112 results about "Motion space" patented technology

Disclosed in the present invention is an obstacle avoidance method for an industrial robot in a complex environment, comprising the following steps: S1, performing model simplification on an industrial robot in a working space, and simplifying an obstacle into an obstacle point cloud; S2, placing a depth camera outside a motion space of the industrial robot in an "eye-to-hand" arrangement mode; and S3, before the industrial robot moves, using a G-APF-RRT* algorithm to plan a feasible path in the working space. In the present invention, the calculation mode of the distance between the industrial robot and the obstacle is simple, the required time is short, virtual joint interpolation is used and a spherical bounding box is used at a joint to completely envelope the industrial robot so as to simplify a model, and distance calculation can be completed only by calculating the distance between the center of sphere of the limited spherical bounding box and each point in the obstacle point cloud.

The invention provides an autonomous navigation path planning method, device and equipment for a humanoid robot in a complex environment. A navigation task is determined by obtaining the current position and path requirement of the robot; constructing a constraint preposition map based on body size constraint, joint motion constraint and dynamic balance constraint, and calculating a feasible motion space of the robot in advance; acquiring environment sensing data for variation trend analysis, and predicting a future movement track of the dynamic obstacle to generate a dynamic environment prediction sequence; establishing a bidirectional planning mechanism, performing forward and reverse path search at the same time, and generating a plurality of candidate path hypotheses through meeting point detection and path fusion; analyzing a human behavior pattern to identify a potential passage conflict area, establishing a social negotiation strategy, and taking an intermediate meeting point as a social key node to adaptively adjust a candidate path; the optimal safety path is determined through multi-dimensional safety evaluation of the falling risk, the collision risk and the energy consumption risk, and intelligent autonomous navigation of the humanoid robot in a complex environment is achieved.

Disclosed are a path planning method and apparatus, and a computer-readable storage medium. The path planning method may include: acquiring a motion space, a starting position, and an end position of a moving object, and information of an obstacle; constructing a first exploration tree starting from the starting position and constructing a second exploration tree starting from the end position in the motion space, the first exploration tree and the second exploration tree grow toward each other according to the information of the obstacle; and in response to a distance between a first tree node grown on the first exploration tree and a second tree node grown on the second exploration tree being not greater than a preset step length, connecting the first exploration tree and the second exploration tree to obtain a planned path of the moving object.

The invention relates to the technical field of robot joint control, and discloses a robot dog mechanical joint control method. The method comprises the following steps: acquiring a whole-body joint real-time sensing data set which covers the torque reading of a multi-axial force sensor, the angle data of a joint encoder and the body attitude data of an inertial measurement unit; motion state compensation is carried out on the sensing data based on a dynamic window mechanism, and a dynamic compensation matrix containing kinematics compensation parameters is generated; and inputting the multi-modal motion control data set into a gradient descent model under space-time constraint to complete multi-modal motion feature fusion so as to obtain a fusion motion control data set. Joint behavior abnormity is detected through a Lyapunov stability analysis algorithm, and abnormal nodes are identified; and iteratively optimizing control parameters through a fuzzy PID optimization algorithm to generate an optimized control parameter set, finally constructing a three-dimensional virtual motion space model, and establishing a dynamic mapping relationship between a virtual track and an actual mechanism.

The invention discloses a space floating mechanical arm motion planning method and system based on zero reaction space and reinforcement learning, and relates to the field of mechanical arm motion planning. The invention aims to solve the problem of base attitude disturbance caused by movement of an existing space floating mechanical arm. According to the technical scheme, the motion space of the space mechanical arm is designed to be the zero-reaction space, it is ensured that the motion of the mechanical arm does not generate unexpected disturbance on the base, and therefore the stability of the system and the task execution precision are improved. In addition, a reinforcement learning algorithm is combined, and the motion space is set as a zero-reaction motion space. The efficient search and optimization capability of reinforcement learning enables the mechanical arm to find an optimal motion strategy in a complex task space, and meanwhile, disturbance to the base is effectively avoided. The strategy can be continuously adjusted through multiple rounds of training and reinforcement learning so as to adapt to different task requirements, and it is guaranteed that when the mechanical arm executes space grabbing, maintenance and other tasks, high-precision operation can be kept, and it can be guaranteed that the base is stable. Experimental results show that by means of the method, deviation of the attitude of the base can be remarkably reduced, the stability and efficiency of task execution are improved, and a feasible solution is provided for on-orbit service tasks of the space mechanical arm in the future.

