3513 results about "Robot control" patented technology

The invention belongs to the technical field of robot control, particularly provides a force feedback teleoperation control system and method for the tail end of a mechanical arm of a quadruped robot, and aims at the key challenges that control errors are caused by communication time delay and soft obstacles are difficult to recognize in a dynamic environment. Modeling and judgment are conducted on the contact state of the tail end of the mechanical arm in advance, and feedforward control and buffer adjustment oriented to communication time delay are achieved. And meanwhile, a dynamic semantic map is constructed in combination with multi-source sensing information, and soft obstacle reasoning and path optimization are performed by fusing a tail end force sense change trend, so that the recognition and avoidance capabilities of the system in a complex and invisible obstacle environment are remarkably improved. The system has good perspectiveness, self-adaptability and high redundancy safety characteristics, is suitable for multi-task inspection operation of industrial sites such as a thermal power plant, and is especially suitable for a remote man-machine cooperative operation scene in a narrow space.

The invention relates to the technical field of robot control, and discloses a robot control method, system, equipment and medium based on a multi-modal large model, and the method comprises the steps: collecting the multi-source modal data of a scene where an operation task is located, and carrying out the processing through a machine learning model, obtaining a multi-modal feature, and carrying out the position coding and Transform fusion processing, multi-modal fusion features are obtained, the multi-modal fusion features and the constructed job task knowledge base are input into a large language model to decompose a target job task, a human-in-the-loop mechanism is introduced to optimize a decomposition result, and a sub-task sequence is obtained; according to a subtask type in the subtask sequence, processing the subtask sequence through a visual language action model or a reinforcement learning model, and generating a motion instruction to enable the robot to start an execution process of the target operation task; live-line work tasks are processed through the multi-modal large models LLM, VLA and the like, and the work efficiency of the autonomous distribution network live-line work robot is improved.

The invention belongs to the technical field of robot control, and discloses a high-gear-ratio humanoid robot robust walking control method and system based on potential dynamics self-adaption, and the method comprises the steps: designing a control strategy training frame based on deep reinforcement learning, and carrying out the optimization through an Actor-Critic structure and a PPO algorithm; constructing a potential dynamic adaptive network LDAN, and extracting environment and ontology dynamic parameters through a variational auto-encoder; designing a multi-dimensional reward function; constructing a periodic gait library by using von Mises distribution and motion capture data; gradually introducing terrain disturbance and dynamic change through curriculum type simulation training; the trained strategy and the LDAN module are deployed on the high-gear-ratio driven humanoid robot, the problems that the high-gear-ratio humanoid robot is poor in motion stability, poor in adaptability and insufficient in action expression in a variable environment are solved, and the high-gear-ratio driven humanoid robot has the advantages of being high in robustness, high in natural expressivity and high in migration ability.

The invention relates to the technical field of robot control, and discloses a heavy-load robot motion trail method and system based on machine learning. The method comprises the steps that historical movement track data of the heavy-load robot in a working scene are collected, and the data comprise a joint position sequence, an end effector pose sequence and environment obstacle distribution information; the data is preprocessed, track features are extracted, a space-time correlation matrix is constructed, and the matrix is used for representing the dynamic coupling relation between joint movement and the tail end pose; training a trajectory prediction model containing a long and short-term memory network and an attention mechanism based on the matrix, and generating a collaborative mapping relation between a joint position and a tail end pose; obtaining a current task target pose sequence and an environment constraint condition in real time, and outputting a candidate track set meeting dynamic constraint through a model; and adopting a multi-objective optimization algorithm to screen candidate tracks, generating an optimal track instruction and issuing the optimal track instruction to an execution mechanism. The method adapts to the complex characteristics and variable working conditions of the heavy-load robot, and the track adaptability is improved.

The invention relates to the technical field of artificial intelligence welding, and discloses an automatic welding robot based on artificial intelligence and a welding system thereof. The system comprises a welding feature acquisition module, a process parameter generation module, a real-time regulation and control module and a motion planning module. The welding characteristic acquisition module is used for acquiring three-dimensional contour data, material component information and welding seam geometric parameters of a workpiece to be welded, and generating a welding characteristic spectrum through characteristic fusion; a process parameter generation module retrieves a matching template from a welding knowledge base according to the parameters, and outputs a reference welding process parameter combination in combination with an environment temperature and humidity compensation coefficient; the real-time regulation and control module dynamically corrects the reference parameters to generate an optimization instruction according to the molten pool form, thermal radiation distribution and electric arc voiceprint characteristics in the welding process; and the motion planning module calculates a motion track, attitude parameters and a speed curve of the welding execution mechanism according to the optimization instruction to form a robot control instruction set. The system can improve the intelligent level of welding, guarantees stable welding quality, and is suitable for welding scenes of multiple manufacturing industries.

