Humanoid robot global automatic valve screwing system and control method

Abstract

The invention belongs to the technical field of humanoid robot valve control, and particularly relates to a humanoid robot global automatic valve screwing system and a control method.The humanoid robot global automatic valve screwing system comprises a movable chassis, a lifting module, a waist pitching module, a robot body, a tail end tool, a sensor assembly and a control system; the tail end tools are arranged at the tail ends of the two arms of the human shape. The sensor assembly is used for environment sensing, collection of valve height and posture information and collection of operation torque information. The control system is used for roughly positioning a target valve, automatically planning and controlling the moving chassis to approach the valve according to a rough positioning result, and adjusting the height based on the collected height information of the valve; and on the basis of the recognized valve posture, the two human-shaped arms and the tail end tool are controlled to complete screwing operation. Different types of valves can be automatically recognized and operated through the intelligent control system, and the time and cost of manual operation are reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of humanoid robot valve control, and in particular relates to a humanoid robot global automatic valve turning system and a control method. Background Art

[0002] With the continuous improvement of industrial automation and intelligence, people's demand for robot automation in complex operation scenarios is growing. In petrochemical, water supply and heating and other industrial pipeline systems, valves are important components of pipeline control, and the opening and closing of valves directly affect the normal operation of the pipeline system. However, due to the variety of valve types (such as ball valves, gate valves, butterfly valves, etc.), the operation methods are different, and some valves may rust or have high operating resistance due to long-term use, which makes manual operation time-consuming and labor-intensive, and may pose safety hazards.

[0003] Especially in some dangerous or complex working environments, such as high temperature, high pressure, toxic gas leakage, etc., manual valve turning is not only inefficient, but also may pose a threat to the safety of operators. In addition, in the daily maintenance of pipeline systems, the large number of valves and their wide distribution make the cost of manual inspection and operation one by one high, consuming a lot of time and human resources.

[0004] Therefore, there is an urgent need for a humanoid robot control method based on automatic valve screwing, so as to replace manual operation of valves in industrial and life scenarios, reduce manual labor intensity and safety risks, and improve the efficiency and accuracy of valve operation. Summary of the invention

[0005] Purpose of the invention: The purpose of the present invention is to address the deficiencies in the prior art and to provide a humanoid robot global automatic valve turning system and control method, which can automatically identify and operate different types of valves through an intelligent control system, thereby reducing the time and cost of manual operation.

[0006] Technical solution: The humanoid robot global automatic valve turning system of the present invention comprises: A mobile chassis equipped with a multi-wheel drive system for mobility and navigation; A lifting module, connecting the mobile chassis and the robot body, configured to automatically adjust the working position of the robot body based on the sensed valve height information; A waist pitch module, linked with the lifting module, is configured to support the pitch adjustment and left-right rotation of the robot body to adjust the working posture; The robot body is equipped with humanoid arms, each of which has multiple degrees of freedom joints; The end tool is arranged at the end of the humanoid double arms, and is used to grasp and screw the valve, and can automatically adjust the grasping force and clamping angle according to the shape and size of the valve; Sensor components, used for environmental perception, valve height and posture information collection, and operating torque information collection; The control system includes: a valve recognition module, which is used to perform environmental perception and recognition based on the YOLO deep learning algorithm to achieve rough positioning of the target valve; a path planning module, which is used to automatically plan and control the mobile chassis to approach the valve according to the rough positioning result; a height adjustment module, which is used to control the lifting module to adjust the height in real time based on the collected valve height information; and a screwing operation module, which is used to identify the valve posture and control the humanoid arms and end tools to complete the screwing operation based on the identified valve posture.

[0007] To further improve the above technical solution, the sensor assembly includes: Head depth camera, configured on the robot head, for environment scanning and valve coarse positioning; The chest depth camera is installed on the robot's chest and is used for close-range identification and precise positioning of the target valve; Laser radar, configured on the mobile chassis and the robot body, is used to detect circumferential obstacles; Ultrasonic sensors are placed on the front and rear sides of the mobile chassis to detect obstacles in the front and rear directions; Torque sensors are installed in the humanoid arm joints and end tools to monitor the torque and force conditions during operation in real time.