The invention discloses a fixed cross beam machine tool with an internal constraint structure, which comprises a machine tool main shaft, a rotary table and a machine tool body, at least two guide rails are arranged in the X-axis direction, the Y-axis direction and the Z-axis direction respectively, at least two guide rails in the same axial direction comprise at least one pair of guide rails which are not on the same coordinate plane, and the guide rails form an internal constraint space; the overlapped area of the at least two inner constraint spaces is a motion space, and the motion space is a motion area of a tool nose point of a machine tool spindle in the machining process; and a workpiece on the rotary table coincides with the motion space through the linear displacement of the rotary table. At least two guide rails which are not on the same coordinate plane are arranged in the three axial directions, the layout of the guide rails is optimized, movement of machine tool parts is restrained in the guide rails, a tool nose point is located in a closed space all the time, movement of the tool nose point in the axial directions is effectively restrained, the influence of cutting force is reduced, and the micro-displacement amount is reduced. The machine tool spindle is effectively prevented from being influenced by overturning moment, vibration and deformation are restrained, and machining precision is guaranteed.

The invention provides a control method and system of a rehabilitation robot, a readable storage medium and a computer. The method comprises the steps that a motion control sketch is constructed according to motion data, collected in real time, of the rehabilitation robot and upper limbs of a patient; calculating displacement data of an end effector according to the motion control sketch and a kinematics model of the rehabilitation robot; according to the kinematics model of the equalization mechanism of the rehabilitation robot, the displacement data of the end effector and the kinematics model, the maximum motion space of the end effector is established; the effective working space of the rehabilitation robot is calculated through the end effector and the maximum movement space of the upper limb hemiplegic patient, and the rehabilitation robot is controlled through the effective working space. According to the method, the displacement data of the end effector is calculated by utilizing the kinematic model and the motion control sketch, and the mechanical model of the rehabilitation robot is established by utilizing the kinetic model and the displacement data, so that the rehabilitation robot is controlled.

According to the intelligent obstacle avoidance reinforcement learning algorithm for the robot in the narrow area, more than ten kinds of common narrow terrains are added in a training map, path points are arranged on the two sides of a target terrain, and a reward function with the robot accurately penetrating through the path points as a core is designed; the problems of high complex terrain collision rate and path planning failure caused by model approximation and single training environment in the prior art are solved. Depth camera data is compressed into a 56 * 80-dimensional feature matrix, ultrasonic sensor data is extracted into a 12-dimensional distance vector, multi-modal data fusion training is performed through a three-layer perceptron network, and a 6-dimensional continuous control quantity including three translational speeds and three angular speeds is directly output. The problems of inaccurate size constraint perception and rough action space caused by dependence on a simplified model in a traditional algorithm are solved, refined control over six-degree-of-freedom motion of the robot in a narrow area is achieved, and the obstacle avoidance safety and the path passing rate in a complex obstacle environment are improved.

The invention discloses a remote humanoid mapping control method based on a virtual reality motion capture mechanical arm. A motion data acquisition module transmits a matrix of a head coordinate system relative to a world coordinate system and a homogeneous transformation matrix to a coordinate system conversion module, establishes a base coordinate system and a tail end coordinate system, and establishes a kinematic chain conversion model; extreme position data of forearm extension of a user is collected, a proportionality coefficient is calculated, and a motion space boundary of the mechanical arm is output; pose normalization processing is carried out to form a discretized mechanical arm tail end pose sequence, and then the spatial relation between the mechanical arm sphere model and the obstacle is analyzed; generating a collision-free track by adopting a parallelization gradient optimization algorithm; the trajectory optimization module realizes trajectory smoothness and time optimization by constructing a multi-objective optimization function; and a mechanical arm motion simulation system is constructed, the tail end track precision is verified, and the controller drives the mechanical arm to achieve high-fidelity reproduction of user actions according to the track. According to the invention, high-precision and smooth-path motion migration of the mechanical arm is realized.

