6712 results about "Robotic arm" patented technology

The invention discloses a multi-mechanical-arm space-time synchronization control method for coiled pipe welding, and belongs to the technical field of automation control, and the method comprises the steps: in a primary laser and TIG hybrid welding execution stage, carrying out real-time data acquisition on a welding area of a workpiece, carrying out real-time deviation detection, and once real-time welding deviation is detected, carrying out time-space synchronization on the welding area of the workpiece; a local correction mechanism is triggered immediately, and deviation is prevented from being accumulated in the single welding process; after one-time welding is completed, the workpiece enters a transition area, global contour reconstruction is conducted on a welded section of the workpiece through three-dimensional scanning equipment, global deviation recognition is conducted, and unprocessed hysteresis deformation and accumulative errors are covered and corrected in real time; on the basis of the analysis result of the global deviation recognition, double correction is conducted on secondary welding, and cooperative control over space track correction and technological parameter adaptation is achieved; and after secondary welding is completed, the correction effect is evaluated through a double-layer evaluation mechanism, and the stability of the correction process is ensured.

A human-guided vision-force fused impedance iterative learning control method for a robotic arm, comprising: analyzing a robot-environment interaction dynamics equation, solving a visual servo acceleration model, and making use of the equation to establish a human-robotic arm-environment interaction dynamics model in an image feature space; acquiring an image feature position and speed curve of a human-guided robot completing an assembly task, and using dynamic movement primitives for coding and generalization; and designing an impedance iterative learning controller which uses image feature tracking errors as control input, learning impedance characteristics when the human-guided robot performs a contact operation, identifying unknown contact dynamics under the interaction between the robot and the environment, and counteracting identified contact interference in the feature space, so as to implement a flexible assembly operation. The control method solves the problems in existing assembly operations that human-robotic arm-environment coupling nonlinear dynamics, unknown contact dynamics of intensive contact assembly tasks and poor generalization of assembly scenarios require relearning for different scenarios, etc.

Systems and methods that allow robots to perform tasks for users are provided. A robot may comprise one or more robotic arms and / or a mobile base. The arms may be controlled by electric actuators and may have six or more degrees of freedom. The robot may have sensors which can be accessed remotely. Robots may have varying levels of autonomy, including, for example, full teleoperation (in which a human can have detailed control over the robot) or full autonomy (in which the robot can complete a task without any human intervention). Various entities can interact with individual robots or groups of robots over a network, locally, directly or in person, or any combination thereof. A management system can allow entities to control and / or monitor the robots.

The invention relates to the technical field of mechanical arm obstacle avoidance path planning, in particular to a multi-degree-of-freedom mechanical arm obstacle avoidance path planning method based on three-dimensional reconstruction, which comprises the following steps: step 1, three-dimensional environment perception and dynamic modeling; preferentially offsetting and expanding the near-obstacle nodes towards the concave area or the hole center to generate a candidate node set; and 4, three-dimensional grid collision verification and safe path correction are conducted, specifically, the working space of the mechanical arm is divided into three-dimensional voxel grids, and collision detection is achieved by judging whether path nodes fall into obstacle object elements or not. According to the method, the laser radar and the depth camera are adopted to synchronously collect data through hardware triggering, statistical filtering denoising and three-dimensional grid modeling are combined, geometrical characteristics of static obstacles and motion parameters of dynamic obstacles are restored, and the collision risk caused by environmental perception errors of the mechanical arm is effectively avoided.

The invention discloses an intelligent grabbing recognition and execution control method and system of a mechanical arm, and relates to the technical field of artificial intelligence. The intelligent grabbing recognition and execution control method and system for the mechanical arm comprises the following steps that S1, grabbing data are collected by integrating various sensors, and abnormity elimination, missing complementation, coordinate registration and normalization processing are completed on the grabbing data; s2, analyzing a structural feature and a time sequence relationship of the captured data, extracting a visual feature vector, a physical contact state vector and a dynamic behavior feature vector, and deducing a stability expression in a clamping process according to the visual feature vector, the physical contact state vector and the dynamic behavior feature vector; s3, confidence analysis is carried out on the grabbing candidate actions based on the mechanical relation and sensing data distribution, and action screening and standard action coding are completed; and S4, a track and a control instruction are generated, the expected clamping force is analyzed in real time in combination with clamping jaw movement and contact state changes, and feedback is collected and executed to update strategy data. The problem that in the prior art, a flexible transparent object is difficult to accurately recognize and stably grab is solved.

