393 results about "Robot control system" patented technology

The embodiment of the invention provides an unhooking robot control method based on multi-source visual fusion, which is applied to the technical field of robot control and comprises the following steps: acquiring an RGB image, a depth image, an infrared image and IMU data through a multi-source sensing system mounted at the tail end of a robot; carrying out feature fusion identification by adopting a double-branch neural network, and outputting the boundary contour of the lifting hook and the three-dimensional coordinates of the optimal grabbing point; the visual coordinates are unified to a robot base coordinate system through a registration correction mechanism; a Transform prediction model is constructed based on the visual and inertial signals, and future pose changes of the lifting hook are estimated; a feedforward control track is generated to counteract swing of the lifting hook, and track correction is carried out in combination with visual servo feedback; and a joint instruction is generated through path planning and inverse kinematics solution, and the mechanical arm is driven to complete precise unhooking operation. According to the method, the recognition precision, the anti-interference capability and the operation success rate of unhooking operation in complex illumination and dynamic environments are effectively improved.

The invention discloses a robot control system and method based on vision and force sense fusion and a robot, and relates to the technical field of robots. The robot control system based on vision and force sense fusion and the control method thereof analyze visual features in real time through an artificial intelligence processing unit to predict mechanical parameters; and the self-adaptive impedance control unit is combined to dynamically fuse a position instruction and force sense feedback, so that precise adaptation of target object characteristics and compliant regulation and control of an interaction process are realized, real-time sensing and dynamic adjustment capabilities are achieved, assembly damage caused by mechanical mismatching is effectively avoided, and the reliability and efficiency of precise assembly are improved.

The present disclosure provides a method for generating annotation data for robotic training using a hierarchical transformer-based model with multiple layers. The transformer-based model includes Alpha models generating low-level control outputs and Beta models generating high-level control outputs. The method receives multimodal input data comprising visual sensor data and natural language instructions, processes this data through the hierarchical transformer-based model to generate annotations at different abstraction levels, wherein Beta models create semantic annotations describing task objectives and Alpha models generate motor command annotations specifying robotic actions, and stores these annotations with the input data to create annotated training data for robotic control systems.

The invention relates to the technical field of industrial robot control, and particularly discloses an intelligent foreign matter sorting robot control system based on AI recognition, which comprises a dynamic spatial feature extraction module, a manipulator motion state coding module, a collaborative conflict detection module, a dynamic trajectory optimization module and an execution control adjustment module, constructing a three-dimensional dynamic space model through multi-sensor fusion, and extracting spatial topological features by utilizing continuous coherence analysis; manipulator motion parameters are converted into topological space representation, and a track feature coding matrix is established; detecting interaction conflicts among the manipulators in real time by adopting a multi-scale coherence analysis method, and generating graded early warning signals; a collision avoidance track is optimized based on topological constraints and a virtual rejection field technology; precise execution is achieved through inverse kinematics of the Lie group theory and self-adaptive control.

This patent discloses a computer system for humanoid robot control system design and implementation, featuring a digital humanoid robot with dynamical models and a set of single-input-single-output (SISO) and multi-input-multi-output (MIMO) controllers. The system comprises a main software program, a generative Al humanoid robot intelligence engine, a robot motion path planner module, and a control system simulation engine. It enables efficient design, testing, validation, and implementation of robot control systems, significantly reducing time to market. The system supports seamless upgrades to accommodate new designs and components, enhancing applications in industrial automation, healthcare, public safety, and more, aligning with the goals of the 4th Industrial Revolution.

The invention relates to the technical field of machine control, and discloses a chemical safety inspection robot control system and method based on sensor fusion, and the system comprises a data fusion module, a strategy construction module, a strategy analysis module, a real-time monitoring module, an optimization instruction module, and an event determination module. Original data of the chemical environment is fused into standardized data, and structural features are analyzed to identify risk factors; constructing a security situation map, mapping the security situation map to the robot, and determining a control strategy; when the robot begins to inspect, analyzing the control strategy to control the movement adjustment path action and the path safety inspection action of the robot; coding the movement adjustment path action and the path safety inspection action into a safety control instruction; optimizing the safety control instruction to obtain an optimized control instruction; when the robot completes inspection, an environment safety abstract and an abnormal event record are obtained; the control accuracy of the chemical safety inspection robot can be improved.

