58 results about "Motion strategy" patented technology

The invention discloses a quadruped robot anti-disturbance motion control method based on reinforcement learning and application, and belongs to the field of robot motion control. Firstly, a self-adaptive propulsion control frame is provided, and a propeller and a leg movement system of the quadruped robot are deeply fused. And secondly, through cooperative training of a double-encoder system (a teacher encoder and a student encoder) and a predictor, hidden state extraction and environment disturbance reconstruction are realized, so that the robot adjusts a motion strategy in real time under complex scenes such as actuator faults and water flow interference. And finally, in combination with multi-stage reinforcement learning training and privilege information utilization, strategy network output is optimized, and a speed and trajectory tracking task is completed. The motion robustness of the robot under unknown interference and damage conditions is remarkably improved through cooperative control of the propellers and the legs, anti-disturbance decision of hidden state driving and dynamic reward function design. The method is suitable for amphibious environments, can adapt to diversified disturbance scenes without additional fine adjustment, and has high practicability and reliability.

The invention belongs to the technical field of three-dimensional scanning path planning and industrial automatic detection, and particularly relates to a full-coverage scanning path planning method for a large complex structural part. The revolutionary optimization of the three-dimensional scanning path of the large structural member is realized by constructing a comprehensive technical system of curvature self-adaptive sampling, pose collaborative optimization, a three-stage Weibull motion strategy, real-time collision detection and whole-process efficiency improvement. According to the scheme, geometric feature perception, motion continuity guarantee, algorithm adaptability enhancement and operation safety control are creatively integrated, a technical breakthrough is formed in three dimensions of non-blind area coverage, high motion efficiency and zero collision risk, and meanwhile, through parameterization design and a cross-platform compatible framework, the operation safety is improved. Deployment flexibility and system robustness in an industrial scene are remarkably improved, and a complete solution with high precision, high efficiency and high reliability is provided for automatic detection of a complex curved surface.

The invention discloses a robot motion control optimization method, device, equipment and medium, and the method comprises the steps: inputting task description in a natural language form, robot state information, a historical execution track and environment feedback information into a preset large language model; through the large language model, selecting a target motion strategy of the robot according to the task description; when it is detected that the task of the robot fails or the action of the robot is abnormal, a reward function used for controlling a deep reinforcement learning controller of the robot is reconstructed; and when the state of the robot is abnormal, parameters of the deep reinforcement learning controller are adjusted and optimized, the motion stability, the task completion efficiency and the strategy adaptability of the robot in a high-risk, high-temperature and high-complexity scene are remarkably improved, and the self-adaptive adjusting and optimizing capability and the abnormity recovery capability of the robot in a dynamic environment are enhanced.

The invention discloses a multi-unmanned aerial vehicle cooperative efficient deployment method in a dynamic environment, and the method comprises the steps: S1, constructing a multi-target optimization model based on a genetic algorithm, and solving the multi-target optimization model, so as to plan a feasible path with the least number of relay unmanned aerial vehicle I nodes between a base station and a nest; and S2, constructing an intelligent agent control model based on a deep reinforcement learning algorithm, so that each relay unmanned aerial vehicle II can adjust a motion strategy according to the real-time position of the task unmanned aerial vehicle, the communication requirement and the environment change in a dynamic task scene to guarantee the stability of a communication link between the aircraft nest and the task unmanned aerial vehicle. According to the two-stage unmanned aerial vehicle cooperative efficient optimization deployment scheme provided by the invention, the efficiency and the stability of an air communication link are remarkably improved in a complex three-dimensional space environment.

The invention provides a motion control method and device of a foot type robot, equipment and a medium. The method comprises the steps that state information, coding information and historical actions of the foot type robot at the previous moment and first sensing information at the current moment are obtained; inputting the state information of the previous moment, the coding information and the historical actions into a world model to obtain the state information of the current moment output by the world model; inputting the state information at the current moment and the first sensing information into a motion strategy model to obtain a target action at the current moment output by the motion strategy model; and controlling the movement of the foot type robot according to the target action at the current moment. Any terrain environment can be accurately sensed, so that the stability of the foot type robot in the movement process is ensured, the problems of falling or movement faults and the like are avoided, and the movement control effect of the foot type robot is improved.