The invention relates to the technical field of medicine quality detection, and particularly discloses an optical detection method and system for the content of vitamin tablets. The method comprises the following steps: driving an optical fiber probe array to carry out three-dimensional multi-angle near-infrared scanning through a multi-axis mechanical arm, and collecting reflection spectrum data; a weighted spectrum is generated through derivative spectrum analysis and double evaluation, and auxiliary material noise is corrected and separated in combination with subspace projection and a dynamic kernel function; performing spectral vector projection and regression coefficient iterative optimization through an online PLS model, and synthesizing an error coefficient based on a four-level index retrieval standard library to perform dual-channel feedback; and finally, fusing the credibility weight to output a detection result of the binding confidence. The method realizes nondestructive and high-precision detection of the vitamin tablets, has the beneficial effects of multi-dimensional data fusion, dynamic error compensation and high model adaptability, and remarkably improves the detection accuracy and reliability.

The invention provides an electric instrument table intelligent control method based on multi-modal perception and model prediction, and relates to the technical field of electric instrument tables, and the method comprises the steps: obtaining high-precision environment perception data through a multi-modal sensor fusion technology, and constructing a dynamic three-dimensional map to recognize an instrument and an obstacle; the system drives the multi-degree-of-freedom mechanical arm to move efficiently through optimal path planning based on model prediction control, the operation period is remarkably shortened, the overall operation efficiency and throughput capacity are improved, meanwhile, potential collision and abnormal stress are monitored in real time in the grabbing and placing process, an intelligent obstacle avoidance and safe shutdown mechanism is started, and the safety of the robot is improved. According to the method, the robustness and safety of system operation are greatly improved, a flexible grabbing strategy is integrated for precious fragile instruments, lossless operation is achieved through real-time force feedback, high-value samples are effectively protected, finally, through machine vision verification and online optimization, the system can continuously conduct self-learning, the operation precision is continuously improved, and the success rate is continuously increased. And the self-adaptive performance is improved.

A robotic system includes a robotic arm that interacts with an object during operation. It further includes a locking component that, during operation, locks a multi-position component in an operating position. Responsive to a triggering event, locking of the multi-position component in the operating position is released and the multi-position component moves away from its operating position, facilitating separation between the robotic arm and the object.

The invention relates to the technical field of data processing, and discloses an in-vehicle testing method and system based on a small model. The method comprises the following steps: acquiring an in-vehicle machine screen image, and extracting interface elements through a lightweight recognition model to generate a recognition result; analyzing element function association to determine operation types to form a test operation sequence; an ADB instruction and a mechanical arm action are generated according to the operation sequence to construct a test script; executing the script to drive the vehicle machine to test and collecting multi-dimensional response data; and analyzing test data, calculating a passing rate and response time, and generating a verification report. According to the method, the technical problems of low interface element identification accuracy, poor test script adaptability and insufficient multi-modal data analysis capability in the traditional vehicle-mounted terminal test are solved, and the automation degree of the vehicle-mounted terminal test and the reliability of the test result are remarkably improved.

The invention discloses a rotating wheel nondestructive testing robot and a testing method thereof, and belongs to the technical field of specialized robots and nondestructive testing. The rotating wheel nondestructive testing robot comprises a permanent magnet adsorption walking mechanism, a multi-degree-of-freedom mechanical arm, a module flaw detection unit, a multi-sensor positioning system and a central controller; the adsorption walking mechanism is used for realizing all-attitude stable crawling on the curved surface of the rotating wheel; the multi-degree-of-freedom mechanical arm is arranged above the middle part of the permanent magnet adsorption walking mechanism and is used for moving the module flaw detection unit to a specified position; the module flaw detection unit is used for performing high-resolution detection on the damage of the composite material on the rotating wheel; the multi-sensor positioning system is used for real-time pose feedback of the robot; the central controller is used for controlling all the components to work cooperatively. According to the nondestructive detection robot for the runner and the detection method thereof, the problems that in the prior art, detection of internal cracks of turbine runner blades depends on a manual frame erecting mode, the high-altitude operation risk is large, the number of detection blind areas is large, and efficiency is low can be effectively solved.

