97 results about "Gait cycle" patented technology

The invention belongs to the technical field of smart old-age care product behavior debugging, and particularly discloses a smart old-age care product behavior dynamic adjustment method based on interactive data perception. According to the method, a sole mechanical fragment, a lower limb movement fragment and a heart rate fragment are extracted based on gait cycle alignment, gait stability, gait coordination and physiological conformity indexes are calculated, and coupling sensing of user movement behaviors and physiological states in the dynamic walking assisting process is achieved; the gait stability and the physiological conformity are fused to construct a gait physiological synchronism criterion, a hierarchical adaptive control strategy is implemented accordingly, and the limitation that a traditional supporting robot only depends on kinematics feedback control is broken through, so that on the premise that the user safety is guaranteed, response type physical and mental collaborative intelligent assistance is achieved, and the user experience is improved. And the risk prevention and control capability of rehabilitation training is effectively improved.

The invention relates to the technical field of artificial intelligence and medical detection, and particularly provides a human body gait variability detection system based on an improved TCN model. The system comprises a multi-modal sensor array, a signal preprocessing module, a self-adaptive time sequence feature extraction module, a bidirectional time sequence context fusion module, a progressive depth feature enhancement module and a variability quantization output module, a receptive field is dynamically adjusted through a learnable expansion coefficient, the bidirectional time sequence context is fused to improve the period segmentation precision, and the precision of the period segmentation is improved. And gradual feature enhancement is adopted to relieve deep network feature degradation, so that accurate quantification of five indexes such as a gait cycle variation coefficient and a stride time standard deviation is realized, and the sensitivity and reliability of clinical gait variation detection are improved.

The invention relates to the technical field of knee joint exoskeleton devices, in particular to a clutch control type knee joint exoskeleton damping device and a control method. Comprising a pair of rotating assemblies which are rotationally connected; the pair of leg connecting assemblies are connected with the pair of rotating assemblies correspondingly, and the pair of leg connecting assemblies are used for being connected with the thighs and the shanks on the same side of the user correspondingly; the rotary damper is controllably coupled with the knee joint assembly; the clutch device is arranged between the rotary damper and the knee joint assembly, and the clutch device is used for switching the coupling state of the knee joint assembly and the rotary damper; and the control unit is used for judging a gait cycle phase and a motion mode according to the signal acquired by the detection unit, and controlling the clutch device to switch the coupling state of the knee joint assembly and the rotary damper according to a preset control rule. And the exoskeleton device can intelligently control the clutch device to dynamically adjust the damping state of the knee joint.

Orthotic devices for providing arch support for the foot are disclosed. The orthotic device includes a base member, an arch support portion, and a plurality of connectors coupled to the base member at a first end and each connector of the plurality of connectors coupled at a second end to each arch member of the plurality of arch members. The orthotic devices provide continuous contact with the plantar surface of the foot during all phases of the gait cycle. In addition, the orthotic devices are assembled by coupling the connectors ends to the base member on one end and each arch member on the other end.

The invention provides an electrical stimulation and lower limb exoskeleton device fusion control method and system, and the method comprises the steps: driving an exoskeleton to move through bottom admittance control based on the actual human-computer interaction torque and expected torque of a knee joint and reference trajectory data of the knee joint in a gait cycle, and triggering ankle joint electrical stimulation through a fixed stimulation parameter group; after the gait cycle is finished, torque errors are calculated, and periodic iteration updating is conducted on the knee joint reference trajectory data through an iterative learning control algorithm till convergence is conducted to obtain target knee joint reference trajectory data; and then determining a target moment of a gait phase based on the target knee joint reference trajectory data, and obtaining a corresponding target stimulation parameter group from the set stimulation parameter time mapping library to replace the fixed stimulation parameter group for subsequent stimulation. According to the method, through single-cycle and cross-cycle trajectory iteration, the adaptation defect of a traditional fixed trajectory is avoided, the stimulation parameters are synchronously optimized, and the dorsiflexion assisting effect is indirectly improved.