The invention relates to a quadruped robot active compliance control method based on hierarchical reinforcement learning. The method comprises a bottom-layer motion strategy network and an upper-layer compliance control strategy network, the bottom layer motion strategy network comprises a basic encoder, a force estimation head, a speed estimation head and a basic strategy network module; the basic encoder is used for outputting a low-dimensional feature vector; the force estimation head is used for estimating the current external force borne by the quadruped robot; the speed estimation head is used for estimating the current trunk speed of the quadruped robot; the basic strategy network module is used for generating a current expected joint position of the quadruped robot; and the upper-layer compliance control strategy network is used for generating a current residual speed instruction and adding the current residual speed instruction and the current trunk speed instruction to obtain a corrected current trunk speed instruction. By adopting the method, high coupling of disturbance estimation and a compliance control module can be realized, and active compliance adaptive to continuous interference can be achieved.

The invention provides a quadruped robot wet-slippery rugged terrain motion control method based on explicit and implicit estimation, and aims to solve the problem that the motion ability of a quadruped robot under the wet-slippery rugged terrain is limited due to the fact that the existing method cannot fully extract environment and robot motion state information. Historical observation information and a current action are utilized to explicitly estimate an environment friction factor, a four-foot contact state and a robot centroid velocity, and current motion model information of the robot is implicitly estimated through a method of predicting a motion state at a next moment. Environmental information, robot motion information and implicit vectors containing robot motion model information are introduced into input of a motion strategy, higher sensing capacity for the motion state and the environment is provided for a motion network, and a novel control method suitable for the quadruped robot to move in the slippery terrain is obtained.

The invention relates to the technical field of intelligent robot control and artificial intelligence, and discloses a robot dynamic trajectory control method based on reinforcement learning and multi-sensor fusion, and the method comprises the steps: firstly fusing multi-modal sensor data through extended Kalman filtering, and predicting the time sequence distribution of dynamic obstacles through a long-short-term memory network; meanwhile, the dynamic operability and singularity risk factors of the robot are calculated, on this basis, a reinforcement learning network based on an attention mechanism is constructed to generate a high-level motion strategy, the high-level motion strategy is converted into a bottom-layer execution instruction through a variable impedance controller and a convex optimization torque distribution module, and singular points are avoided by using null-space characteristics. In addition, according to the method, model parameters are finely adjusted in real time by monitoring and predicting errors and the safety intervention degree on line. According to the method, organic fusion of logic decision and physical execution is realized through a layered architecture, and the operation safety, robustness and control precision of the robot in a dynamic environment are remarkably improved.

The invention discloses a robot whole body control method and system based on real-time inertia motion capture and reinforcement learning, and belongs to the field of robot control. The system comprises a motion capture module, a data processing and forward kinematics module, a motion redirection and optimization module, a general motion strategy control module and a real-time control and driving module which are connected in sequence, and an end-to-end closed-loop control assembly line is formed through a shared memory and a high-speed communication protocol. According to the method, human body joint data are collected through inertia motion capture equipment, high-quality mapping from a human body posture to a robot model is achieved through posture calculation, non-uniform scaling and two-stage differential inverse kinematics optimization, and a stable joint instruction is generated in combination with a reinforcement learning strategy trained by a PPO algorithm. The method solves the problems of lack of feedback closed loop, joint deadlock, contradiction between fidelity and stability and the like in the prior art, has the characteristics of high robustness and high expansibility, and can be widely applied to scenes of remote operation, action reproduction and the like.

The invention relates to the technical field of track obstacle avoidance, and discloses a track robot path obstacle avoidance data updating method and system, and the method comprises the steps: carrying out the vector assembly of multi-dimensional features in a real-time environment data flow of a track robot, and obtaining a primary feature vector, carrying out abnormal mode identification on the primary feature vector and a historical normal mode library to obtain a dynamic abnormal feature; according to the dynamic abnormal features, reconstructing a local topology of a pre-stored path knowledge graph to generate an obstacle influence domain; analyzing the field intensity distribution change trend of the obstacle influence domain to obtain a gradient field, and mapping the dominant direction of the gradient field into a conflict resolution strategy; correcting a predetermined path of the orbital robot to obtain a conflict-free path trajectory fragment; performing efficiency judgment on the conflict-free path trajectory fragments to obtain a multi-dimensional evaluation result; fusing multi-dimensional evaluation results to obtain an emergence type motion strategy; the efficiency of updating the path obstacle avoidance data of the rail robot can be improved.