[0008] Furthermore, when the robot approaches the valve, it uses sensor components including laser radar, depth camera, and ultrasonic sensor to scan and obtain spatial layout information of the target area in real time. Based on the obtained spatial layout information, it uses laser SLAM and multi-sensor fusion technology in combination with a preset path planning algorithm to generate an optimal path from the current position to the valve. According to the generated path, the robot moves step by step according to the predetermined motion instructions by controlling the joints of the mobile chassis and the robot body; based on the collected valve height information, the real-time height difference between the robot and the valve is calculated based on the fusion data of the depth camera, lidar and ultrasonic sensor, and the lifting module and waist pitch module are adjusted synchronously for dynamic adjustment.

[0009] The control method of the global automatic valve screwing system using the humanoid robot comprises the following steps: S101: Valve coarse positioning: Based on the YOLO deep learning algorithm, the sensor component acquires images for real-time image recognition and processing to achieve the coarse positioning result of the target valve; S102, approaching the valve: according to the rough positioning result, automatically planning and controlling the mobile chassis to approach the valve; S103, real-time height adjustment: when approaching the valve, continuously collect valve height information, control the lifting module to adjust the height, and ensure that the robot's humanoid arms are within a suitable height range; S104, posture recognition and screwing execution: When the robot approaches the valve, it accurately recognizes the valve posture and adjusts the posture and strength of the two arms according to the recognition result to complete the screwing operation.

[0010] Furthermore, the step S101 of valve rough positioning includes the following steps: S201, obtaining a valve image dataset based on a binocular vision camera; S202, labeling the valve data set to generate a labeled data set; S203, performing data enhancement processing on the annotated data set; S204, using the YOLO algorithm to perform real-time recognition on the enhanced image to generate a two-dimensional bounding box of the valve; S205 . Generate three-dimensional spatial information of the valve through the depth map, and estimate the position of the valve in the robot space coordinate system.

[0011] Further, the step S102 of approaching the valve includes the following steps: S301, obtaining spatial layout data of the target area, constructing a three-dimensional map of the environment, and dynamically updating obstacle information, wherein the spatial layout data includes the location, size, shape, distance between the valve and the obstacle, and ground conditions of the obstacle; S302, generating a path from the current position to the valve based on the spatial layout data, based on laser SLAM and multi-sensor fusion technology, combined with a path planning algorithm, wherein the path planning takes into account avoiding obstacles and physical limitations of the robot; S303, controlling the humanoid robot to move along the planned path, and monitoring the motion state and making adjustments through a real-time feedback system.

[0012] Furthermore, the step S103 of real-time height adjustment includes the following steps: S401, collecting real-time vertical distance information between the valve and the robot end tool through a depth camera, a laser radar, and an ultrasonic sensor to obtain the target valve position and current relative height data; S402, calculating the difference between the current valve height and the preset target grasping height of the robot to obtain the height adjustment amount, and simultaneously calculating the waist pitch angle adjustment amount to keep the waist in a vertical state; S403, controlling the lifting module to adjust the height according to the height adjustment amount, and synchronously controlling the waist pitch module to adjust the pitch angle, and ensuring the stability of the robot's movement process through closed-loop control.

[0013] Further, the identification of the valve posture in S104 includes the following steps: S601, acquiring an image data set of a target valve from different viewing angles by moving a depth camera, and recording depth information; S602, recording the internal and external parameter information of the camera for each image, and performing camera calibration and pose estimation; S603, segmenting the valve image by using the Mask R-CNN algorithm to obtain a labeling mask; S604, registering the multi-view image data with the depth information to generate point cloud data of the scene; S605, using the BundleSDF algorithm to perform three-dimensional reconstruction on the point cloud data to construct a three-dimensional model of the valve; S606, inputting the valve 3D model into the FoundationPose algorithm to obtain a 6D pose estimation of the valve from the camera perspective; S607, combining the hand-eye calibration results, obtain the posture conversion relationship between the camera and the robotic arm, calculate and record the relative posture of the current robotic arm end tool and the valve as the valve grasping posture. Furthermore, the valve gripping in S104 includes the following steps: S701, obtaining the current position of the valve in the camera coordinate system in real time in the depth camera, calculating the expected position of the end tool of the robot arm in the robot base coordinate system in the current environment, solving the expected angles of each joint of the robot arm through the inverse kinematics of the robot arm and moving the robot arm to the expected position; S702. When the robot arm reaches the desired position, it uses the equipped end tool to grab or clamp the valve.