The present invention relates to the field of robotic arm teleoperation technology, and specifically to a construction method and system for real-time teleoperation of a dual arm and hand robot based on vision guidance, which includes setting up a first experimental platform, acquiring pose information of the dual arm and hand robot and a homogeneous transformation matrix of an end joint and transforming a first coordinate system; setting up a second experimental platform; performing calibration by a plurality of cameras and transforming a second coordinate system; obtaining spatial transformation pose information of the end joint of the robotic arm under a tracking state, reading finger pose data, and performing real-time following. The real-time teleoperation system of the present disclosure includes a control system host, an operation glove, an optical locator, a positioning coordinate plate, a marker ball tool, and a dual arm and hand robot. The present disclosure introduces a method of identifying the marker ball tool by the optical locator into the teleoperation control of the dual arm and hand robot, which is more accurate and faster. Meanwhile, the method of remotely controlling the robotic arm by an operator wearing the operation gloves can provide better human-machine interaction function.

The invention discloses a visual perception and dynamic anti-collision intelligent closed-loop control method for a central control mechanical arm in a vehicle, and the method comprises the steps: S1, loading an improved YOLOv11 network detection model, and reading a video stream of a camera; s2, preprocessing each frame of image in the video stream, inputting the preprocessed image into the model, and performing target identification; s3, inputting an identification result into a dynamic safe area collision model, and performing coordinate conversion through a hand-eye calibration algorithm; calculating a relative position and a motion trend in combination with depth sensor data, and judging a risk level to generate a corresponding protection instruction; and S4, executing a hierarchical control strategy according to the risk level, updating the action track of the mechanical arm, and returning to the step S1 through a closed-loop feedback mechanism to adjust the safety threshold and the control parameters to form a complete'perception-decision-execution-optimization 'autonomous evolution closed loop. According to the method, the visual perception robustness and the target detection precision under the complex illumination condition are improved, and real-time dynamic anti-collision response and millisecond-level rapid obstacle avoidance are realized.

The invention relates to the technical field of mechanical arm control, and discloses a bionic self-adaptive variable-stiffness mechanical arm joint control method. The method comprises the steps that multi-source biological signals such as electromyographic signals, tendon tension signals and joint angle signals during joint operation are collected; constructing a stiffness feature vector based on the myoelectricity and tendon tension signals, and generating a motion trail sequence according to the joint angle signals; extracting a corresponding stiffness feature vector for each track point, and calculating stiffness sensitivity; constructing a bionic stiffness reference model containing a mapping relation between the stiffness feature vector and a joint angle signal, and dynamically weighting and adjusting the mapping relation by using stiffness sensitivity; predicting a joint stiffness change sequence based on the adjusted model and the real-time signal, and fusing the sequence with the current joint angle signal to generate a dynamic stiffness parameter; and calculating a driving torque correction amount according to the dynamic stiffness parameter and a preset safety threshold range, iteratively updating the model weighting parameter until the correction amount meets a convergence condition, and outputting a driving torque instruction to an execution mechanism.

The invention discloses a deep reinforcement learning robot-assisted ultrasonic scanning system and method based on security constraints. The invention discloses a deep reinforcement learning mechanical arm ultrasonic scanning method and system based on security constraints. A scanning system comprising a mechanical arm, an ultrasonic probe, a joint torque and visual sensor and a control unit is constructed. The environment state space covers the joint angle, the tail end pose, the contact force, the scanning path and the safety state variable of the mechanical arm, and the action space is a tail end linear speed instruction of the mechanical arm. A deep reinforcement learning model is built based on a near-end strategy optimization (PPO) algorithm, and a reward function including image quality, task completion reward and multiple penalty terms is designed. A control barrier function (CBFs) is used for implementing safety constraint on motion of the mechanical arm, and the safety constraint is fused into deep reinforcement learning training through a penalty function method. A model is trained in a simulation environment simulating an actual scanning scene and then deployed to an actual system, and a mechanical arm is controlled to scan and monitor safety constraints according to a real-time environment state. The mechanical arm can efficiently execute the ultrasonic scanning task under the condition that the safety constraint is met, and a reliable scheme is provided for ultrasonic scanning automation. Meanwhile, the system is provided with a data acquisition module, a state construction module, a reward calculation module, a security constraint module, a control module and the like, and the model performance can be improved through simulation training.