The invention provides an action mask assisted obstacle avoidance target tracking method based on deep reinforcement learning, and the method comprises the steps: constructing simple to complex obstacle-target combinations based on an obstacle distribution type and a target motion type, and each combination corresponds to a training stage; in each training stage, according to an obstacle distribution type and a target motion type corresponding to the obstacle-target combination, determining an environment mode of the current stage, and further constructing a task execution map; the input of the main strategy network and the target network is robot observation information introduced with the action masks, and the optimal action output is generated after the action probability distribution output by the main strategy network and the target network is corrected by utilizing the action masks. By using the method, a reasonable motion strategy can be provided for the robot in an environment with a dynamic and static mixed obstacle and a variable-motion-mode target, the risk that the robot collides with the obstacle is reduced, and effective tracking of the target is realized and maintained.

The invention discloses a salamander-imitating robot omni-directional motion control method and system based on reinforcement learning, and belongs to the field of electromechanical system control. The method comprises the following steps: acquiring robot state information and a motion instruction; a periodic phase variable is generated through a phase integration module, and target actions of all joints are output through a track generator; designing a reward function based on behavior constraint, and constraining motion directivity and attitude stability; the morphological symmetry of the body structure of the salamander-imitating robot is utilized to symmetrically enhance the state-action sample so as to expand training data; and a reinforcement learning algorithm is adopted, and a stable and efficient omnidirectional motion control model is obtained according to a reward feedback and symmetric enhancement data iteration updating control strategy. The method can realize the generation of the omni-directional motion strategy driven by reinforcement learning without presetting a gait model, has the advantages of natural motion mode, high control precision and strong adaptability, and can be widely applied to the fields of complex terrain detection, intelligent inspection and the like.

In various examples, policy prediction-based motion planner systems and methods for autonomous and semi-autonomous systems and applications are provided. A scenario tree structure may be generated that represents potential behaviors of one or more peripheral agents based on perception data of a scene within which an ego vehicle operates. A joint MPC algorithm may optimize the motion of an ego vehicle within the context of the scenario tree structure to produce a policy tree structure. An MPC policy prediction model may be trained to predict the policy tree structures that a joint MPC algorithm would produce, given a set of environmental perception data. An ego vehicle may comprise a trained MPC policy prediction model that receives perception data, and based on that input predicts a policy tree structure that may be used to define a motion policy for navigating the ego vehicle through the scene.

The present application relates to the technical field of track obstacle avoidance, and discloses a track robot path obstacle avoidance data updating method and system, the method comprising: assembling a plurality of dimensional features in real-time environment data flow of the track robot into a vector group to obtain a primary feature vector, and performing abnormal mode identification on the primary feature vector and a historical normal mode library to obtain dynamic abnormal features; reconstructing a local topology of a pre-stored path knowledge graph according to the dynamic abnormal features to generate an obstacle influence domain; analyzing a field strength distribution trend of the obstacle influence domain to obtain a gradient field, and mapping a dominant direction of the gradient field into a conflict resolution strategy; correcting a predetermined path of the track robot to obtain a conflict-free path trajectory segment; performing efficiency determination on the conflict-free path trajectory segment to obtain a multi-dimensional evaluation result; and fusing the multi-dimensional evaluation result to obtain an emergent motion strategy; the present application can improve the efficiency of track robot path obstacle avoidance data updating.

The invention provides a high-precision control method applied to multi-axis independent steering, and the method comprises the steps: obtaining a control instruction, and determining a corresponding motion control strategy according to the control instruction; based on the motion control strategies, the transverse control angle and the longitudinal control torque of the steering shaft are output, and the motion control strategies comprise an arc motion control strategy, a straight motion control strategy, an in-situ steering motion control strategy and a reversing motion control strategy. According to the method, flexible movement of the multi-axis equipment can be realized by comprehensively utilizing various movement strategies, the requirement of a high-speed movement scene is met, the safety of equipment movement control is improved, and accurate and effective movement control can be performed on the multi-axis cooperative steering equipment.