The invention relates to a mechanical arm trajectory optimization method and system based on adversarial learning, and specifically, the method comprises the steps: discretizing a motion space of a mechanical arm to obtain voxels, obtaining a multi-channel image based on whether the voxels contain obstacles or not, and obtaining a to-be-optimized voxel sequence of the mechanical arm through an RRT algorithm; voxel sequences under different conditions are calculated by adopting different neighborhood radiuses and step lengths; calculating a label of a voxel sequence according to the neighborhood radius and the step length, extracting features of the multi-channel image through a feature extraction unit of a discriminator, performing feature fusion on the features of the multi-channel image and the voxel sequence to obtain output of the discriminator, and pre-training the discriminator based on the label and the output of the discriminator; and training the adversarial network by adopting a pre-trained discriminator, and inputting the multi-channel image and the voxel sequence to be optimized into the trained generator to obtain a mechanical arm trajectory optimization result.

The invention discloses a movable cross beam machine tool with an internal constraint structure. The movable cross beam machine tool comprises a machine tool spindle, a rotary table and a machine tool body, the X-axis direction, the Y-axis direction and the Z-axis direction are each provided with at least two guide rails, the at least two guide rails in the same axial direction comprise at least one pair of guide rails not located in the same coordinate plane, and the guide rails form an inner constraint space. The overlapped area of the at least two inner constraint spaces is a motion space, and the motion space is a motion area of a tool nose point of a machine tool spindle in the machining process; the rotary table is fixedly arranged on the machine tool body, and a workpiece on the rotary table coincides with the motion space through linear displacement of the machine tool spindle. At least two guide rails which are not on the same coordinate plane are arranged in three axial directions, the layout of the guide rails is optimized, movement of machine tool parts is restrained in the guide rails, a tool nose point is always located in a closed space, movement of the tool nose point in each axial direction is effectively restrained, the influence of cutting force is reduced, and the micro-displacement amount is reduced. The machine tool spindle is effectively prevented from being influenced by overturning moment, vibration and deformation are restrained, and machining precision is guaranteed.

The invention discloses a path planning method, device and equipment for a mechanical arm actuator, a medium and a product. The method comprises the steps that a motion starting point and a motion end point of a mechanical arm actuator are obtained, and a grid map of a mechanical arm motion space is generated; taking the motion starting point as a current node, determining adjacent nodes of the current node in the grid map, and determining joint angle data matched with each adjacent node; according to the joint angle data of the mechanical arm at the current node and the joint angle data matched with the adjacent nodes, the next node is determined in the adjacent nodes; and updating the motion path, updating the next node as the current node, returning to the execution of determining the adjacent node of the current node in the grid map until the next node is a motion end point, and outputting a path planning result of the mechanical arm actuator. According to the technical scheme, the problem that the movement efficiency of the mechanical arm actuator is low is solved, the rotation energy consumption of the mechanical arm joint can be effectively reduced, and the movement efficiency of the mechanical arm actuator is improved.

The invention provides a posture recognition method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-recognized video clip, wherein each image frame of the video clip comprises a hand of a target object; performing feature recognition processing on each image frame to obtain a hand feature map of each image frame; the hand feature map comprises motion space features and motion time sequence features; the motion space feature comprises a hand shape information feature of a hand in the image frame; the motion time sequence features comprise hand motion features of the hand in multiple image frames; and performing classification prediction processing according to the hand feature map of each image frame to obtain sign language text information corresponding to the information transmitted by the hand action in the video clip. In this way, according to the embodiment, the hand shape information and the hand motion information of the target object are concerned, and the recognition ability of the hand posture is improved.