The invention relates to a biomimetic robot control system based on digital human action mapping, in particular to the technical field of robot control, solves the problem that a biomimetic robot is difficult to perceive physical attributes only by means of vision, achieves accurate pre-judgment of contact force and material attributes by analyzing digital human fingertip microscopic color change and object texture deformation, and improves the accuracy of the biomimetic robot control system. A robot can establish an adaptive mechanical model before contact, the system dynamically adjusts the flexibility and damping of a mechanical arm according to the environment rigidity and friction characteristics, soft grabbing of hard objects and stable grabbing of sliding objects are achieved, the hysteresis quality of traditional feedback control is effectively overcome, meanwhile, the time sequence feed-forward and energy monitoring mechanism is combined, and the control precision is improved. Collision protection is provided while zero-delay synchronization of actions is ensured, and the operation stability and safety of the robot for fragile and flexible objects in a complex environment are remarkably improved.

The invention provides an aerial operation robot control system and method for water quality monitoring. The control system provided by the invention comprises a collaborative and autonomous navigation module which accurately plans a water quality monitoring flight path according to the monitored water area and position point information, and intelligently starts a fine monitoring module as required according to the regional water quality analysis result of a remote sensing monitoring module, thereby guaranteeing the comprehensive coverage of a monitored region, and timely focusing an abnormal region. The monitoring efficiency is greatly improved; the multi-rotor unmanned aerial vehicle control module guarantees stable flight; and the mechanical arm control module assists in accurate measurement. The remote sensing monitoring module and the fine monitoring module respectively utilize different sensors to obtain regional and point water quality data. The data fusion analysis module integrates the two types of data, determines and corrects the pollution range and source, locks the pollution source according to the pollution gradient, and improves the efficiency and precision of water quality monitoring.

The invention relates to the technical field of automatic welding, and discloses a micro welding seam tracking method and system based on electromagnetic induction. According to the method, a high-frequency alternating magnetic field is applied to a welding seam area through an exciting coil in the micro electromagnetic sensing core; an induction coil in the electromagnetic sensing core is used for detecting magnetic field disturbance caused by geometric shape changes of the weld groove, and induction signals are obtained; processing the induction signal through a signal processing circuit integrated in the probe, namely converting the impedance change of the coil into a voltage signal, demodulating and filtering the voltage signal, and extracting a direct-current voltage signal corresponding to the deviation of the probe relative to the central position of the welding seam; the direct-current voltage signals serve as position feedback information to be output to a welding robot control system; and the movement track of the welding robot is adjusted in real time according to the position feedback information, and welding seam tracking and path deviation correction are achieved.

The invention discloses a robot control system parameter optimization training system based on machine learning, and relates to the technical field of intelligent control. The system comprises a data acquisition and structured marking module, a coupling influence strength evaluation module, a deviation mapping model construction module, a neural network training module, a real-time prediction and trajectory correction module and a closed-loop control execution module, and is characterized in that joint data is acquired in real time, a lightweight machine learning model is constructed and trained to predict trajectory deviation caused by dynamic coupling, and the trajectory deviation is corrected. According to the method, a target trajectory is dynamically corrected, closed-loop online compensation is achieved through a bottom layer controller, the whole process from data collection and prediction to trajectory correction and bottom layer control execution is continuously and circularly executed, and therefore closed-loop online compensation of the joint dynamic coupling effect is achieved. The objective of the invention is to solve the problems of trajectory tracking and dynamic response precision caused by dynamic coupling of multi-joint robots.