This application relates to the fields of intelligent robot control and artificial intelligence technology, and discloses a robot dynamic trajectory control method based on reinforcement learning and multi-sensor fusion. This method first utilizes extended Kalman filtering to fuse multimodal sensor data and then predicts the temporal distribution of dynamic obstacles through a long short-term memory network. Simultaneously, it calculates the robot's dynamic maneuverability and singularity risk factors. Based on this, a reinforcement learning network based on an attention mechanism is constructed to generate high-level motion strategies, which are then transformed into low-level execution instructions via a variable impedance controller and a convex optimization torque allocation module, utilizing null space characteristics to avoid singularities. Furthermore, the method fine-tunes model parameters in real time by monitoring prediction errors and the degree of safety intervention online. This invention achieves the organic integration of logical decision-making and physical execution through a hierarchical architecture, significantly improving the robot's operational safety, robustness, and control accuracy in dynamic environments.

The invention discloses a humanoid robot motion control method based on reinforcement learning and Sim2Real migration, and particularly relates to the field of pedestrian robot motion control, and the method comprises the following steps: S01, constructing a robot model based on a physical engine, including terrain friction, inertia, noise and collision characteristics, and setting a joint angle and a speed upper limit; s02, learning a motion strategy in a simulation environment by adopting a PPO algorithm; s03, designing a reward function of a stable and efficient gait for guiding strategy learning; s04, parameter disturbance is introduced in training so as to reduce the real gap; and S05, deploying the simulation strategy to the real robot, and integrating a security mechanism. The humanoid robot motion control method aims at solving the problems that in the prior art, strong modeling is relied on, disturbance is sensitive, and deployment cost is high, the lightweight and self-adaptive humanoid robot motion control method is provided, rapid adaptation to uncertain environments (such as irregular terrains and external thrust) is achieved, and the falling risk in actual deployment is reduced.

The application belongs to the technical field of data processing, and relates to a robot whole-machine joint calibration method, a robot and a storage medium. By constructing whole-machine calibration state expression information, the robot camera, the chassis and the environment information are uniformly represented as the basic input of the joint calibration process, realizing centralized management of multi-source information and avoiding information fragmentation in module calibration. In the calibration process, the target calibration data is evaluated to determine the calibration information gap, and when the constraint is insufficient, a whole-machine motion strategy is generated and new joint calibration data is collected. Then, the joint calibration data is uniformly optimized, the correlation of multi-source data is comprehensively considered, and the independent calibration error accumulation problem is reduced. At the same time, a verification mechanism is introduced to evaluate the calibration result and judge whether the termination condition is met. If not, the calibration process is re-entered to form a closed-loop control. Therefore, the integrity, controllability and result reliability of the calibration process are improved.

The invention belongs to the technical field of path planning, and provides a humanoid robot indoor path planning method and system based on earth surface trafficability estimation, electronic equipment and a storage medium. The method comprises the steps of earth surface type map generation, texture feature extraction, equivalent friction coefficient prediction, flatness index calculation, trafficability probability map prediction, candidate path generation, safety audit screening and comprehensive cost screening, and optimal motion strategy generation. According to the method, the ground surface physical characteristics are introduced into the decision-making process, so that the planning level improvement from geometric obstacle avoidance to physical quality and efficiency is realized; by actively identifying and avoiding specific risks, main accident hidden dangers such as slipping and stumbling are directly eradicated from a decision source, and the reliability is improved.

This invention discloses a collision prediction method and system for mobile charging piles based on model predictive control, relating to the field of electric vehicle charging technology. The method includes the following steps: acquiring kinematic and dynamic parameters of the mobile charging pile during its movement, and establishing a dynamic model of the charging pile; constructing a model predictive control algorithm, setting an objective function and corresponding constraints; using the model predictive control algorithm to predict the charging pile's trajectory over a future period based on the dynamic model; acquiring surrounding environmental perception data, and predicting the collision risk between the charging pile and surrounding obstacles based on the trajectory and environmental perception data, obtaining collision risk analysis results; and adjusting the charging pile's movement strategy based on the collision risk analysis results. This invention can effectively analyze and avoid collision risks by predicting the charging pile's behavior over a future period, ensuring the safety and reliability of the charging process.