The invention provides an intelligent warehouse goods posture recognition and automatic sorting method and system, and the method comprises the steps: S2, extracting the edge contour and surface features of goods from point cloud data for a preliminary value set, calculating the direction vector and shape distribution characteristics of the goods through a principal component analysis method, and obtaining a quantitative result of shape feature extraction; s6, historical sorting data and real-time sensor data are extracted from the warehousing system database according to the classification basis adapted to the complex scene, the dynamic posture change trend of the goods is predicted through a time sequence analysis method, and optimization parameters of real-time processing are obtained; and S7, the movement track and the grabbing angle of the sorting mechanical arm are adjusted through the optimization parameters subjected to real-time processing, a deep reinforcement learning algorithm is adopted to conduct iterative optimization on the sorting action sequence, and an execution scheme of sorting accuracy is determined. According to the method, the accuracy of goods posture recognition and the automatic sorting efficiency in the complex storage environment are remarkably improved.

A multi-robotic-arm collaborative control method. The method comprises the steps of: according to process requirements of an execution task and on the basis of a plurality of robotic arms, constructing a multi-arm coupled dynamics model, the multi-arm coupled dynamics model being used for position decomposition and force distribution for the plurality of robotic arms; on the basis of the multi-arm coupled dynamics model, decomposing the execution task to form a plurality of sub-task segments; on the basis of the sub-task segments, forming a collaborative controller group, the collaborative controller group consisting of controllers corresponding to a plurality of robotic arms under a master terminal; and, by means of the collaborative controller group, controlling each robotic arm to execute a path of a sub-task segment. The present application solves the problems of poor coordination and adaptability among various robotic arms when confronted with unknown working environments and uncertainties of task objectives during cooperative operation of the multiple robotic arms. Further provided are a multi-robotic-arm collaborative robot system and a storage medium.

Disclosed is a robotic system and method designed for the verification and validation of smart connected Human-Machine Interface (HMI) devices. The robotic system integrates a multi-finger modular robotic module, a haptic module, a finger actuator, vision cameras, vision lights, a finger rotary module, a Cartesian robotic arm, an onboard user interface, and an L-shaped door. The method involves replicating human finger interactions, simulating touch sensations on a device under test (DUT), ensuring continuous and reliable operation, utilizing vision cameras for navigation and verification, optimizing vision with controlled lighting, positioning cameras strategically, executing various tasks with a robotic arm, and facilitating user interaction through an onboard interface.

The invention belongs to the technical field of steel pipe welding, particularly relates to high-strength steel pipe welding equipment and process based on a laser-induced hybrid welding technology, and solves the problems of high interference degree and poor correction function in the prior art, the high-strength steel pipe welding equipment comprises a base, and the top of the base is fixedly connected with an outer gear ring and two symmetrically arranged clamping assemblies; a welding assembly is installed on the peripheral face of the outer gear ring and composed of an arc-shaped transmission frame and a limiting transmission frame, the outer gear ring is movably sleeved with the arc-shaped transmission frame, the limiting transmission frame is slidably assembled in the arc-shaped transmission frame, a laser induction head and a welding head are installed on one side of the limiting transmission frame, and the welding assembly is used for welding steel pipes. Through the arrangement of the outer gear ring, the arc-shaped transmission frame and other structures, the continuity and stability of circumferential welding are achieved, the problems of mechanical arm interference and the like are avoided, meanwhile, the adaptability of equipment to steel pipes with different pipe diameters is improved, frequent equipment parameter adjustment or clamp replacement is not needed, and the welding efficiency is remarkably improved.

The invention relates to a mechanical arm ultrasonic guided wave multi-defect detection path planning method based on data driving, relates to the technical field of nondestructive detection and automatic detection, and solves the technical problem that automatic defect detection for a large plate structure and a large curved surface structure does not exist in the prior art. A system applicable to the method comprises a control and test system and a tested piece. According to the invention, the mechanical arm is used for carrying the electromagnetic acoustic sensor to scan a large plate and a large curved surface structure, so that detection, positioning and identification of various different defects are realized; the use of a coupling agent can be reduced, the detection time efficiency is improved, the detection precision is improved, the detection accuracy is realized, and the accuracy of positioning and identifying defects is improved; the scanning path of the mechanical arm is optimally designed, so that the detection efficiency is improved; and the collected data serve as an original data set to construct a deep learning model and an integrated CNN model, and mechanical arm scanning detection path planning of multiple defects in a large component and a large curved surface structure is achieved.

A mobile security robot includes a human-sized mannequin mounted on a vehicle. A storage unit, mounted on the vehicle, stores security devices and high-powered energy storage devices for facilitating extended patrols without recharge. A video recording system, disposed in the mannequin, continuously records images of a patrol area. Multiple sensors mounted on and proximal to the mannequin generate sensor data based on environmental conditions of the patrol area. A computing system coupled to the sensors processes the sensor data using artificial intelligence models and generates action commands for execution of tasks by actuators including electric motors, robotic arms, and supplementary attachment devices. The electric motors run the vehicle at different speeds with wheel speed feedback based on the environmental conditions and navigate the vehicle along a predefined travel path with object avoidance during patrols. User interface devices facilitate auditory and visual communication with humans in the patrol area.