[0014] Furthermore, the valve screwing in step S104 includes the following steps: after the robot arm clamps the valve using the end tool, an adaptive admittance control algorithm is used for control, and force tracking is performed along the tangent direction of the valve edge to achieve the screwing of the valve; The adaptive admittance control algorithm comprises the following steps: S801, acquiring force data read by the six-dimensional force sensor, performing gravity compensation and coordinate transformation, and obtaining force data in the coordinate system of the end of the robot arm; S802, setting a desired force, and calculating a desired trajectory estimate and an environmental stiffness estimate based on an adaptive admittance control algorithm; S803: Perform force tracking based on the expected trajectory estimation and the environmental stiffness estimation, and control the robotic arm to achieve valve screwing.

[0015] Beneficial effects: Compared with the prior art, the advantages of the present invention are: The present invention adopts an automatic valve screwing control method based on a humanoid robot, which can automatically identify and operate different types of valves through an intelligent control system, reducing the time and cost of manual operation. Compared with traditional manual operation, the present invention can significantly improve the efficiency of valve operation, especially in pipeline systems that require frequent operation.

[0016] Robots replace manual operation to screw valves, avoiding the potential safety hazards of manual operation in dangerous environments such as high temperature, high pressure, and corrosive gas leakage. By reducing the direct contact of operators with dangerous environments, the risk of accidents and the labor intensity of personnel are significantly reduced, ensuring the safety of operators.

[0017] The present invention can automatically identify and locate valves of the required type (such as ball valves, gate valves, butterfly valves, etc.) by pre-specifying the size and shape of the valves. This adaptability enables the robot to be widely used in various pipeline systems and valves of different specifications, and has strong versatility.

[0018] The robot of the present invention can adapt to various complex working environments, can cope with situations where the valve position is not fixed, the operating space is limited, and the mechanical characteristics are complex, and has strong environmental adaptability. The robot automatically adjusts its posture and height to ensure the safety and stability of operation in complex environments, thereby avoiding the problem that traditional manual operations cannot complete operations in these environments.

[0019] Based on the force-controlled admittance algorithm, the robotic arm has good flexibility during the valve screwing process and can be dynamically adjusted according to the actual contact force to avoid damage to the valve or robotic arm due to excessive operating force, thereby improving the reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a structural schematic diagram of the global automatic valve screwing system of a humanoid robot of the present invention; The reference numerals in the figure are: 1, radar; 2, depth camera; 3, humanoid arms; 4, pitch module; 5, lifting module; 6, radar; 7, mobile chassis; Figure 2 is a flow chart of the control method of the present invention; Figure 3 It is a flow chart of the coarse positioning of the valve in the control method of the present invention; Figure 4 It is a schematic diagram of the dynamic height adjustment of the lifting module of the present invention; Figure 5 It is a flow chart of obtaining the valve gripping posture in the present invention; Figure 6It is a schematic diagram of the valve of the present invention; Figure 7 is a schematic diagram of the valve image after processing by the present invention; Figure 8 It is a schematic diagram of a three-dimensional model of the valve of the present invention; Fig. 9 It is a valve grasping flow chart of the present invention; Fig.10 is a schematic diagram of the valve grasping posture in the present invention; Fig.11 is a schematic diagram of a grip valve in the present invention; Fig.12 Schematic diagram of the valve screwing in the present invention Fig.13 It is a schematic diagram of the adaptive admittance control algorithm of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is described in detail below with reference to the accompanying drawings, but the protection scope of the present invention is not limited to the embodiments.