The invention discloses a hand-eye cooperative robot control system and method based on dynamic operator arrangement, an upper computer planning layer operates a master control computer to periodically trigger task scheduling, a joint controller of a lower computer execution layer receives an instruction through a redundant bus to perform servo control, hand-eye camera data triggers a visual assembly line through an interrupt event, and a visual assembly line is controlled through a control interface. According to the method, pressure is calculated through visual processing, motion planning and joint control in a load sharing mode, a double-buffering mechanism is adopted to enable current frame visual processing and previous frame motion control to be executed in an overlapping mode, real-time scheduling and parallel computing of tasks are completed, hot data are cached in a memory database, cold data are archived to an HDFS and migrated through an LRU strategy, and the real-time scheduling and parallel computing of the tasks are completed. Data type conversion is automatically derived and performed based on a feature type registry, and conditional branch execution is triggered according to real-time sensor data. According to the control system, cross-hardware plug and play, algorithm flow configurability and data flow real-time sharing are achieved, and the requirement for improving the efficiency of complex operation tasks is met.

The invention discloses an AI-driven industrial robot intelligent assembly collaborative scheduling method and system, and the method comprises the steps: collecting assembly operation data, and constructing a semantic structure which comprises a process, a robot and a space region; extracting time sequence data, inputting the time sequence data into the prediction model, calculating offset and mapping a shell state; constructing an origami surface structure, analyzing space and time conflicts, and determining conflict positions; rearranging execution space and time windows, generating constraint mapping, and constructing a regular space-time layout; constructing a two-dimensional scheduling texture block, executing a reconstruction operation, and generating a scheduling texture sequence; and generating a scheduling scheme, completing constraint verification, and issuing the scheduling scheme to a robot control system for execution. According to the method, by introducing a beat prediction and state driving cooperative scheduling mechanism based on assembly semantic data, advanced perception and stable cooperative control of beat fluctuation, space conflicts and scheduling disturbance in the assembly process of multiple industrial robots are achieved.

The invention belongs to the technical field of medical robots and minimally invasive surgery, and provides a robot control system and method for blue laser vaporization surgery of prostatic hyperplasia. Mapping the nuclear magnetic image volume data to a deformation field under an ultrasonic acquisition coordinate system, and deforming the preoperative nuclear magnetic image to an intra-operative ultrasonic space by using the deformation field to complete image registration; fusing the registered image with a stereoscopic vision system; the spatial depth of the surface of the target tissue is obtained from the endoscopic image so as to supplement navigation information; according to the utility model, the prostate deformation and probe posture change adaptive capacity in an operation is improved, the real-time visual closed-loop regulation and control capacity is improved, and the characteristics of small light spots, shallow heat diffusion, excellent hemostasis and the like of blue laser are combined, so that the vaporization and hemostasis precision in a tiny blood vessel dense area is ensured, and the problems of large tissue trauma and the like are avoided.

The invention discloses a three-mode switching type sewage plant biochemical pool inspection robot control system, and belongs to the technical field of robot inspection, the three-mode switching type sewage plant biochemical pool inspection robot control system comprises a composite moving system, an integrated crawler walking module, a buoy module and a propeller module, and the three-mode switching type sewage plant biochemical pool inspection robot control system is used for controlling and switching walking modes of an inspection robot; the mode switching triggering mechanism is used for switching the composite moving system to the crawler walking module, the buoy module or the propeller module according to the water depth; the multi-source heterogeneous sensor monitoring module is used for detecting environmental data in real time through a multi-source heterogeneous sensor; and the path planning module is used for fusing monitoring data of the multi-source heterogeneous sensor, optimizing a global path by adopting an improved ant colony algorithm, and carrying out dynamic obstacle avoidance in combination with a D * Lite algorithm. Switching of multiple propelling modes is supported, and limitation of a single moving mode of a traditional robot is broken through; and meanwhile, monitoring data of heterogeneous sensors are aligned, and dynamic obstacle avoidance is performed by adopting an improved ant colony algorithm in combination with a D * Lite algorithm, so that the accuracy of path planning is improved.

The invention discloses an amphibious robot power system fault prediction method based on land and water working condition difference, and belongs to the technical field of robot control systems, and the method comprises the steps: sensing land and water physical field characteristics in real time, and emerging an environment coupling topology state; monitoring an energy and information exchange flow, and obtaining a flow mode divergence as a fault precursor; receiving land and water environment switching identification, inducing relaxation and tending to a new convergence steady state; taking the new steady state as an initial condition, taking the flow mode divergence and the energy dissipation rate as evolution driving potential, and generating a minimum action quantity track; and driving parameter or weight adjustment along a minimum action quantity track to realize structural adaptation and toughness internalization. According to the method, a control strategy integrating dynamic topology modeling, prospective risk assessment and structural learning adaptation is adopted, the active fault prediction capacity and the self-adaptive stability in the land and water environment switching process can be improved, and the overall reliability and toughness of the robot are enhanced.