The invention relates to the technical field of robot control, and discloses a mechanical arm trajectory planning control method and system based on a BAFARNN model. The method comprises the steps that a mechanical arm kinematics model is established, and a trajectory tracking problem is converted into a time-varying equation; designing a bounded adaptive function to activate a recurrent neural network model, defining an error function and constructing a dynamic equation; designing a piecewise adaptive coefficient function, and dynamically adjusting the gain according to an error norm and time; setting a Lissajous curve as an expected trajectory, and initializing a simulation environment; the joint speed is solved in real time through an ODE numerical method, and the mechanical arm is driven to move; actual motion data is collected and compared with an instruction, and closed-loop feedback control is triggered when the actual motion data exceed a threshold value. According to the method, rapid convergence is achieved through the piecewise adaptive coefficient function, the bounded activation function and the negative feedback mechanism are adopted to suppress noise, and high-precision and real-time trajectory tracking of the mechanical arm in the dynamic environment is achieved.

The invention relates to a multi-source perception-based mechanical arm operation data acquisition system and method, the system comprises an isomorphic mechanical arm operation module, a multi-view visual image acquisition module, an optical motion capture module and a shielding detection and data fusion module, vision, pose and force sense data are cooperatively acquired through multiple sensors, and time-space consistency is synchronously kept by adopting hardware. The system has a multi-dimensional occlusion detection mechanism and can dynamically switch data processing strategies according to the occlusion degree: visual data is preferentially adopted when no occlusion exists, multi-sensor information is fused when partial occlusion exists, and force feedback compensation is predicted and introduced based on a dynamic model when complete occlusion exists. Physical feedback and visual perception are creatively combined, the problem of data missing of a traditional single sensor data acquisition system under the shielding condition is solved, more comprehensive and more reliable data support is provided for mechanical arm algorithm training and performance optimization, and the method is particularly suitable for complex operation scenes with shielding.

The invention relates to the field of electric power, in particular to an angle steel tower bolt and double-nut mounting robot which comprises a climbing platform crawling along an angle steel tower, and a material supplementing device is fixed to the climbing platform and synchronously advances along with the climbing platform; a mechanical arm is further fixed to the climbing platform, a fastening device is fixed to the driving end of the mechanical arm, and the material supplementing device is located in the moving range of the mechanical arm. The fastening device comprises a fixing base fixed to the mechanical arm, a guide rail is vertically arranged on the fixing base, and a bolt fastening base and a nut fastening base are both in sliding fit with the guide rail. The nut fixing sleeve and the bolt fixing sleeve are arranged on the bolt fastening base and the nut fastening base respectively and are coaxial, and openings of the nut fixing sleeve and the bolt fixing sleeve are opposite. One-time continuous fastening operation of bolts and double nuts on a plurality of bolt hole positions of a flange plate on an angle steel tower can be achieved in one-time tower climbing operation, and the installation efficiency is high.

Dynamic pick pose recovery is described. The concepts can be relied upon to determine the pose of an item during a process for picking, moving, and placing the item among totes, or other uses. In one example, an item can be picked using a robotic arm, and the item can be repositioned for placement at a second location. Images of the item can be captured as the item moves. The images can be segmented to determine masks of the item. The masks can be projected into a point cloud within a bounding volume, to generate contours. Points of the point cloud that are positioned outside the contours can be discarded, to find a subset of points representative of a pose of the item. The position and orientation of the item can be calculated, for placement of the item at a second location, based on the pose of the item.

A robotic surgical system network includes a plurality of robotic surgical systems. Each system includes robotic arms, sensors, a surgeon console, and a control system with an integrated AI module. A network interface is associated with robotic surgical system and provides secure data communication. A central or distributed data repository securely stores surgical data aggregated from the robotic surgical systems. The surgical data includes at least one of procedural data, sensor readings, imaging data, AI decision logs, surgical outcomes, or user interaction data. A training module utilizes aggregated surgical data to train or update AI models for the robotic surgical systems using unsupervised learning, transfer learning, or federated learning techniques. A cybersecurity module implements security measures for data transmission and system access, the measures comprising at least one of encryption, multi-factor authentication, or real-time threat detection.