[0022] Example 1: Figure 1 The humanoid robot global automatic valve screwing system shown in the figure uses an industrial-grade mobile chassis as its walking mechanism, equipped with a high-precision laser radar and a multi-wheel drive system, which enables flexible movement and navigation. The chassis supports laser SLAM (simultaneous localization and mapping) technology, which can build real-time maps in dynamic environments, and achieve path planning and precise positioning through an inertial measurement unit (IMU).

[0023] Mobile chassis: The robot uses an industrial-grade mobile chassis as its walking mechanism, equipped with a high-precision laser radar and a multi-wheel drive system, which enables flexible movement and navigation. The chassis supports laser SLAM (simultaneous localization and mapping) technology, which can build real-time maps in dynamic environments, and achieve path planning and precise positioning through an inertial measurement unit (IMU).

[0024] Lifting module: The mobile chassis is connected to the robot body through the lifting module. The lifting module adopts an electric drive system, which can adjust the working position of the robot body within different height ranges. The device senses the valve height information in real time and automatically adjusts to ensure that the robot arms can accurately aim at the target valve.

[0025] Waist pitch module: The waist pitch module is linked with the lifting module to support the pitch adjustment of the body, which can ensure that the robot maintains a stable working posture in operation scenarios at different heights and angles. The module has the function of left and right rotation, allowing the robot to capture and operate surrounding targets in all directions.

[0026] Body and humanoid arms: The body module is equipped with humanoid arms. Each humanoid arm has multiple degrees of freedom joints. Combined with high-precision servo motors and torque sensors, it can achieve flexible movement of complex paths. The end of the humanoid arm is equipped with a special grasping and screwing device (humanoid arm end tool), which can automatically adjust the grasping force and clamping angle according to the shape and size of different valves.

[0027] The sensor components include depth cameras, laser radars, torque sensors, and ultrasonic sensors. Among them, the depth cameras are configured on the robot's head and chest to capture the shape, size, and posture information of the valve. The head depth camera provides a wide-angle field of view for environmental scanning and coarse positioning; the chest depth camera focuses on close-range identification and precise positioning of the target valve. The laser radar is configured on the mobile chassis and the robot body to detect obstacles in the environment, and combines the SLAM algorithm for autonomous navigation and obstacle avoidance operations. The torque sensor is installed on the humanoid arm joints and end tools to monitor the torque and force conditions during operation in real time to ensure the safe operation of the valve. Ultrasonic sensors are configured in front and behind the mobile chassis for front and rear obstacle identification and distance perception.

[0028] Embodiment 2: A control method is performed using the humanoid robot global automatic valve screwing system used in Embodiment 1. The specific flow chart is as follows: Figure 1 As shown, it is mainly divided into the following 4 steps: S101, valve rough positioning Through the visual component, the robot performs real-time image recognition and processing based on the YOLO (You Only Look Once) deep learning algorithm, thereby achieving rough positioning of the target valve.

[0029] S102, close to the valve Based on the rough positioning results, the robot automatically plans and executes the motion path and approaches the valve accurately.

[0030] S103, real-time height adjustment While approaching the valve, the robot continuously collects real-time height information of the valve, and uses the robot lifting module to make dynamic adjustments to ensure that the robot arms are within the appropriate height range to ensure stable grip of the valve.

[0031] S104, posture recognition and twisting execution When the robot approaches the valve, it begins to accurately identify the valve posture, and adjusts the posture and strength of its arms based on the identification results to complete the screwing operation.

[0032] Step S101: Through the visual component, the robot performs real-time image recognition and processing based on the YOLO (You Only Look Once) deep learning algorithm to achieve rough positioning of the target valve. The specific flow chart is as follows: Figure 2 As shown, the following steps are included: S201. Obtain a valve image dataset based on a binocular vision camera: Specifically select the source of the dataset, such as valves in industrial environments such as hydropower stations and petrochemical plants. Although the structures of these valves are relatively complex, they are more in line with the needs of actual application scenarios; S202, labeling the collected valve data set to generate a labeled data set: using the LabelImg tool to manually label and mark the position of the valve boundary box and its center point; S203, enhancing the labeled data: formulating a specific enhancement strategy, processing the image by various methods such as rotation, flipping, scaling, and brightness adjustment to expand the data set; S204, using the YOLO algorithm to process the images, identify the target valve in real time, and generate a preliminary two-dimensional bounding box; S205 , generating three-dimensional spatial information of the target valve through the depth map, and estimating the position of the valve in the spatial coordinate system of the robot by calculating the three-dimensional coordinates.