The invention discloses a multi-robot task conflict resolution and dynamic scheduling system and method, and belongs to the technical field of robot control. The system comprises a perception detection layer which is used for acquiring operation information of a plurality of robots and a space-time semantic map of a to-be-executed task executed by the robots, and generating conflict information under the condition that at least two target robots are detected to conflict; the decision scheduling layer is used for determining task execution priorities of the to-be-executed tasks according to the conflict information and priority factors and value functions of the to-be-executed tasks corresponding to the target robots so as to rearrange the to-be-executed tasks corresponding to the target robots and generate a task sequence; and the execution control layer is used for generating a dynamic scheduling instruction according to the task sequence, the space-time semantic map and the operation information of the target robot and issuing the dynamic scheduling instruction to the corresponding target robot. The system can flexibly cope with a dynamic scheduling scene of multiple robots in real time.

The invention discloses a double-arm robot autonomous control system and method based on teleoperation and visual features. The system comprises a teleoperation acquisition module, a multi-view visual perception module, a data synchronization and demonstration acquisition module, a strategy model training module, an autonomous strategy execution module, a track deviation detection and takeover module and a hybrid control interface module. Human demonstration is completed through teleoperation, multi-modal information of images, tracks, clamping jaws and muscle activation is collected, perception features are fused by adopting multi-view space-time alignment and a cross-view attention mechanism, strategy learning is completed in combination with an end-to-end large model, and in the autonomous operation stage, the multi-view space-time alignment and the cross-view attention mechanism are combined with the end-to-end large model. The risk of current operation is predicted and evaluated through track deviation detection and collision probability, the autonomous control proportion is dynamically adjusted, manual intervention is allowed when necessary, the safety and stability of the whole system are improved, the robot control mode of seamless switching between man-machine cooperation and autonomous and teleoperation is achieved, and the method is suitable for object control tasks in complex and highly variable environments.

The invention relates to the technical field of robot training. The robot self-adaptive training method based on reinforcement learning comprises the steps that task sub-target information is generated through a high-level strategy network, the task sub-target information is input into a low-level execution network, an action control instruction is generated according to the task sub-target information, interaction feedback information is collected in the execution process, and the action control instruction is sent to a robot through a robot. Calculating a reward value according to the interaction feedback information, carrying out association processing on the reward value and the scene complexity parameter, executing a dynamic reward shaping operation, generating an adjusted reward signal, generating a strategy model optimized by meta-learning based on the adjusted reward signal, loading the strategy model in a simulation environment, and carrying out dynamic reward shaping. A target strategy model optimized through simulation training is generated, the target strategy model is loaded to the robot, and the robot is controlled to execute task operation in the actual interaction scene. The method has the effect of realizing adaptive task learning of the robot in a multi-interaction scene.

The invention discloses a finite time tracking adaptive control method for a mechanical arm based on a neural network, and relates to the technical field of industrial robot control. The method comprises the following steps: constructing a kinetic model of the mechanical arm, obtaining an existence form of an unknown nonlinear term in the model, and defining a joint position tracking error and an error change rate of the mechanical arm; constructing a sliding mode dynamic equation based on the tracking error and the error change rate; a BP neural network is adopted to approach the unknown nonlinear dynamic state of the mechanical arm, and the mapping relation between a network input vector and an output vector is determined; combining a sliding mode dynamic equation with BP neural network output, and designing a finite time control method including adaptive gain; and a self-adaptive updating method of BP network weight and sliding mode gain is deduced, so that the tracking error of the mechanical arm is converged to a zero neighborhood within preset time, and self-adaptive control of the mechanical arm is completed. According to the method, high-precision trajectory tracking within the preset time can be realized, and the anti-interference capability is high.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a task processing method, device, equipment and medium based on an expert sub-path, comprising: setting a shared attention layer, an understanding expert sub-path, a control expert sub-path and a router module in a neural network, the method comprises the following steps: constructing a robot action trajectory data set, a visual text pair data set and a structured language template set, training based on the robot action trajectory data set and the structured language template set to obtain an intermediate training model, and training based on the intermediate training model and the visual text pair data set to generate a unified training model; and when target task input is received, the router module selects a corresponding expert sub-path, and a result is output through the unified training model. According to the method, staged training is combined with an expert mixing mechanism, catastrophic forgetting is avoided, semantic understanding and robot control keep stable coexistence in a unified model, and the accuracy of task execution is improved.