The application discloses a kind of humanoid robot linear joint permanent magnet motor design optimization method, this method includes: based on the mechanical characteristics of human gait cycle to establish knee joint connecting rod mechanism dynamics model, extract characteristic working condition point and establish screw-motor electromechanical matching criterion, using Latin hypercube sampling to obtain design sample point, establish permanent magnet motor multi-objective optimization model with limit torque, torque ripple, efficiency as target, then introduce evolutionary algorithm for global optimization, obtain Pareto non-inferior solution set;Finally, based on CRITIC-TOPSIS evaluation method, fusion objective data characteristics and subjective working condition demand, determine the optimal design scheme from Pareto non-inferior solution set.The design optimization method of the application can define the design requirements of permanent magnet motor, and can also scientifically distribute the target weight, ultimately can obtain the permanent magnet motor scheme highly matched with specific joint working condition, effectively improves the power performance and operating stability of humanoid robot linear joint.

The application discloses a gait recognition method and system based on local and global difference modeling networks, relates to the field of gait recognition, and comprises the following steps: acquiring a gait contour sequence and environment parameters of a target object; processing the gait contour sequence according to the environment parameters to generate local limb motion trajectory segments and a global gait cycle sequence; performing feature extraction on the local limb motion trajectory segments and the global gait cycle sequence to obtain a local difference feature vector and a global difference feature vector; generating a fusion difference feature according to the local difference feature vector and the global difference feature vector; performing dynamic weight distribution on the fusion difference feature according to the environment parameters to obtain an identity discrimination feature; selecting a matching strategy according to the environment parameters, performing similarity matching on the identity discrimination feature and a pre-stored gait feature library according to the matching strategy, and outputting an identity determination result of the target object; and the application can overcome complex environmental interference and improve the stability of feature extraction.

The invention relates to medicine, and more particularly to a novel method for the control of stepping movements in patients with traumatic injuries or diseases of the spinal cord and / or the brain using transcutaneous electrical stimulation, which includes continuously stimulating the spinal cord at the level of the C5-C6, T11-T12 and L1-L2 vertebrae and simultaneously creating a synergistic effect to control foot movement by means of spatial-temporal stimulation of the flexor and extensor muscles of the lower leg in the corresponding phases of the gait cycle. This combined spinal and muscular stimulation enables a coordinated, complete gait, in which the patient is able to control the stepping movements, including controlling foot movements.

The invention provides a footwear design method based on gait biomechanics and a footwear, which integrate an integrated process of foot biomechanics modeling, dynamic gait data acquisition, multi-region lattice structure configuration, multi-target collaborative optimization and additive manufacturing, and realize direct mapping from individual biomechanics characteristics to personalized footwear products. The fundamental problem that a traditional shoe design cannot meet the differential biomechanical requirements of multiple areas of the foot in the dynamic gait cycle at the same time is solved, and systematic and accurate adaptation is achieved.

The application discloses a portrait inspection and identification method based on gait cycle decomposition and multi-phase force analysis, and comprises the following steps: extracting the skeleton key points of a target object in a target object image set in a comparison video and the confidence score of each skeleton key point; extracting the features of the target object in the target object image set according to the skeleton key points of the target object, and obtaining the target object features, wherein the target object features comprise basic features, gait cycle features, gait stage features and gait parameter features; integrating the basic features, the gait cycle features and the gait stage features to obtain comprehensive features; respectively calculating the similarity of the target object features and the comprehensive features in the comparison video to obtain similarity calculation results and overall similarity calculation results; and obtaining the identity identification result of the target object according to the similarity calculation results and the overall similarity calculation results.

The application provides a gait intelligent monitoring method, system, device, medium and program product. The method comprises the following steps: based on multi-pose positioning, synchronously collecting pressure data and center of gravity dynamic data of different regions of the sole of a target object; performing denoising processing on the synchronously collected pressure data and center of gravity dynamic data; performing multi-dimensional data fusion on the denoised pressure data and center of gravity dynamic data based on gait cycle, spatial distribution and dynamic characteristics, and generating comprehensive gait data containing sole pressure distribution parameters and center of gravity dynamic balance parameters through fusion; transmitting the obtained comprehensive gait data to an evaluation terminal; selecting an evaluation model adapted to the multi-pose positioning based on the evaluation terminal, evaluating and identifying the comprehensive gait data through the evaluation model, and obtaining a gait recognition result. The embodiment of the application is based on multi-pose standardized positioning, and is adapted to evaluation of different evaluation scenes. The pressure data and gravity dynamic data are fused to perform gait monitoring, and the monitoring accuracy is improved.