[0033] The target valve described in this embodiment does not specify a valve of a specific size or shape. By establishing a data set containing a variety of valve types, sizes, and shapes, the YOLO algorithm is trained so that the algorithm can automatically adapt to changes in different valves.

[0034] Step S102, the robot automatically plans and executes a motion path based on the rough positioning result to accurately approach the valve, including the following steps: S301. Obtaining spatial layout data of the target area The robot uses a variety of sensors such as laser radar, depth camera, ultrasonic sensor, etc. to scan and obtain the spatial layout information of the target area in real time. This process uses laser SLAM technology to build a three-dimensional map of the surrounding environment and dynamically update the obstacle information of the target area. The spatial layout data includes the relative position, size, shape, distance between the valve and the obstacle, and ground conditions of the obstacle. In addition, combined with the inertial navigation system, the robot can sense its own position changes in real time and automatically adapt to the dynamic changes of the surrounding environment. The data is represented by a point cloud map and is processed as input for subsequent path planning to ensure that the robot can navigate smoothly in complex and dynamic environments.

[0035] S302: Determine the planned path of the robot in the target area according to the spatial layout data Based on the acquired spatial layout data, the robot uses laser SLAM and multi-sensor fusion technology, combined with a preset path planning algorithm, to generate the best path from the current position to the valve. During the path planning process, the robot not only considers the shortest path to the valve, but also dynamically avoids obstacles and optimizes the robot's physical limitations (such as size, turning radius, maximum speed, acceleration, etc.). Combined with the high-resolution map generated by SLAM, the robot can adjust the path in real time, avoid new obstacles, and ensure the accuracy of path execution through an inertial measurement unit. Path planning also takes into account the relative posture between the robot and the valve, so that the robot can accurately align the grasping angle when approaching the valve.

[0036] S303, controlling the humanoid robot to move along the planned path Based on the generated planned path, the robot moves step by step according to the predetermined motion instructions through its chassis control system and each joint drive system. During the movement, the robot will monitor its own motion state by using real-time feedback systems such as lidar and IMU sensors to ensure that there is no deviation during the path execution. Through the inertial navigation system and real-time environmental perception system, the robot can adjust its posture, speed and acceleration in real time and avoid obstacles in time. During the execution of the robot, the feedback system will make real-time corrections to its current posture, speed, acceleration and distance from obstacles to avoid errors or collisions, ensuring that it moves efficiently and safely along the planned path. The robot will also make dynamic adjustments according to changes in the environment, optimize the motion trajectory in real time, and ensure that the robot is always in an ideal motion state.

[0037] Step S103, in the process of approaching the valve, the robot continuously collects the real-time height information of the valve, and uses the robot lifting module to make dynamic adjustments to ensure that the robot arms are within the appropriate height range to ensure stable grip of the valve.

[0038] S401, collect real-time height information between valve and robot When the robot approaches the valve, it first collects the vertical distance between the valve and the robot's end effector in real time through depth cameras, lidar, ultrasonic sensors and other equipment. This information is processed through sensor fusion technology to obtain accurate valve position and current relative height data.

[0039] S402: Calculate the required height adjustment amount and simultaneously calculate the waist pitch angle After collecting the height information, the robot calculates the difference between the current valve height and the robot's preset target grasping height through the control system to obtain the height difference that needs to be adjusted. At this time, the robot not only needs to adjust the lifting position of the chassis according to the height difference, but also needs to calculate the pitch angle of the waist to ensure that the robot waist remains vertical while adjusting the height. Through the collaborative control algorithm, the robot synchronously calculates the pitch angle adjustment of the waist based on the adjustment amount of the lifting module and the target posture. Figure 3 shown.

[0040] S403, controlling the lifting module to perform dynamic height adjustment and synchronize waist pitch.