The invention discloses a spraying robot trajectory planning method based on depth camera scanning. The method comprises the steps that wall surface boundary polygon data, an initial spraying stroke set and a spraying dosage model parameter set are obtained; calculating a predicted coating thickness field, and performing difference calculation on the predicted coating thickness field and a preset target thickness to generate a thickness error field; performing connected domain clustering on the thickness error field to generate topological thickness error regions, and determining region type labels for the topological thickness error regions one by one; calling a matched editing operator from a discrete stroke editing operator library, performing geometric constraint verification, and generating a candidate editing scheme; and evaluating the candidate editing schemes based on a preset comprehensive scoring function, updating the initial spraying stroke set by using the scheme with the optimal score, obtaining an optimized spraying stroke set, and converting the optimized spraying stroke set into a robot control instruction. According to the method, the problem that global coverage and local thickness uniformity cannot be considered in traditional geometric planning is solved, and high-quality full-automatic spraying is achieved.

The invention provides a robot control method based on Model-Based and RL, and relates to the technical field of automatic control. According to the method, a high-level task atlas model and a predefined task action set are constructed, a target task is mapped into a state node, graph search is carried out in combination with a current world state, an optimal task action path is planned, and a first action instruction is output. And calling a baseline strategy in the simulation environment to generate a control instruction, executing feasibility verification, compensating the deviation between the simulation and the real environment through the error prediction model, correcting the real control instruction, and then driving the robot to execute. And dynamically updating the success probability weight of state transition in the atlas based on the execution result, and feeding back the executed state for subsequent decision. According to the method, the reliability, the adaptability and the execution safety of migrating a simulation strategy to a real robot are improved, and closed-loop optimization and continuous self-adaption of a complex task are realized.

The invention belongs to the technical field of robot control, and discloses a bionic robot control method and system based on a muscle fiber model.The method comprises the steps that a multi-scale muscle model is constructed based on a scale division mechanism, and the multi-scale muscle model is optimized by means of physiological state variables and fatigue accumulation variables to obtain a muscle fiber model; according to the muscle group cooperation relation and the kinematics model of the robot limbs, geometric structure adaptation is carried out on the model in combination with a deformation compensation strategy; on the basis of the fused multi-sensor data, a muscle fiber model and a model after geometric structure adaptation are utilized to construct a feedback adjustment mechanism; and on the basis of an adaptive neural network algorithm, the muscle fiber model, the model after geometric structure adaptation and a feedback adjustment mechanism are optimized, solving is carried out in combination with a multi-objective optimization algorithm, and command information of the limbs of the bionic robot is obtained and executed. Accurate control over the limb joint position, the torque and the impedance of the bionic robot is achieved.

The invention belongs to the field of robot control, and particularly relates to a robot self-adaptive impeller welding control method and system fused with multi-modal data, and the method comprises the steps: obtaining an impeller workpiece image and three-dimensional point cloud data through an industrial vision subsystem, and extracting a three-dimensional welding seam position point set representing a welding seam track; generating a candidate welding path set based on welding seam geometric feature analysis; in combination with welding seam morphology and process requirements, optimal welding process parameters are predicted through a regression model, and a welding gun attitude angle is calculated through quaternion conversion according to a curved surface normal vector; in the welding process, the relative position deviation of a robot and a workpiece and the parameter deviation of welding current / voltage and a planned value are monitored in real time, when the deviation exceeds a preset tolerance interval, a PID control algorithm is adopted to dynamically adjust robot motion parameters or welding process parameters, and closed-loop control over the welding process is achieved; according to the method, precise planning of the welding path and self-adaptive regulation and control of the process are achieved, and the welding quality and the forming consistency are remarkably improved.

The invention provides a robot control strategy migration method and device, a medium and a program product, and the method comprises the steps: collecting a state-action sequence, generated by a pre-training strategy model, of a robot in a real operation environment, and carrying out the preprocessing, and obtaining structured training data; judging whether a preset updating condition is met or not based on the running state, and when the preset updating condition is met, performing fine adjustment on the strategy model by utilizing the training data to generate an updated strategy model; thermally deploying the updated strategy model to a real operation environment of the robot, so that the robot operates based on the updated strategy model and generates new operation data under the condition of not interrupting task execution; the three stages of data collection, preprocessing, strategy fine adjustment and model deployment are executed circularly, data interaction and flow decoupling between the stages are achieved through a message queue, and continuous optimization based on real operation feedback is achieved. According to the method, the stability and generalization ability of strategy migration are improved through condition-triggered cyclic fine tuning and a hot deployment mechanism of uninterrupted operation.