The invention discloses a machine tool with an internal constraint structure, which comprises a machine tool main shaft, at least two guide rails are arranged in the X-axis direction, the Y-axis direction and the Z-axis direction, at least two guide rails in the same axial direction comprise at least one pair of guide rails which are not in the same coordinate plane, and the guide rails form an internal constraint space; the overlapped area of the at least two inner constraint spaces is a motion space, and the motion space is a motion area of a tool nose point of a machine tool spindle in the machining process. At least two guide rails which are not on the same coordinate plane are arranged in the three axial directions, the layout of the guide rails is optimized, movement of machine tool parts is restrained in the guide rails, a tool nose point is located in a closed space all the time, movement of the tool nose point in the axial directions is effectively restrained, the influence of cutting force is reduced, and the micro-displacement amount is reduced. The machine tool spindle is effectively prevented from being influenced by overturning moment, vibration and deformation are restrained, and machining precision is guaranteed.

The invention discloses a moving part space pose error detection method and system and a medium. The method comprises the steps of obtaining pose information of a machine tool moving part based on an IMU module and an electronic level meter, wherein the IMU module obtains an accelerometer signal and an angular velocity signal, and the electronic level meter obtains an angle error signal; performing data fusion on the pose information to obtain a line value error and an angle error; establishing an error prediction model by adopting a BP neural network based on the line value error, the angle error and the movement speed of the linear axis of the machine tool; obtaining the optimal initial weight and threshold value of the BP neural network by adopting a beetle antennae search algorithm, and substituting the optimal initial weight and threshold value into the error prediction model for model training to obtain a trained error prediction model; and based on the trained error prediction model, carrying out motion part space pose error detection to obtain a pose error detection result. According to the invention, equipment motion space pose error measurement can be realized, and the measurement precision is improved under the condition that the accuracy is ensured.

The invention relates to the technical field of visual real-time detection and evaluation of fitness actions, and particularly discloses a barbell fitness action real-time detection and evaluation method, which comprises the following steps of: determining a barbell fitness action type, acquiring an image, inputting a network model to predict and obtain a barbell rod area coordinate, mapping to obtain depth information, and extracting point cloud data of a barbell rod area; and fitting a barbell rod center straight line to obtain a real-time motion space trajectory of the barbell, analyzing and calculating to obtain barbell rod motion change information in a motion period, and analyzing and evaluating with a pre-created motion layering condition library to obtain real-time detection and evaluation information. The method combines a deep learning algorithm and a depth camera, can effectively identify and process, has high-precision and high-accuracy detection and evaluation effects, and is suitable for detection and evaluation of various actions of barbell fitness exercises.

The invention belongs to the field of autonomous operation of underwater robots, and particularly relates to a visual mechanical arm grabbing method after an autonomous underwater robot sits on the bottom, which comprises the following steps: after the AUV sits on the bottom, a binocular camera is utilized to shoot seabed images, and target identification and positioning of seabed grabbing are carried out; judging whether a grabbed target is in a seabed motion space of the flexible hand or not by utilizing a transformation matrix of a camera coordinate system and a mechanical arm coordinate system, if not, performing AUV body pose adjustment, and re-executing target recognition and positioning; and if the target is in the seabed motion space of the flexible hand, the AUV performs mechanical arm motion planning and execution based on a table look-up interpolation method according to the spatial position information of the target, so that the flexible hand moves to the target position, and the flexible hand is controlled to be closed to complete grabbing. According to the grabbing motion planning method for the visual mechanical arm, autonomous grabbing actions of the mechanical arm and the flexible hand can be rapidly completed under the low calculation complexity, the grabbing position error is small, and the grabbing success rate is high.