The invention discloses a double-arm robot main and auxiliary moving operation coordination control method based on vision / force sense servo and implementation thereof. Double-arm coordination is supported, multi-sensing information is fused, compliant operation is considered, and the method is adaptive to a moving scene. The mobile main and auxiliary double-arm robot control system comprises a mobile base subsystem, a main and auxiliary double-arm subsystem and a control subsystem. The double-arm main and auxiliary operation coordination control method based on visual / force sense servo comprises visual servo target tracking based on a tail end camera and force sense servo compliant operation control based on a force sensor, operation tasks are achieved in the state that a base moves, and the double-arm main and auxiliary operation coordination control method adapts to the complex working environment; a state machine mechanism is adopted to manage a mechanical arm motion mode, screw assembly task-oriented operation process arrangement is realized, and the efficiency and controllability of the operation process are improved.

The invention discloses a chain type hybrid deep reinforcement learning quadruped robot control system. The system comprises a sensing module, a data processing module, a chain type hybrid reinforcement learning model module, a feedback module and the like. The invention further discloses a control method of the chain type hybrid deep reinforcement learning quadruped robot control system, and the method comprises the steps: S1, collecting bionic motion data, robot state data and environment data, and training based on an attention mechanism space-time diagram neural network and antagonistic imitation learning to obtain a reference gait model containing motion prior; and S2, constructing a three-level parallel simulation environment, setting a progressive course target, training the progressive course target by adopting an improved PPO algorithm, and optimizing the gait stability, the movement efficiency and the environmental adaptability. By means of high-precision data acquisition with the sampling frequency larger than or equal to 240 Hz and antagonistic imitation learning, motion priori knowledge is introduced, the training period can be shortened by 50% or above, abnormal gaits are avoided, and the training process is controllable.

The invention discloses an artificial intelligence robot control system fused with a world model architecture, and the system comprises a control main system which comprises a shared multi-mode backbone network module, a strategy head, and a world model head. A visual encoder, an ontology perception encoder, a text encoder and multi-mode fusion are integrated in the shared multi-mode backbone network module, and the strategy head is used for generating a current action instruction. According to the method, a self-supervision signal provided by a world model is used as an additional training constraint, the dependence on large-scale teaching data is reduced, and a strategy head generates actions based on representation rich in physical dynamic information, so that the device has the advantages that the decision is more stable when facing environmental noise or uncertainty; error accumulation in a long-range task is remarkably reduced, and compared with a traditional open-loop strategy model, the method has the advantage that the generalization ability of training out-of-distribution scenes is remarkably improved.

The invention discloses a robot control system and method based on AI voice, and belongs to the technical field of robot intelligent control. The system comprises a local voice processing module, a dialogue management and context understanding module, an instruction mapping and generating module and a robot communication and control module. The local voice processing module is integrated with a 16 kHz sampling ASR engine, voice-to-text conversion is realized through a 6-layer LSTM network and beam search decoding, and the TTS engine adopts a WaveNet architecture to synthesize voice. A 7 billion parameter large language model is arranged in the dialogue management module, a 32-layer Transform decoder architecture is adopted, 10 rounds of dialogue history is maintained, and intention recognition and entity extraction are achieved through a multi-head self-attention mechanism. And the instruction mapping module performs trajectory planning by adopting quintic polynomial interpolation and quaternion spherical linear interpolation. According to the invention, full-link localization processing is realized, the speech recognition delay is 180 milliseconds, the position error is less than 0.5 mm, and the problems of high delay, high privacy risk and weak complex instruction understanding ability in the prior art are effectively solved.