The invention relates to the technical field of robot control, and discloses a master-slave cooperation-based control method, device, equipment and medium, and the method comprises the steps: collecting a spatial pose, a contact force and a dual-view image, and constructing a multi-modal demonstration data set; executing time alignment and normalization to form a standardized input sequence; action features, force features and visual features are extracted through the action modal coding network, the mechanical modal coding network and the visual coding network; fusing to form a multi-modal tensor sequence, and inputting the multi-modal tensor sequence into a Transform decoder to generate a joint time sequence representation; outputting a training action prediction vector from the joint time sequence representation through an action predictor, constructing a supervision loss function in combination with expert demonstration annotation to update each network, and obtaining an optimization control model; and processing the real-time input control driving execution mechanism based on the optimization control model. According to the method, the control model is trained and optimized through multi-modal sensing and time sequence modeling, the joint control instruction is generated in deployment, and stable execution of a complex interaction task is achieved.

The invention relates to the technical field of robot control, particularly discloses a path planning and dynamic obstacle avoidance control method for multi-task collaborative operation of an industrial robot, and aims to solve the problems of task scheduling conflict, dynamic obstacle response lag and low collaborative efficiency in a multi-robot system. The method comprises the following steps: constructing a task-resource joint scheduling model and generating initial task allocation; planning a conflict-free collaborative path based on an improved space-time A star algorithm; predicting a dynamic obstacle trajectory by using an LSTM network and generating a space-time envelope; constructing a second-order safety barrier function fusing task priorities; local obstacle avoidance re-planning is realized through rolling horizon model predictive control; and the global rescheduling is triggered when the task delay exceeds the limit or the deadlock risk occurs. According to the technical scheme, closed-loop linkage of global task collaboration and local dynamic obstacle avoidance is realized, and the system collaboration efficiency, the obstacle avoidance success rate and the operation robustness are remarkably improved.

The invention provides a robot control method and device, equipment and a storage medium, and relates to the technical field of robot control. The method comprises the steps of obtaining robot data of a robot executing a task, and determining a learning data set according to the data; building a first robot action prediction model based on the initial visual language model; obtaining a second robot action prediction model according to the data set and the first robot action prediction model; a robot time sequence, image data and a language instruction are taken and input into a second robot action prediction model, the time sequence data are input into a second language model through a preset time sequence model and a multi-layer projector, the image data are input into the second language model through a visual encoder and the projector, and the language instruction is input into the second language model through the first language model; the second language model outputs continuous actions to be executed; and completing the task according to continuous action control. And the time sequence model captures time sequence characteristics, so that the second robot action prediction model outputs continuous actions to be executed, and the operation smoothness and continuity are effectively guaranteed.

The invention discloses a fusion control method and system for mechanical arm flaw detection operation during robot dog climbing, and relates to the related field of robot control, and the method comprises the steps: building a climbing feature sequence when the position of a robot dog meets a detection working position; performing multi-dimensional injury condition prediction on a to-be-detected target to obtain target injury condition prediction distribution, and performing arm-out operation control analysis on the mechanical arm; performing multiple rounds of propagation evolution optimization on the arm-out operation control space to generate an arm-out control optimization strategy; interference triggering prediction is carried out on the robot dog, optimization compensation is carried out on the robot dog according to an interference triggering prediction result, and an interference compensation strategy is obtained; and performing flaw detection fusion control on the to-be-detected target, and executing flaw detection control closed-loop correction according to the flaw detection process induction data. The technical problems that in existing flaw detection work, climbing and flaw detection are lack of a dynamic cooperation mechanism, the environmental adaptability is poor, and the flaw detection precision is low are solved, and the technical effect that the environmental adaptability and the flaw detection precision are improved through climbing and flaw detection cooperation optimization is achieved.