The invention relates to a health association analysis method based on foot pressure and gait dynamic monitoring. The method comprises the following steps: acquiring original plantar pressure data; performing vibration suppression processing on the original plantar pressure data by adopting dual-reference adaptive filtering according to the vibration of the treadmill and the torso acceleration to obtain expected plantar pressure data; carrying out gait cycle division on the expected plantar pressure data; gait features are extracted from the data obtained after gait cycle division; a causal reasoning model is constructed and trained, and the causal reasoning model adopts a three-layer directed graph model and comprises an observation layer formed by gait feature nodes, a latent variable layer formed by health correlation feature nodes and an output layer formed by health risk item nodes; causal edges are set among the hierarchical nodes according to causal constraints; during reasoning, the trained causal reasoning model is utilized to establish output from gait features to health association features and from the health association features to risk item probabilities; therefore, health risk analysis is carried out according to the gait features.

The application discloses a flexible variable stiffness knee joint rehabilitation exoskeleton and a motion control method thereof. The flexible variable stiffness knee joint rehabilitation exoskeleton comprises a back fixing assembly, a thigh fixing assembly and a shank fixing assembly. The thigh fixing assembly and the shank fixing assembly are hingedly connected through a knee joint shaft group and are provided with a pose detection assembly at the hinge connection. An output wheel and an input wheel are connected through a Bowden cable group. The back fixing assembly is respectively provided with a controller, a driving mechanism, a nonlinear variable stiffness mechanism and an energy recovery mechanism. The device uses magnetic repulsion between a permanent magnet and a power coil to construct a nonlinear stiffness adjusting mechanism. The actuator is fixed on the human back through a bandage. The Bowden cable is used to realize remote transmission of the torque to the knee joint, thereby effectively reducing the load bearing burden of the lower limbs. In the swing phase of the gait cycle, the system uses the principle of permanent magnet cutting magnetic induction lines to realize energy feedback, thereby improving the overall energy efficiency of the assisting process.

Disclosed is a method by which a computing device, according to one embodiment of the present disclosure, identifies an object by using a gait cycle. The method may comprise the steps of: generating first gait information on the basis of first type information by using a first neural network model; generating second gait information on the basis of second type information by using a second neural network model; and identifying an object on the basis of the first gait information and the second gait information by using a classifier.

This invention belongs to the technical field of rehabilitation robots, specifically relating to a continuous phase control method for a lower limb rehabilitation exoskeleton that adapts to user gait. It employs a multi-task learning model, simultaneously outputting user identity probability and movement pattern probability to generate a probability map representing the similarity between the current gait and a certain movement pattern of a sample user in a sample database. A gait phase variable parameter prediction model is used to predict gait phase variable parameters, employing angular velocity data from the initial stage of the current gait cycle and the matched movement pattern to predict the gait phase variable parameters for the current cycle. Finally, a pre-constructed relational constraint model corresponding to the matched sample user and their movement pattern is used to obtain the desired joint angles from the real-time gait phase, and the exoskeleton is tracked and controlled via a PD controller. This invention can adaptively adjust the exoskeleton's motion assistance mode according to the user's gait characteristics, and is suitable for rehabilitation training of patients with lower limb motor dysfunction.

Bodywear apparatus configured to be worn by a human user and attachable to footwear of the human user in order to augment the abilities of the lower limbs of the user is disclosed. In another aspect, footwear apparatus configured to be worn by a human user in order to augment the abilities of the lower limbs of the user is disclosed. Such bodywear apparatus and footwear apparatus are configured to reduce the effort a user must exert and improve the user's performance during walking, running, hiking, marching, and various other gaits as well as jumping, hopping, and other activities. In an aspect, bodywear apparatus further comprises a supplemental power device configured to further augment the user's abilities by activating during portions of the user's gait cycle.