The invention discloses an intelligent interaction robot control system which comprises a sensing input module, a core processing module, an output execution module and a system management and maintenance module. The perception input module collects multi-modal data through a visual, auditory, environment and touch unit; the core processing module carries out fusion analysis on the data and generates a decision instruction through a multi-modal information fusion unit, a situation cognition and decision unit, an emotion calculation unit and a motion planning unit; the output execution module executes an interaction task through a voice unit, an expression action unit and a motion unit; and the system management and maintenance module provides knowledge base, cloud collaboration and energy monitoring support. Through multi-modal information deep fusion and situational cognition, accurate understanding of user intentions and environments is realized, emotional interaction and personalized service capabilities are provided, the problems that an existing system is single in interaction mode and lacks context understanding are solved, and the intelligent level and user experience of the robot are remarkably improved.

The invention discloses a workshop supervision robot control system based on path planning, and relates to the technical field of intelligent equipment control. The workshop supervision robot control system based on path planning comprises an environment perception and map construction module, a path planning and autonomous navigation module and an intelligent identification and data recording module. Through application of the environment perception and map construction module and the path planning and autonomous navigation module, the robot can update a workshop map in real time and effectively avoid obstacles, the safety and flexibility of operation are improved, the robot can intelligently generate and optimize a path, a control strategy can be adjusted according to actual conditions in the autonomous navigation process, and the autonomous navigation efficiency is improved. And the navigation accuracy and efficiency are improved. And furthermore, the intelligent identification and data recording module not only realizes accurate management of identities of research and development personnel and equipment use, but also improves the accuracy of operation content identification through a deep learning algorithm and a multi-modal information fusion technology.

An AI-driven optimization method for a massage robot control system, and a system. A personalized massage control strategy is generated by means of acquiring massage process feedback data, which carries a guidance instruction, in combination with a multi-dimensional massage feedback knowledge vector sequence and by using a massage control strategy decision-making model. Model parameters are continuously optimized and updated, such that the service of a massage robot can better suit the actual needs and preferences of a user, thereby improving the user experience and the quality of service.

The invention provides a body-equipped robot control system and a body-equipped robot, and relates to the technical field of robots and computers. The system comprises a sensing module, a self-adaptive environment learning module, a man-machine interaction center module and an execution module, the sensing module is used for acquiring multi-modal data, and the multi-modal data comprises multi-modal environment sensing data and multi-modal man-machine interaction data; the self-adaptive environment learning module is used for carrying out environment perception and dynamic modeling based on the multi-modal environment perception data and generating a behavior strategy instruction; the man-machine interaction center module is used for performing intention and emotion analysis based on the multi-modal man-machine interaction data and generating an interaction feedback instruction; and the execution module is used for executing the behavior strategy instruction and the interaction feedback instruction and carrying out physical interaction with the environment and the user. The environment adaptability, the task execution efficiency and the man-machine interaction naturalness of the robot are improved.

The invention discloses high-strength steel laser wire filling welding equipment and method based on AI intelligent identification, and belongs to the field of laser welding and artificial intelligence. Comprising a laser wire filling welding system, a robot control system loaded with a laser wire filling welding head, an element analysis and vision and distance measurement system integrated on the laser wire filling welding head, an online detection system loaded with a CNN training model and a PLC real-time feedback system. Laser wire filling welding is carried out through the laser wire filling welding system and the robot control system, meanwhile, whether an AlSi coating exists on the surface of a high-strength steel plate or not and the appearance of a plate butt joint gap and a welding pool are obtained through the element analysis and vision and distance measurement system, and data are transmitted to the on-line detection system to be analyzed; and then an analysis result is fed back to a laser wire filling welding system through a real-time feedback system, so that the wire feeding type and the wire feeding speed of a wire feeding system are changed, and wire feeding parameters are modified in situ.