The invention relates to the technical field of data processing, in particular to a robot control method, device and system based on a diffusion model and a medium, and the method comprises the steps: collecting the position information of the tail end of an index finger and the state information of a flexible linear object in a human hand teaching process, and constructing a training sample; training the training sample by using a diffusion model, and learning mapping from a high noise state to a clear target state through a noise prediction network in the training diffusion model to obtain a trained diffusion model; the training process of the diffusion model comprises forward noise addition and reverse noise reduction; the state of the flexible linear object and the tail end position of the mechanical arm are collected, a current observation environment is constructed, the current observation environment is input into the trained diffusion model, a target action sequence is generated, and the mechanical arm is controlled to execute control actions based on the target action sequence; according to the invention, the accuracy and real-time performance of the robot to control the flexible linear object can be improved.

The invention discloses a heterogeneous robot control method and system based on an extensible command library, electronic equipment and a storage medium, and the method comprises the steps: dividing a plurality of different types of commands from the angle of robot commands, and defining a unique code for the commands; constructing a hardware-independent command library on the to-be-executed command queue according to the unique code of each command; constructing a command mapping table according to the code of each command under the to-be-executed command queue, and expanding according to the command codes based on the commands to form a command library related to the robot; based on man-machine interaction of a large model, a specific command to be executed by a user is recognized through semantic understanding and command recognition, and then the recognized command is sent to a to-be-executed command queue from a hardware-independent command library through command execution management; and monitoring a to-be-executed command independent of the robot in real time, mapping a command irrelevant to hardware into a specific command of the robot through a robot related command library, and executing the specific command of the robot at the same time.

A robot control method based on tactile prediction pre-training comprises the following steps: acquiring and generating a human playing data set consisting of three-channel image tensors in an offline stage, and training a constructed conditional diffusion model comprising a tactile encoder, a tactile decoder and an action and visual encoder; in the online stage, the trained conditional diffusion model is integrated into a standard imitation learning strategy network, and an action instruction of the robot is generated according to the state of the robot, the current visual features and the tactile feature vectors extracted by the imitation learning strategy network. According to the method, a specific agent task is completed by training a deep neural network model, that is, a future tactile signal sequence is predicted according to historical information and future action intentions; the model is enabled to characterize generic haptic features contacting physical dynamic laws for further migration into downstream robot control tasks.

The invention relates to the technical field of robot control and somatosensory interaction, and particularly discloses a knee joint exoskeleton robot control system based on somatosensory interaction. The system comprises a somatosensory signal acquisition and fusion module, a personalized dynamic model construction module, an adaptive intention decision module, a variable impedance compliance control module and a rehabilitation process evaluation and parameter self-tuning module. Through cooperative work of the modules, precise recognition of the motion intention of a wearer, online construction of an individualized biomechanical model and flexible and adaptive motion control are achieved, control parameters can be automatically adjusted according to the rehabilitation process, and therefore the flexibility and individuation level of man-machine interaction and the effectiveness of rehabilitation training are improved.

The invention belongs to the technical field of robot control, and particularly relates to a self-adaptive whole-body control method suitable for a quadruped robot in an uncertain dynamic environment, and the method integrates an extended state observer (ESO), a model prediction controller (MPC) and a whole-body controller (WBC) based on hierarchical optimization. And a closed-loop control architecture is constructed to improve the robustness and motion coordination ability of the quadruped robot in a complex environment. Firstly, external disturbance is estimated and compensated in real time through ESO; then, the MPC optimizes future system behaviors in a rolling manner under the condition of considering interference terms, and an expected foot end counter-acting force is output; and finally, the WBC is combined with the priorities of the multiple tasks to generate all joint control instructions in a constraint optimization form, and task collaboration and dynamic adaptation are achieved. The method has the advantages of being high in disturbance self-adaptive capacity, high in control precision, suitable for a multi-task environment and the like, and is particularly suitable for quadruped robot control tasks in complex dynamic scenes such as transportation and search and rescue.

The invention relates to a multi-mode-based body robot control method and device, electronic equipment, a readable storage medium and a program product. The method comprises the steps of obtaining a task instruction, obtaining multi-modal environment data based on the task instruction, carrying out fusion processing on the multi-modal environment data to obtain fused multi-modal sensing information, and determining a task path and a task action sequence for a target task based on the multi-modal sensing information and the state of the robot with the body. And converting the task path and the task action sequence into a control instruction for the robot with the body, thereby controlling the robot with the body to execute the target task according to the control instruction. According to the method, multi-modal environment data are fused, so that the perception robustness of the body robot in a dynamic and uncertain environment can be ensured, the real-time response capability and the accuracy of intelligent decision can be optimized, and the adaptability and the execution capability of the body robot to complex working conditions are remarkably improved.