This invention discloses a biomimetic cheetah spine elastic energy storage high-speed gait mechanism, belonging to the field of biomimetic legged robot motion execution and efficient gait control technology. Currently, quadrupedal and humanoid robots generally suffer from low energy utilization, high overall motion power consumption, significant gait rigidity impact, and limited continuous long-distance high-speed movement capability under high-speed running conditions. Conventional rigid linkage structures are difficult to achieve the efficient conversion and recycling of kinetic and elastic potential energy during biological movement. This invention mimics the biological movement mechanism of a cheetah during high-speed running, characterized by periodic bending and extension of the spine accompanied by elastic energy storage and release through tendons. It designs a multi-segment biomimetic flexible spinal main structure, combined with high-modulus energy storage tendon components, joint damping buffer units, and a collaborative drive linkage mechanism. This enables the robot to recover, store, and release energy within the complete gait cycle of stepping, takeoff, and landing, thereby significantly improving running speed, reducing drive system load, minimizing body vibration and impact, and enhancing overall stability and endurance under high-speed movement conditions. This technical solution has a highly original structure and is significantly different from existing bionic gait mechanisms. It can be widely used in equipment such as high-speed quadruped robots, emergency rescue robots, outdoor inspection robots, and racing robot platforms.

The invention provides a humanoid robot grabbing force grading intelligent judgment method and device, and the method comprises the steps: collecting the ratio of the contact areas of two soles and the inclination angle of a trunk in real time, recognizing a current gait phase, and estimating the transverse shaking amplitude of the trunk in a current gait period; judging a high-stability or low-stability state of a current phase according to the trunk transverse shaking amplitude, identifying a continuous high-stability state as a biped support period, and fusing target motion information in the biped support period to calculate a residual reachable distance; according to the residual reachable distance and the target movement speed, dynamically adjusting the grasp strength grade; determining a grasping stability boundary condition corresponding to the grasping force level, and analyzing a cooperative boundary satisfaction degree of grasping execution under the current condition; the grabbing feasibility is judged according to the cooperative boundary satisfaction degree, and the optimal grabbing execution opportunity is determined under the feasible condition; and inputting the optimal execution opportunity and the grabbing force level into a grabbing controller to generate a grabbing execution plan.

By using the helical axis in the knee joint movement of subjects during walking, we perform gait analysis that can be used to detect early-stage osteoarthritis of the knee. [Solution] A gait analysis method comprising the steps of: calculating the helical axis of the knee joint based on motion data of the subject's lower limbs during walking; extracting the flexion phase and extension phase during the stance phase of the subject's gait cycle; and obtaining an evaluation value to assess the condition of the knee by quantifying the variability of the helical axis group in one or both of the flexion phase and the extension phase.

The application discloses a kind of field operation personnel identity feature fusion identification method and system, the method includes: the decoding frame extraction of monitoring video file or real-time monitoring video stream is carried out, and sequence frame is obtained;Sequence frame is obtained to pedestrian detection, pedestrian re-identification and pedestrian tracking, and the gait image sequence and gait contour sequence of the object to be identified are extracted, and the target feature set is constituted;The target feature set of the object to be identified is matched with the target feature set in the target library constructed in advance, and the identity of the object to be identified is identified;In the application, each target feature set in the target library is bound with a worker identity in advance.The application can effectively solve the problem of identity recognition of uniformed workers in the scene where face is difficult to obtain and complete gait cycle cannot be captured, realize the identity recognition of field workers covering all scenes, and effectively improve the safety control level of plant and station.

The invention discloses a depression risk assessment method based on multi-modal gait feature fusion, and the method comprises the steps: collecting the multi-modal gait data of a subject, and recording a plurality of complete gait cycles; gait event anchor points are extracted, a unified gait phase sequence is constructed, and multi-modal alignment is completed; improving an XFat model to extract local features, constructing a cross-frame connection chain, and forming a local response embryo body sequence; applying forward and reverse rhythm perturbation, extracting phase correction, and starting delay, overshoot, damping and recovery steps; constructing a two-way debt transfer closed loop to form a two-way debt circulation closed tensor; and constructing a gait debt hysteresis loop, extracting an area, drift and a residual error, and outputting a risk level. According to the invention, through subthreshold rhythm perturbation and multi-modal gait feature fusion modeling, high-sensitivity identification and risk assessment of depression-related mental movement hysteresis features are realized.