[0041] After calculating the required height adjustment and waist pitch angle, the robot control system will control the chassis lifting module and waist pitch mechanism at the same time. The lifting module will adjust the overall height of the robot according to the calculated height difference. At the same time, the robot monitors the real-time pitch angle of the waist through IMU and sensor feedback, and the waist pitch mechanism will be adjusted synchronously according to the target pitch angle to ensure that the robot always keeps the waist upright during the adjustment process. This process uses a closed-loop control system to correct the adjustment amount through real-time feedback to ensure that the robot's movement process is stable and accurate. Figure 4 shown.

[0042] Step S104, when the robot approaches the valve, it starts to accurately identify the valve posture, and adjusts the posture and strength of the arms according to the identification result to complete the screwing operation, including the following steps: S501, valve grasping posture acquisition; S502, grasping the valve; S503, valve screwing.

[0043] Step S501, the specific steps of obtaining the valve grasping posture are as follows: S601, multi-view acquisition of valve data sets By moving the depth camera to obtain images of the target operating valve at different viewing angles, ensure that the images cover all parts of the valve and avoid occlusion. At the same time, record the depth information, such as Figure 6 The valve used in this embodiment is just a simple example. In actual use, a valve data set can be established according to the size and shape of the specific valve to be operated, and then a valve model can be established to obtain the valve position.

[0044] S602: Recording camera parameter information Record the camera’s extrinsic and intrinsic parameters for each image, and perform camera calibration and pose estimation.

[0045] S603, Valve segmentation marking The Mask R-CNN algorithm is used to segment the collected valve image data to obtain the annotation mask. Figure 7shown.

[0046] S604, point cloud generation The multi-view image data is aligned with the depth information to generate high-quality point cloud data of the scene.

[0047] S605, Model Reconstruction The image, depth information, camera pose and other information are converted into the input format of BundleSDF, and the BundleSDF algorithm is used for 3D reconstruction to construct a high-quality 3D valve model. Figure 8 shown.

[0048] S606, valve position acquisition Input the constructed valve 3D model into the FoundationPose algorithm to obtain the valve 6D pose estimation from the camera perspective. .

[0049] S607, valve gripping posture acquisition Through hand-eye calibration, the position conversion relationship between the camera and the robotic arm is obtained At the same time, combined with the end tool currently equipped with the robot arm, the robot arm is pre-taught to move to a reasonable valve grasping position, and the valve position in the camera coordinate system obtained in S106 is used. , calculate and record the relative position of the current end of the robotic arm and the valve , the calculation formula is as follows: in, , They are , The inverse matrix of It can be solved by the forward kinematics of the robot arm.

[0050] Step S502, Fig. 9 This is a valve gripping flow chart of an embodiment of the present invention, and the specific process is as follows: S701, obtain the expected joint angle of the robot arm to grab the valve and move Based on the above S60 steps, Fig.10 As shown, the 6D posture of the valve within the current camera view can be identified , use the FoundationPose algorithm to obtain the current position of the valve in the camera coordinate system in real time , based on the pre-calculated desired position of the robot end and the valve , calculate the expected position of the end of the robot arm in the robot arm base coordinate system in the current environment , the calculation formula is as follows: Then use the inverse kinematics of the robot arm to solve the expected angles of each joint of the robot arm , and move the robot arm to the desired position, such as Fig.11 shown.

[0051] S702, Robotic arm grasps valve When the robot arm reaches the desired position, use the equipped end tool to grab or clamp the valve to ensure that the end tool and the valve do not slide relative to each other when the valve is screwed. Fig.12 shown.

[0052] Step S503, the specific steps of valve tightening are as follows: after the robot arm uses the end tool to clamp the valve, it quickly uses the adaptive admittance algorithm to control it, and performs force tracking along the tangent direction of the edge of the valve clamped by the robot arm to achieve valve tightening.

[0053] In the embodiment of the present invention, the adaptive admittance control is as follows: Fig.13 As shown, the specific control steps are as follows: S801. Obtain force data read by the six-dimensional force sensor The influence of the six-dimensional force sensor and the end gravity is eliminated through gravity compensation, and the force data based on the six-dimensional force sensor coordinate system is converted into force data based on the robot end coordinate system by coordinate transformation.