The invention relates to a target following method and device, computer equipment and a computer readable storage medium. The method comprises the steps of obtaining environment sensing information of a target environment where the robot is located; target detection is carried out based on the environment perception information, and candidate position information of candidate following objects in the target environment is obtained; responding to a following object indication operation for the robot; determining a target following object corresponding to the robot from the candidate following objects according to the following object indication operation; the target position information of the target following object is sent to a motion controller corresponding to the robot, so that motion strategy planning is carried out through the motion controller according to the target position information, and a target following strategy is obtained; wherein the motion controller comprises a motion control strategy generation model which is trained in simulation environments corresponding to various terrains; and executing the target following strategy through the robot. By adopting the method, the stability and robustness of target following can be improved.

The invention discloses a robot motion strategy interpretability identification method based on a sparse auto-encoder, and the method comprises the steps: the training of a motion strategy of a mobile robot and the training of an SAE layer of the sparse auto-encoder: employing the motion of a two-wheel differential robot as a typical robot navigation task; a simulation learning model trained on the task is used as a typical robot strategy model, and then an SAE layer is trained to analyze the strategy model as a typical normal form of strategy model analysis; extracting and explaining sparse neuron features in the strategy model: screening out effective features of a neural network by using a filtering mode, and explaining the effective features; and verifying the interpretability by activating the patch intervention strategy model. According to the embodiment of the invention, the SAE layer is adopted to decouple the superimposed effect in the neural network, so that the characteristics of neurons are relatively single, and the relevance between a neuron mode and a motion strategy can be analyzed conveniently; by activating patch intervention, the model interpretation effect is verified, and the transparency of the neural network strategy is improved.

The invention provides an action tracking method and device and electronic equipment, and relates to the technical field of robots, and the method comprises the steps: determining a motion increment for executing a tracking action through a trained motion strategy based on the tracking action and motion parameters of a target robot, the motion strategy is obtained by training resampling based on distribution perception and failure priority; and controlling the target robot to perform action tracking based on the motion increment and the tracking action. According to the method, through distributed sensing and failure-first resampling, a motion strategy can be converged more quickly, the training efficiency is improved, and more stable long-time-history high-dynamic tracking can be realized by combining motion increment focusing dynamic compensation and reducing drifting and accumulative errors.

The application belongs to the technical field of robots, and particularly relates to a robot force control method and device, a computer readable storage medium and a robot. The method comprises: generating a Riemann motion strategy-based motion generation for an overall target task of a robot to obtain joint acceleration control quantity at a current control moment; determining joint torque control quantity at the current control moment according to the joint acceleration control quantity at the current control moment based on a preset control quantity mapping relationship; wherein the control quantity mapping relationship is a mapping relationship between the joint acceleration control quantity and the joint torque control quantity; and performing torque control on the robot according to the joint torque control quantity at the current control moment to execute the overall target task. In the application, the position control of the robot is converted into torque control through the preset control quantity mapping relationship, so that torque control of the robot can be realized under the algorithm framework of RMP.

The invention discloses a frequency domain measurement method and system for motion distribution of a humanoid robot, and belongs to the technical field of intelligent and robot control. The method comprises the steps that joint real-time motion data are collected and mapped to a normalized state space, and strategy density distribution is obtained; extracting a frequency domain feature vector by adopting a truncated Fourier basis function; constructing a template mean value and a covariance matrix based on the group samples; and the frequency domain deviation is calculated through the spectrum weighted mahalanobis distance. According to the method, time sequence dependence is eliminated through frequency domain conversion, the robustness is improved in combination with group statistical information and spectrum weighting, the structural difference of strategy distribution is accurately captured, and switching of multiple feature extraction and distance measurement modes is supported. The method solves the problems that an existing method depends on a time domain, is insufficient in structural sensitivity and is weak in anti-noise capability, is suitable for scenes such as motion strategy evaluation and mode diagnosis, and is high in engineering practicability.