The present application relates to the technical field of electromyography, in particular to a multi-modal electromyography monitoring driven fall risk prediction method and system for the elderly. The method comprises the following steps: collecting electromyography sequence, comparing voltage changes to generate activity trajectory, calculating peak distribution based on the activity trajectory to generate discharge rhythm trajectory, extracting adjacent rhythm changes to generate change distribution record, comparing change position and time relationship to judge time continuity to generate change section record, and establishing association between change section record and gait cycle to generate risk prediction result. In the present application, dynamic trajectory is generated based on continuous sequence to extract microscopic rhythm characteristics, position adjacency relationship is verified during walking process to determine evolution continuity, continuous record is strictly compared with gait cycle to judge corresponding association, details of lower limb movement dynamic reflection are fully restored, defects of traditional truncation means covering lag phenomenon are effectively overcome, abnormal potential activity rules are accurately captured in complex scenes, and comprehensive reliability of risk prediction is effectively improved.

The invention relates to the technical field of quadruped robot spine structures, and discloses a robot spine structure and a control method thereof.The robot spine structure comprises a robot and further comprises a spine body, the spine body is driven by a driving cable system, the two ends of the driving cable system are arranged at the trunk part of the robot, and the driving cable system is driven by a driving motor carried by the trunk part of the robot; and a flexible piezoelectric sensor for detecting bending and twisting deformation of the spine main body is arranged in the spine main body. The structure is integrated in a single structure, so that the robot can obtain high agility, high energy efficiency and excellent impact tolerance robustness at the same time, rigidity is dynamically scheduled in a gait cycle, and the robot is switched to a flexible state when quick movement is needed so as to save driving energy consumption; when force needs to be transmitted, the rigid state is switched to avoid energy loss, the elastic frame is used for storing and releasing energy, and the overall energy efficiency and cruising ability of the robot are greatly improved.

The present application relates to the technical field of medical health data analysis, in particular to a high-risk patient fall abnormal behavior early warning system based on multi-modal data fusion. The present application obtains a plurality of gait cycles constituted by time frames according to ankle coordinate distribution of time frames for any patient; obtains gait high risk of each gait cycle according to ankle coordinate distribution of time frames in each gait cycle; obtains center of gravity offset degree of each gait cycle according to hip coordinate distribution of time frames in each gait cycle, and obtains high-risk center of gravity offset benchmark of all patients in each gait cycle; obtains fall probability in each sliding window according to center of gravity offset degree, high-risk center of gravity offset benchmark of different gait cycles and a plurality of physiological parameter data of different time for any patient; and early warns fall abnormal behavior. The present application improves the accuracy of fall abnormal behavior early warning by accurately analyzing fall probability of high-risk patients.

The invention discloses a gait symmetry analysis and fall risk dynamic early warning method and system, and a medium, and belongs to the technical field of intelligent health monitoring. The method comprises the following steps: synchronously acquiring double-foot pressure time sequence data through a left foot pressure acquisition unit and a right foot pressure acquisition unit, and performing time synchronization and gait cycle segmentation; extracting multi-dimensional gait symmetry characteristics including time symmetry, pressure distribution symmetry and plantar pressure center symmetry; performing weighted fusion on the multi-dimensional features to calculate a gait asymmetry index; establishing a user personalized health baseline; and comparing the real-time gait asymmetry index with a baseline to calculate a standardized deviation degree, and triggering falling risk early warning by adopting a grading strategy in combination with time sequence trend analysis. Gait symmetry analysis is realized through bifoot pressure fusion, a personalized health baseline is established, long-term trend monitoring is performed, early dynamic early warning of the falling risk can be realized, and the method has the advantages of high early warning accuracy, high interpretability, low hardware cost and the like.

