, and performing a vertical calculation on the algorithm support of the plane as a Z axis to segment the scene plane and the project point cloud.

4. The method for dynamic optimization of robot flexible operation space in complex scenarios according to claim 1 is characterized in that: The flexible workspace calculation in step S4 includes: Monte Carlo sampling of the robot's adjacent workspace; Monte Carlo sampling is performed on the adjacent workspace of the robot arm. The operation point position is fixed and rotated around the x, y, and z axes in steps of 30°. For each posture, it is verified whether an inverse kinematic solution exists. The solution is the operation point in the flexible workspace.

5. The method for dynamic optimization of robot flexible operation space in complex scenarios according to claim 1 is characterized in that: The posture transformation in step S5 includes: Based on the calculation of the object point cloud centroid, guide the object point cloud centroid to move along the preset path to the center point of the robot arm base coordinate system; Adjust the project point cloud layout according to the optimized intersection, so that the project can fully enter the flexible workspace.

6. The method for dynamic optimization of robot flexible operation space in complex scenarios according to claim 1 is characterized in that: The step S5 also includes workspace adaptation adjustment. When the project point cloud cannot fully adapt to the flexible workspace, the posture of the mobile robot structure is adjusted to achieve partial intersection between the project point cloud and the workspace of the robotic arm.

7. The method for dynamic optimization of robot flexible operation space in complex scenarios according to claim 1 is characterized in that: The step S5 further includes collision parameters and adjustments. When the robotic arm moves to the collision parameter limit, it stops moving and adjusts its position to maximize the coverage of the workspace.

8. The method for dynamic optimization of robot flexible operation space in complex scenarios according to claim 1 is characterized in that: The optimized operation space position in step S6 is obtained by inverse posture adjustment calculation. Through adjustment, the robot arm maintains the flexibility of multiple degrees of freedom in complex scenes, thereby achieving the best operation effect.

Images