[0054] S802, setting expected force , is brought into the adaptive admittance controller of the present invention to calculate the desired trajectory estimate and environmental stiffness estimation , the calculation formula is as follows: in, , To estimate the initial value, , is an adaptive parameter. In this embodiment, 450000、 S803. Perform force tracking according to the estimated reference trajectory and environmental stiffness to achieve the screwing of the valve. The calculation formula is as follows: Among them, m is the mass coefficient, b is the damping coefficient, and k is the stiffness coefficient, all of which are constant matrices. is the adaptive control coefficient, and its update rate is as follows: in, , to prevent the denominator from being 0, is the update rate.

[0055] The actual motion trajectory of the robot arm calculated by the adaptive admittance controller This is input into the robot controller, which performs force tracking to achieve valve turning.

[0056] As described above, although the present invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the present invention itself. Various changes in form and details may be made without departing from the spirit and scope of the present invention as defined in the appended claims.

Claims

1. A humanoid robot global automatic valve screwing system, characterized in that: include: A mobile chassis equipped with a multi-wheel drive system for mobility and navigation; A lifting module, connecting the mobile chassis and the robot body, configured to automatically adjust the working position of the robot body based on the sensed valve height information; A waist pitch module, linked with the lifting module, is configured to support the pitch adjustment and left-right rotation of the robot body to adjust the working posture; The robot body is provided with humanoid arms, wherein the humanoid arms have joints with multiple degrees of freedom; The end tool is arranged at the end of the humanoid double arms, and is used to grasp and screw the valve, and can automatically adjust the grasping force and clamping angle according to the shape and size of the valve; Sensor components, used for environmental perception, valve height and posture information collection, and operating torque information collection; The control system includes: a valve identification module for performing environmental perception and identification based on the YOLO deep learning algorithm to achieve rough positioning of the target valve; A path planning module is used to automatically plan and control the mobile chassis to approach the valve according to the rough positioning result; a height adjustment module is used to control the lifting module to adjust the height in real time based on the collected valve height information; and a screwing operation module is used to identify the valve posture and control the humanoid arms and end tool to complete the screwing operation based on the identified valve posture.

2. The humanoid robot global automatic valve screwing system according to claim 1, characterized in that: The sensor assembly comprises: Head depth camera, configured on the robot head, for environment scanning and valve coarse positioning; The chest depth camera is installed on the robot's chest and is used for close-range identification and precise positioning of the target valve; Laser radar, configured on the mobile chassis and the robot body, is used to detect circumferential obstacles; Ultrasonic sensors are placed on the front and rear sides of the mobile chassis to detect obstacles in the front and rear directions; Torque sensors are installed in the humanoid arm joints and end tools to monitor the torque and force conditions during operation in real time.

3. The humanoid robot global automatic valve screwing system according to claim 2, characterized in that: When the robot approaches the valve, it uses sensor components including laser radar, depth camera, and ultrasonic sensor to scan and obtain spatial layout information of the target area in real time. Based on the obtained spatial layout information, it uses laser SLAM and multi-sensor fusion technology in combination with a preset path planning algorithm to generate an optimal path from the current position to the valve. According to the generated path, the robot moves step by step according to the predetermined motion instructions by controlling the joints of the mobile chassis and the robot body; based on the collected valve height information, the real-time height difference between the robot and the valve is calculated based on the fusion data of the depth camera, lidar and ultrasonic sensor, and the lifting module and waist pitch module are adjusted synchronously for dynamic adjustment.

4. A control method for the global automatic valve screwing system of a humanoid robot using any one of claims 1 to 3, characterized in that: The following steps are involved: S101: Valve coarse positioning: Based on the YOLO deep learning algorithm, the sensor component acquires images for real-time image recognition and processing to achieve the coarse positioning result of the target valve; S102, approaching the valve: according to the rough positioning result, automatically planning and controlling the mobile chassis to approach the valve; S103, real-time height adjustment: when approaching the valve, continuously collect valve height information, control the lifting module to adjust the height, and ensure that the robot's humanoid arms are within a suitable height range; S104, posture recognition and screwing execution: When the robot approaches the valve, it accurately recognizes the valve posture and adjusts the posture and strength of the two arms according to the recognition result to complete the screwing operation.