The invention provides a foot type robot task planning control method and system, and relates to the technical field of robot control, and the method comprises the steps: obtaining a task instruction and multi-source sensing data of a robot; extracting the task instruction to obtain a semantic feature, and constructing a structured environment representation according to the multi-source sensing data; based on the semantic features, performing retrieval from a preset historical task library to obtain historical task experience fragments corresponding to the task instruction; a hierarchical task plan of the robot is generated through a language model according to historical task experience fragments in combination with structured environment representation, feasibility and safety verification is carried out, a target skill sequence of the robot is obtained, skill arrangement is carried out, a skill execution scheduling strategy is generated, and the robot is driven to execute the skill; and meanwhile, when the robot executes skills, real-time closed-loop correction is performed on a skill execution scheduling strategy according to real-time sensing data of the robot. According to the invention, the execution effect of the foot-type robot in a complex long-time task is improved.

The invention relates to the technical field of robot control, and discloses an industrial robot adaptive control method and system based on multi-modal sensor fusion, and the method comprises the steps: collecting multi-modal original data, and carrying out the time-space alignment; capturing space-time semantic association of visual textures, tactile pressure distribution and force sense fluctuation in the multi-modal data through a multi-head attention mechanism guided by a physical model, and performing space-time registration; a CNN-LSTM hybrid model is adopted to extract visual texture features and time sequence tactile features in the physical information enhanced multi-modal feature matrix; and carrying out dynamic weight distribution on the fusion feature vectors with physical consistency by utilizing a weight distribution model driven by element reinforcement learning to generate dynamic weighted fusion features. According to the method, the spatial positioning precision of the industrial robot in a precise assembly scene is greatly improved, the contact force control stability is greatly improved, and the control robustness in a complex operation scene is remarkably enhanced.

The invention relates to the technical field of quadruped robot control, and discloses a quadruped robot anti-disturbance motion control method based on a cost weight adaptive mechanism, which comprises the following steps: constructing a quadruped robot state equation based on a single rigid body dynamic model, a model prediction control problem with cost weight, friction cone constraint and gait constraint is formed through discretization; a cost weight self-adaptive mechanism based on disturbance observation is introduced on the basis of a model prediction control framework, the disturbance intensity is estimated by taking the attitude error of the fuselage and the corresponding change rate as disturbance observation values, and the cost weight corresponding to the attitude in the model prediction control problem is dynamically adjusted; by solving a model prediction control problem, an expected ground reaction force and a target state are calculated in real time, and motion control of the quadruped robot is realized in combination with a gait planner and a joint controller. According to the invention, the motion stability and anti-disturbance performance of the quadruped robot under external disturbance are improved based on a cost weight adaptive mechanism of disturbance observation.

The invention discloses a robot image-free visual target docking method and system based on multi-modal perception, and the method comprises the steps: carrying out the recognition calculation of a preset target in the image data of the environment in front of a robot through a target detection model YOLOv4-tiny, and constructing a robot control feedback quantity; radial distance information of an object in the environment is obtained, a scanning range is divided through a regional strategy, straight line fitting calculation is conducted, and a deviation evaluation value of the robot relative to the yaw angle is constructed; and the robot accumulative mileage is obtained, finite-state machine hierarchical decision making and mistaken stop prevention judgment are conducted in combination with the robot control feedback quantity and the robot relative yaw angle deviation evaluation value, and robot graph-free visual target docking is achieved. According to the invention, full-process autonomous control of the robot from target discovery, navigation on the way, obstacle avoidance to end fine alignment can be realized. The robot graph-free visual target docking method and system based on multi-modal perception can be widely applied to the technical field of graph-free navigation.

The invention belongs to the field of robot control and bionic machinery, and particularly relates to a sensing-driving-control integrated dexterous hand single-finger modularization control method which comprises the following steps that a series-parallel connection hybrid three-degree-of-freedom mechanical structure is adopted, a modularization single-finger mechanism is constructed, and a single-finger driving control circuit board is designed on the modularization single-finger mechanism; a motor outputs joint driving torque through a lever transmission mechanism, and the joint motion state is fed back in real time through a magnetic encoder. Collecting a contact force vector F in real time through a sensing system; the single-finger driving control circuit board adopts a layered control framework to sequentially execute current closed-loop control, speed closed-loop control and position closed-loop control; based on the contact force vector F, generating a joint angle compensation amount through an admittance control model; a target joint angle instruction is received through a bus, and multi-module cooperative control is achieved. According to the invention, a current-speed-position three-ring nested control architecture is designed, and the disturbance rejection ratio is effectively improved.