To provide a robot control system in which a robot apologizes in an appropriate bowing motion according to severity.SOLUTION: A robot control system (10) includes a robot (12) capable of a bowing motion and, when an operation terminal (16) or a robot (12) determines that the robot has failed, it determines severity in all the categories of the failure, such as temporal loss, pecuniary loss and injuries (physical loss). The robot (12) calculates time spent until it bows (a leaning forward time tb), an angle of a bow (a leaning forward angle θb), and time for bowing (a leaning forward duration time tk) according to the determined severity, and performs a series of bowing motions by controlling an actuator according to the calculated leaning forward time (tb), leaning forward angle (θb), leaning forward duration time (tk) and a time for returning to the original position (a restoration time te).SELECTED DRAWING: Figure 5

The application discloses a multi-part coordinated voice AI programming expression robot control system and method, the system comprises a master control unit, a voice processing module, an AI acceleration unit, a secure storage area, a debugging and program injection interface, an actuator driving circuit and a multi-stage safety hardware; the system extracts a structured control intention vector through voice recognition, combines an emotional action mapping library and physical constraints, and automatically generates or modifies control code by an AI programming agent; after digital twin simulation verification and automatic debugging optimization, the control code is safely burned into hardware and executed, realizing automatic generation and reliable execution of multi-part coordinated expression actions, significantly reducing programming complexity, and improving interaction naturalness and system safety.

The invention relates to the technical field of hazardous chemical substance emergency robot control, in particular to a hazardous chemical substance accident site gas cylinder leakage automatic closing robot control system, which comprises an environmental data acquisition module, a physical equipment device, a multi-modal sensor data real-timely acquired by the environmental data acquisition module, and a timestamp synchronization algorithm for alignment; the state reconstruction module reconstructs a three-dimensional environment map through a deep convolutional neural network and a point cloud segmentation algorithm; the dynamic risk assessment module is integrated with a Bayesian reasoning network to predict the risk and output a dynamic risk field graph; the adaptive exploration decision module adopts a layered reinforcement learning framework and a risk constraint strategy to adjust exploration and utilization balance; the control output module converts the decision action sequence into a robot joint track; and the system coordination engine aggregates the output of each module through a federated learning framework for coordinated operation. The system realizes global adaptive decision through multi-module co-evolution, effectively balances exploration and utilization, and improves the reliability and efficiency of autonomous closing control.

The invention discloses a body-equipped robot control system and method based on multi-modal perception and deep learning, and the system comprises a multi-modal perception module which is used for obtaining and fusing visual information, tactile information and proprioceptive information, and generating a unified state representation; the deep reinforcement learning control module adopts a reinforcement learning algorithm based on an actor-commentator framework and is used for representing an output control strategy according to the unified state, and the reinforcement learning algorithm adopts an experience playback mechanism and a target network technology to realize stable learning; the hierarchical motion planning module is connected with the deep reinforcement learning control module and is used for decomposing a complex task corresponding to the control strategy into high-level strategy planning and bottom-level motion execution; the self-adaptive impedance control module is connected with the hierarchical motion planning module and is used for dynamically adjusting impedance parameters of the robot according to interaction information of the robot and the environment; and the safety guarantee module is used for applying constraint optimization to the control strategy or the motion execution so as to ensure the operation safety of the robot.

The invention discloses a multi-workstation collaborative chemical experiment robot control system, and relates to the technical field of robot control. According to the system, through closed-loop collaboration of the chemical knowledge model module, the robot experiment execution module, the equipment management module and the multi-workstation collaborative scheduling module, intelligent design of an experiment process, full-process automatic execution, standardized integration of data and accurate optimization of parameters are realized, and the efficiency and repeatability of a chemical experiment are greatly improved; errors caused by manual intervention are reduced, the research and development process of chemicals is accelerated, meanwhile, the product performance standard-reaching rate is increased by means of a spectrum structure-activity relationship prediction model, efficient overall utilization of resources of multiple workstations is achieved, and the working efficiency is improved. The problems that in a traditional chemical experiment, cooperative scheduling of multiple workstations is not smooth, experiment process design depends on artificial experience, parameter adjustment lacks scientific data support, experiment data processing is fragmented, and product performance prediction precision is insufficient are solved.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for automatically generating code for contact-rich manipulation tasks by providing action space constraints to a large language model. One of the methods includes obtaining a library of available control methods for a robotic control system to cause a physical robot to move in an operating environment. The method further includes providing an input to an LLM that specifies a manipulation task to be performed using one or more of the available control methods and that specifies one or more action space constraints that constrain the physical movement of the robot in the operating environment according to forces sensed during performance of the manipulation task. Output code can be generated by the LLM, where the output code, when executed by the robotic control system, causes the physical robot to perform the manipulation task.