5. The control method according to claim 4, characterized in that: The step S101 of valve rough positioning includes the following steps: S201, obtaining a valve image dataset based on a binocular vision camera; S202, labeling the valve data set to generate a labeled data set; S203, performing data enhancement processing on the annotated data set; S204, using the YOLO algorithm to perform real-time recognition on the enhanced image to generate a two-dimensional bounding box of the valve; S205 . Generate three-dimensional spatial information of the valve through the depth map, and estimate the position of the valve in the robot space coordinate system.

6. The control method according to claim 4, characterized in that: The step S102, approaching the valve, comprises the following steps: S301, obtaining spatial layout data of the target area, constructing a three-dimensional map of the environment, and dynamically updating obstacle information, wherein the spatial layout data includes the location, size, shape, distance between the valve and the obstacle, and ground conditions of the obstacle; S302, generating a path from the current position to the valve based on the spatial layout data, based on laser SLAM and multi-sensor fusion technology, combined with a path planning algorithm, wherein the path planning takes into account avoiding obstacles and physical limitations of the robot; S303, controlling the humanoid robot to move along the planned path, and monitoring the motion state and making adjustments through a real-time feedback system.

7. The control method according to claim 4, characterized in that: The step S103 real-time height adjustment comprises the following steps: S401, collecting real-time vertical distance information between the valve and the robot end tool through a depth camera, a laser radar, and an ultrasonic sensor to obtain the target valve position and current relative height data; S402, calculating the difference between the current valve height and the preset target grasping height of the robot to obtain the height adjustment amount, and simultaneously calculating the waist pitch angle adjustment amount to keep the waist in a vertical state; S403, controlling the lifting module to adjust the height according to the height adjustment amount, and synchronously controlling the waist pitch module to adjust the pitch angle, and ensuring the stability of the robot's movement process through closed-loop control.

8. The control method according to claim 4, characterized in that: The identification of the valve posture in S104 includes the following steps: S601, acquiring an image data set of a target valve from different viewing angles by moving a depth camera, and recording depth information; S602, recording the internal and external parameter information of the camera for each image, and performing camera calibration and pose estimation; S603, segmenting the valve image by using the Mask R-CNN algorithm to obtain a labeling mask; S604, registering the multi-view image data with the depth information to generate point cloud data of the scene; S605, using the BundleSDF algorithm to perform three-dimensional reconstruction on the point cloud data to construct a three-dimensional model of the valve; S606, inputting the valve 3D model into the FoundationPose algorithm to obtain a 6D pose estimation of the valve from the camera perspective; S607. In combination with the hand-eye calibration result, the posture conversion relationship between the camera and the robotic arm is obtained, and the relative posture between the current robotic arm end tool and the valve is calculated and recorded as the valve grasping posture.

9. The control method according to claim 4, characterized in that: The valve grasping in S104 includes the following steps: S701, obtaining the current position of the valve in the camera coordinate system in real time in the depth camera, calculating the expected position of the end tool of the robot arm in the robot base coordinate system in the current environment, solving the expected angles of each joint of the robot arm through the inverse kinematics of the robot arm and moving the robot arm to the expected position; S702. When the robot arm reaches the desired position, it uses the equipped end tool to grab or clamp the valve.

10. The control method according to claim 4, characterized in that: The valve tightening in step S104 includes the following steps: After the robot arm uses the end tool to clamp the valve, it uses the adaptive admittance control algorithm to track the force along the tangent direction of the valve edge to achieve the screwing of the valve; The adaptive admittance control algorithm comprises the following steps: S801, acquiring force data read by the six-dimensional force sensor, performing gravity compensation and coordinate transformation, and obtaining force data in the coordinate system of the end of the robot arm; S802, setting a desired force, and calculating a desired trajectory estimate and an environmental stiffness estimate based on an adaptive admittance control algorithm; S803: Perform force tracking based on the expected trajectory estimation and the environmental stiffness estimation, and control the robotic arm to achieve valve screwing.

Images