A gear-driven massage device comprising a housing (1) and a soft sleeve (2) enclosing the housing (1), the soft sleeve (2) forming outwardly projecting massage balls (3), a mounting plate (4) being provided inside the housing (1), at least one main wheel (5) being arranged on the mounting plate (4), a movement space being formed between the mounting plate (4) and the inner wall of the housing (1), massage rods (6) being provided in the movement space, the housing (1) being provided with through-holes (7) the number of which corresponds to the number of massage rods (6), the heads of the massage rods (6) extending from the through-holes (7) and engaging the massage balls (3), each massage rod (6) being provided with an elongated hole (8), the main wheel (5) having an eccentric rod (9), the eccentric rod (9) being inserted into the elongated hole (8).wherein a main circuit board (10) and a drive motor (11) electrically connected to the main circuit board (10) are provided in the housing (1), wherein the rotating shaft of the drive motor (11) is rigidly connected to an output wheel (12), wherein the output wheel (12) is connected to the main wheel (5) via a first driven wheel (13) and the main wheel (5) rotates with it, causing the massage rods to move back and forth in the movement space in order to massage the human body.

The present invention discloses a method, system, and medium for detecting the spatial posture error of a moving component. The method comprises the following steps: obtaining posture information of a machine tool moving component based on an IMU module and an electronic level: accelerometer signals and angular velocity signals obtained by the IMU module, and angular error signals obtained by the electronic level; fusing the posture information to obtain linear error and angular error; establishing an error prediction model using a BP neural network based on the linear error, angular error, and the motion speed of the machine tool linear axis; obtaining the optimal initial weights and thresholds of the BP neural network using a longhorn beetle whisker search algorithm, substituting these values ​​into the error prediction model for model training to obtain a trained error prediction model; and performing spatial posture error detection on the moving component based on the trained error prediction model to obtain posture error detection results. The present invention can measure the spatial posture error of equipment motion and improve measurement precision while ensuring accuracy.

The invention relates to the technical field of time delay measurement, and provides a robot control end-to-end time delay measurement method and device and electronic equipment. The method comprises the following steps: acquiring a trigger timestamp of a robot motion instruction; based on a candidate displacement composite search strategy and a cost function early stop mechanism, performing global motion estimation on a monitoring video stream corresponding to the robot to obtain a global timestamp of global motion of a monitoring image in the monitoring video stream; the candidate displacement composite search strategy is used for adjusting a search sequence of candidate displacement between adjacent monitoring images based on motion space-time continuity; under the condition that the candidate displacement triggers a cost function early stop mechanism, the cost function early stop mechanism is used for terminating calculation of a cost function of the candidate displacement in advance; and determining an end-to-end time delay corresponding to the robot based on the global timestamp and the trigger timestamp. According to the embodiment of the invention, the end-to-end time delay of a complete link can be measured, and the accuracy and real-time performance of time delay measurement are improved.

The present invention provides a control system for a rehabilitation robot, the method comprising: constructing a motion control diagram according to the real-time collected motion data of the rehabilitation robot and the patient's upper limbs; calculating the displacement data of the end effector according to the motion control diagram and the kinematic model of the rehabilitation robot; establishing the maximum motion space of the end effector according to the kinematic model of the equalization mechanism of the rehabilitation robot, the displacement data of the end effector and the kinematic model; calculating the effective working space of the rehabilitation robot using the end effector and the maximum motion space of the upper limb hemiplegic patient, and controlling the rehabilitation robot using the effective working space. The present invention calculates the displacement data of the end effector using the kinematic model and the motion control diagram, and establishes the mechanical model of the rehabilitation robot using the dynamic model and the displacement data, thereby realizing the control of the rehabilitation robot.

The embodiment of the invention discloses a path planning method, a mobile robot and related equipment, and is applied to the technical field of path navigation. According to the embodiment of the invention, the method comprises the steps: obtaining a plurality of planning paths of the mobile robot, and discretizing a motion space where the plurality of planning paths are located into a plurality of cells; determining first position information of the cells in the motion space and first timestamp information when the planned path arrives at the cells; predicting second position information of cells passed by the dynamic obstacle in the motion space and second timestamp information when the dynamic obstacle arrives at the cells; the dynamic barrier is a position-changing barrier; based on the first position information, the second position information, the first timestamp information and the second timestamp information, determining a collision path colliding with the dynamic obstacle; determining a target planning path from the plurality of planning paths based on the collision path; and the path planning speed can be effectively improved.