The invention discloses a quadruped robot motion control method and device, equipment, a medium and a product, and relates to the field of robots and automation, and the method comprises the steps: constructing a semantic topographic map of a target region according to environment point cloud data and environment images of the target region at the current moment; inputting the dynamic motion mode library, the semantic topographic map of the target area, the body state data of the quadruped robot at the current moment and the residual electric quantity into a high-level strategy network to obtain an optimal motion mode of the quadruped robot at the current moment; inputting the optimal motion mode, the body state data and the sensor data of the quadruped robot at the current moment into a low-layer strategy network to obtain the reverse compensation torque and PD gain of each joint of the quadruped robot at the current moment; and the quadruped robot is controlled according to the reverse compensation torque and the PD gain. The problems that in the face of complex tasks, the training efficiency is low, convergence is difficult and the like, and collaborative optimization of terrain perception and a motion strategy is difficult to achieve can be solved.

Systems, methods, and other embodiments described herein relate to estimating a policy for object motion by training a multi-modal model using diffusion through inferred goals and noise. In one embodiment, a method includes training a multi-modal model to generate a policy using semi-labeled data derived from wild data, and the multi-modal model predicts operator intent and a parameter associated with the policy for an agent in motion. The method also includes expanding outputs from the multi-modal model using noise within a diffusion model, and the noise augmenting the semi-labeled data. The method also includes feeding the outputs including the noise and the wild data to the multi-modal model until satisfying a training parameter associated with the policy.

The invention relates to the technical field of automatic nondestructive testing, in particular to an automatic ultrasonic testing system for large castings, which comprises an acoustic coupling quantification module for generating a real-time acoustic coupling quality index through collected real-time interface wave amplitude, stability indexes and the like; the speed modulation decision module is used for generating a speed scaling coefficient according to the coupling quality index and a preset threshold value; the scanning speed generation module is used for generating an instantaneous scanning speed instruction in combination with the speed scaling coefficient and the basic scanning speed; the coupling recovery control module is used for triggering a micro-motion strategy to recover coupling when the speed scaling coefficient is zero; according to the method, an acoustic coupling quantification model is established, an ultrasonic signal is converted into a quality index to dynamically modulate the scanning speed, and real-time coupling of physical perception and motion control is achieved; the defect of data loss caused by the fact that surface obstacles cannot be perceived in traditional fixed-speed scanning is overcome, and the detection reliability on a complex surface is ensured.

This invention belongs to the field of robot control technology and provides a reinforcement learning gait optimization method and system for quadruped robots. The technical solution involves acquiring the robot's posture and speed data; determining the robot's direction of movement based on its speed; calculating the expected angles for turning in different directions using the posture data; and calculating the posture angle reward function by combining the expected turning angles with corresponding angles in the simulation environment. The relationship between the quadruped robot's travel speed and a set speed range is compared, and corresponding gait reward functions are obtained based on different matching values. The posture angle reward function and gait reward function are then introduced into reinforcement learning training to obtain an optimized robot motion control scheme. This guides the robot to adopt a more accurate and realistic motion strategy.

The embodiment of the invention provides a method and equipment for dynamically adjusting action amplitude based on human-computer interaction, a medium and a program product, and relates to the field of intelligent medical treatment. The method comprises the following steps: acquiring a preoperative three-dimensional anatomical model and an intraoperative view image; respectively extracting intraoperative actual coordinates and model feature point coordinates of A feature points in the intraoperative view image and the preoperative three-dimensional anatomical model, and generating a dynamic coordinate system after registration; in the dynamic coordinate system, receiving pose change data of the operating handle and an optimal path for the to-be-operated part; and inputting the pose change data into the intention recognition model, analyzing the operation intention of the operator to obtain operation intention information, and generating a control instruction for guiding the mechanical arm in combination with the operation intention information and the optimal path. A dynamic coordinate system matched with a real-time visual field and a three-dimensional anatomical model is generated, and then based on the dynamic coordinate system, an operation intention of a doctor is actively captured through pose change data of an operation handle, so that a motion strategy is dynamically adjusted.