The invention relates to a sole foam structure optimization method based on foot dynamic stress distribution in the technical field of new-generation information, which comprises the following steps: acquiring pressure data of a foot in a gait cycle through a sensor array, and generating a foot dynamic stress distribution diagram; carrying out iterative simulation on the preliminary node distribution scheme, optimizing node spacing and an arrangement mode, and generating an optimized node distribution model; extracting a force application center coordinate from the optimized node distribution model, generating a sole foam structure prototype through three-dimensional modeling, and determining a dynamic matching parameter; executing a virtual wearing test according to the dynamic matching parameters, obtaining pressure distribution deviation data, and if the deviation is smaller than a preset threshold value, determining a final node distribution position; constructing a physical sample shoe by adopting the final node distribution position, and obtaining a durability index; and comparing the durability index with comfort experience data to judge whether the design requirement is met or not, and outputting a complete foam node arrangement scheme.

The invention provides an electro-hydraulic active ankle joint artificial limb control method and device. The method comprises the steps that a human body mass center height sequence in a first gait cycle of a normal leg of a subject is obtained; determining the human body mass center height of the prosthetic leg of the subject at the current moment of the second gait cycle by using the human body mass center height sequence of the first gait cycle; acquiring a hip joint angle, a knee joint angle and an ankle joint angle of the prosthetic leg of the subject at the current moment of the second gait cycle; based on the human body mass center height, the hip joint angle and the knee joint angle at the current moment, calculating an expected ankle joint angle and an expected ankle joint angular velocity at the next moment by utilizing a human body lower limb motion model; and determining a control law of the ankle joint controller at the next moment based on the ankle joint angle at the current moment and the expected ankle joint angle and the expected ankle joint angular velocity at the next moment. Compared with a traditional finite-state machine method, the method greatly simplifies the whole process of the test, and improves the control precision.

The invention discloses a biped robot gait control method, device and equipment and a storage medium. According to the technical scheme, the preset gait vector generation model is trained through the offline gait control data set, the target gait vector generation model is obtained, the training method does not depend on online interaction of a reinforcement learning environment, the model training process is stable, convergence is fast, interpretability is high, and the training efficiency is high. Through a reinforcement learning algorithm, according to the current state vector and the joint motion trail of the current gait cycle, the current control parameter is output to adapt to the current gait rhythm, the motion stability of the biped robot is guaranteed, the two processes of gait vector generation and control parameter generation are decoupled, and the motion stability of the biped robot is improved. The problem that a model is difficult to train after the stride frequency is put into a state vector is solved, and meanwhile, autonomous adjustment of the stride frequency of the biped robot, optimization of full-speed-domain energy efficiency, enhancement of robot gait control robustness and generation of humanoid natural gaits are achieved.

The application discloses a disturbance estimation and humanoid robot whole-body disturbance rejection control method based on DCM residual, and relates to the technical field of humanoid robot motion control. A disturbance observer based on DCM residual is designed, external force disturbance acting on the robot centroid can be estimated in real time without the need of a foot force sensor, and the disturbance observer has stronger robustness to model errors and sensor noise; secondly, a hierarchical online motion planner is proposed; a foothold planner optimizes the foothold position and gait cycle in real time through quadratic programming; a gait generator adopts a model predictive controller based on three-dimensional DCM, generates a robust centroid trajectory and gait according to the planned foothold; further, a whole-body disturbance rejection controller is developed, the estimated disturbance is embedded into the whole-body dynamics constraint, active compensation of the disturbance and direct control of the joint torque are realized. The application is used to solve the problems of insufficient robustness, low disturbance estimation accuracy and coupling of gait planning and whole-body control existing in the prior art.

The utility model discloses a robot for gait training, which relates to the technical field of gait training and comprises two robot bases and supporting arms, and the supporting arms are fixed at the top ends of the robot bases; the longitudinal section of each robot base is triangular, the robot bases are all hollow, and the interiors of the robot bases are all connected with power main motors. The cross beam is held to walk, the robot base is pushed to move for long-term training so as to correct the abnormal gait of a trainee, physical support is provided for the trainee through the cross beam, the risk of falling down in the training process is reduced, and the trainee can gradually adapt to the center transfer of the body and the rhythm change of the gait cycle. The power main motor is used for driving the one-way lead screw to rotate, the one-way lead screw is in threaded fit with the threaded hole, the adjusting arm and the cross beam are made to do lifting motion, and the requirements of patients with different heights and body function states are met.