This invention relates to a humanoid robot, specifically a parallel rotating mechanical joint based on a ring-shaped guide rail, mimicking the rotation of a human neck. The aim is to provide a parallel rotating mechanical joint based on a ring-shaped guide rail to achieve three degrees of freedom in the movement of a biomimetic human neck joint while ensuring high rigidity and motion accuracy. Furthermore, the joint features a simplified structure, good support performance, and sufficient movement space for the neck joint. The technical solution is a parallel rotating mechanical joint based on a ring-shaped guide rail, characterized by: a head motion platform, a neck ring-shaped guide rail base, and three PSS (Personal Stability Support) link branches connected in parallel between the head motion platform and the neck ring-shaped guide rail base; the center of the head motion platform and the center of the neck ring-shaped guide rail base are connected by a composite rotating shaft.

The invention discloses a radiation treatment bed anti-collision method and system, and the method comprises the steps: drawing a 3D envelope boundary for constraining the motion space of a treatment bed; establishing an incidence relation model among the position of the treatment bed in the 3D envelope boundary, the motor operation current variable quantity and the displacement variable quantity; in the radiotherapy process, the motion space position of the radiotherapy bed and the motor operation current variable quantity and the displacement variable quantity corresponding to the motion space position are monitored in real time, and whether the treatment bed has the collision risk or not is judged based on the incidence relation model. According to the scheme, automatic collision prevention is achieved, when collision occurs, the treatment bed stops moving immediately, and a collision early warning mechanism is provided.

The invention belongs to the technical field of medical robots, and particularly relates to a puncture surgery robot system. The CT bed is provided with the multi-axis movement mechanism, the multi-axis movement mechanism comprises an X-axis linear guide rail mechanism, a Y-axis linear guide rail mechanism, a Z-axis linear guide rail mechanism and a tail end executing mechanism, a cantilever structure in the tail end executing mechanism is connected with the Z-axis linear guide rail mechanism, and a first rotating shaft arranged in the tail end executing mechanism is connected with a second rotating shaft through an output connecting rod. The axis where the first rotating shaft is located and the axis where the second rotating shaft is located are arranged in a crossed mode. The method has the advantages that the positioning error is smaller than or equal to 0.3 mm, and the angle adjusting precision reaches 0.1 degree; non-coplanar puncture paths of anatomical structures such as lungs and livers are adapted; 180-degree horizontal rotation and + / -90-degree pitching adjustment are achieved, the movement space limitation of a parallel structure is broken through, and the device is compatible with obese patients and special body positions such as side lying and prone lying; target point coordinates are fitted in real time through CT images, the motion trail of the robot is dynamically corrected, the manual calibration frequency is reduced, and the operation efficiency is greatly improved.

The application discloses a motion planning method and equipment for a steam generator tube plate quadruped robot, and belongs to the technical field of motion planning of a nuclear industry steam generator quadruped robot. In order to solve the problems that the existing robot has low planning efficiency when inspecting a steam generator tube plate, and the execution success rate of a planning scheme needs to be improved, the application firstly performs traversal search to determine the motion space of a base and a foot end, and determines a feasible foot landing set; then divides a given polyline path into multiple straight line paths, plans a base track, determines the base position, and for each straight line path, the robot selects a foot landing point in the feasible foot landing set according to a turning motion evaluation index, continuously performs a turning motion process until the robot adjusts the posture to face a given orientation and completes the turning motion; the robot selects a foot landing point in the feasible foot landing set according to a straight line motion evaluation index, continuously repeats a straight line motion process until the base of the robot reaches the terminal point of the straight line path.