The invention provides an osteotomy path adjusting system in robot-assisted knee arthroplasty, and belongs to the technical field of knee joint detection. The system comprises a multi-modal data acquisition unit which comprises a knee joint pressure measuring gasket, an optical acquisition module and a kinematics data acquisition module, the knee joint pressure measuring gasket is used for acquiring knee joint pressure signals in an operation, and the optical acquisition module is used for acquiring relative poses of a femur and a tibia; the kinematics data acquisition module is used for acquiring kinematics data of the mechanical arm; the main control calculation unit comprises a data fusion module and a dynamic compensation module, and the data fusion module is used for constructing a synchronous spatio-temporal data set; and the dynamic compensation module is used for outputting a compensation instruction to the mechanical arm to adjust an osteotomy path based on the synchronous spatio-temporal data set, the preoperative predicted pressure prediction matrix and the soft tissue stiffness matrix. The pressure change in the operation can be responded in real time, the operation precision of the knee arthroplasty is improved, and the dependence on the experience of doctors can be reduced.

An automatic charging device is particularly suitable for automatically charging a heavy rail tractor, including a box body; a robotic arm, the robotic arm including a fixed arm and a retractable arm, the fixed arm is fitted in the box body, a driving screw assembly is fitted between the fixed arm and the retractable arm, and the retractable arm can be driven by the driving screw assembly to extend and retract relative to the fixed arm; a flexible unit; and a charging part, wherein the charging part is fitted to a retractable end of the retractable arm by means of the flexible unit, the charging part may be driven by the retractable arm to extend from the box body to implement charging, and after the charging is completed, the charging part may retract into the box body.

The invention provides a mechanical arm motion planning method based on vision-language multi-modal data. The method comprises the following steps: acquiring a human language instruction, and controlling an image acquisition device of the robot to acquire an environment image; generating multi-modal data based on the human language instruction and the environment image by utilizing a multi-modal data generation module; encoding the human language instruction by utilizing a language model to obtain a text language vector; performing absolute position coding on the environment image to obtain a visual coding vector; fusing the text language vector and the visual coding vector to obtain multi-modal data; and inputting the multi-modal data into the trained multi-modal motion control model to obtain a motion planning track of the mechanical arm. A target track generated by the mechanical arm under manual control is used for reinforcement learning to train a multi-modal motion control model, the motion planning path and strategy of the mechanical arm are optimized, and the mechanical arm can achieve the motion effect approaching human beings.

The invention relates to the technical field of mechanical arms, in particular to a chemical emergency disposal-oriented manipulator cross-modal sensing control system which comprises an environment scanning module, a visual positioning module, an obstacle avoidance planning module, a pose compensation module, a decision mapping module and a grabbing updating module. Obtaining environment state information; an operation view angle image of the manipulator is collected, visual features of the operation view angle image are solved, and pose information is obtained; obstacle avoidance correction is conducted on the motion trail of the mechanical arm, and a collision-free approaching path is obtained; the operation view angle image and the multi-mode micro-touch signal are fused, error compensation is carried out on the pose information, and an accurate grabbing pose is obtained; mapping object surface physical attributes sensed by the multi-mode micro-tactile signals to obtain a self-adaptive grabbing instruction; the manipulator is controlled to conduct grabbing through the self-adaptive grabbing instruction, and environment state information is updated; according to the invention, the accuracy of cross-modal sensing control of the manipulator can be improved.

The invention provides a mechanical arm control method and system based on mechanism-Bayesian joint modeling, and relates to the technical field of robot control, and the method comprises the steps that firstly, a mechanical arm mechanism model is constructed, parameters of the mechanical arm mechanism model are estimated, and preliminary dynamics prediction is obtained; then, combining with motor driving torque observation data, establishing a random mathematical model of mechanism model residual errors, and decomposing the random mathematical model into deterministic and random parts; carrying out probability learning on the residual error by utilizing a Bayesian neural network, and outputting a prediction mean value and a variance of the residual error; in combination with preliminary dynamic prediction and residual information, constructing a data-driven uncertainty adaptive control law without dependence of an acceleration signal, and carrying out random stability analysis; and a stable joint driving torque instruction is generated, and high-precision trajectory tracking of the mechanical arm is achieved. According to the method, the interpretability of the mechanism model and the high adaptability of the data driving model are combined, the control precision and flexibility are effectively considered, and the robustness and reliability of the mechanical arm in the complex dynamic environment are improved.