The application belongs to the field of autonomous operation of underwater robots, and particularly relates to a visual mechanical arm grabbing method after autonomous underwater robots sit on the bottom, which comprises the following steps: after the AUV sits on the bottom, a binocular camera is used to shoot the seabed image, and target recognition and positioning for seabed grabbing are performed; a transformation matrix of the camera coordinate system and the mechanical arm coordinate system is used to determine whether the grabbing target is in the seabed movement space of the flexible hand, if not, the AUV body pose is adjusted, and the target recognition and positioning are re-executed; if the target is in the seabed movement space of the flexible hand, the AUV performs mechanical arm movement planning and execution based on the look-up table interpolation method according to the spatial position information of the target, so that the flexible hand moves to the target position, and the flexible hand is controlled to close to complete grabbing. The visual mechanical arm grabbing movement planning method provided by the application can quickly complete the autonomous grabbing action of the mechanical arm and the flexible hand under low calculation complexity, and has small grabbing position error and high grabbing success rate.

The invention provides a robot mechanical arm motion space simulation method and system and a photovoltaic robot. The method comprises the steps that a mechanical arm motion model is constructed according to the size of each joint connecting rod of a mechanical arm and the allowable rotation range of a joint angle; taking an XZ plane or a YZ plane as a display plane of the simulation system, adding a photovoltaic array model on the display plane, taking an area where the photovoltaic array model is located as a target area, and selecting a plurality of position points in the target area as target position points; the target position points are sequentially input into a mechanical arm motion model for motion simulation, and whether the tail end of the mechanical arm can reach all the target position points or not is judged; a point cloud mark is generated at a target position point where the tail end of the mechanical arm can reach, and a first point cloud set is formed; and rotating the first point cloud set around the Z axis of the mechanical arm base by one circle to form a motion space of the mechanical arm. According to the scheme, the motion space of the mechanical arm of the photovoltaic cleaning robot can be simulated, so that design and engineering verification of the mechanical arm are facilitated.

The invention discloses a long-time reference and motion space-time correlation end-to-end monitoring video coding and decoding method. The method comprises the following steps: step 1, in a motion estimation stage, simultaneously utilizing a long-time reference frame (xLTR) and a short-time reference frame # imgabs0 # in a monitoring video and an original image xt to carry out optical flow estimation, and simultaneously generating two pieces of motion information, namely mt1 and mt2; step 2, sending mt1 and mt2 into a motion information coding and decoding module, and outputting a reconstruction value of motion information by the motion information coding and decoding module, namely # imgabs1 #; step 3, carrying out motion compensation on # imgabs3 # by using # imgabs2 # to obtain a prediction frame # imgabs4 #, carrying out motion compensation on xLTR by using # imgabs5 # to obtain a prediction frame # imgabs6 #; step 4, sending # imgabs7 # into a prediction frame fusion module, and carrying out motion compensation on xLTR by using # imgabs4 #; and step five, carrying out subtraction on the prediction frame # imgabs9 # and the original image xt to obtain an image residual error rt, carrying out encoding and decoding on the image residual error to obtain a reconstruction residual error # imgabs10 #, and adding the reconstruction residual error # imgabs10 # and the prediction frame # imgabs11 # to obtain a reconstruction frame. According to the invention, stable and high-quality reference information can be provided.

The invention provides an upper limb rehabilitation robot torque compensation method and system, a storage medium and a computer, and the compensation method comprises the steps: dividing an effective motion space of a tail end execution device of an upper limb rehabilitation robot, and building a coordinate system in the effective motion space; torque function matrixes of the healthy crowd and the crowd to be recovered in the effective motion space are sequentially obtained, and compensation force of a tail end execution device is obtained according to the torque function matrixes; determining a motion track of the to-be-recovered crowd according to the compensation force, and establishing a target torque compensation model according to the motion track; and acquiring an expected movement track corresponding to the current patient and a corresponding movement track, and substituting the expected movement track and the movement track corresponding to the current patient into the target torque compensation model to obtain a compensation torque of the upper limb rehabilitation robot to the current patient. According to the torque compensation method, the compensation torque can be automatically adjusted according to the condition of the patient, and the application range is wide.