49 results about "Gait pattern" patented technology

The invention discloses a complex terrain-oriented quadruped robot self-adaptive gait generation system and method. The system comprises a sensor system used for collecting terrain data and robot state information; the terrain sensing module identifies terrain types and terrain feature parameters according to sensor data, and quantifies terrain features into parameters; the multi-modal gait library is used for storing a plurality of basic gait modes and corresponding gait parameters; the parameterized gait generation module is used for selecting a basic gait from the gait library and optimizing and generating an optimal gait adaptive to the current environment according to terrain parameters and task parameters; the gait smooth transition algorithm synthesizes all intermediate postures in the time and space interpolation generation transition process to obtain a smooth transition trajectory; the terrain adaptability adjusting module is used for finely adjusting the gait parameters according to real-time feedback; and the execution control module is used for converting the generated gait parameters into joint control instructions for controlling the robot so as to execute corresponding actions. The quadruped robot can adapt to more complex environments.

The invention provides an ankle rehabilitation exercise intelligent management system and method based on multi-modal data fusion, and relates to the technical field of medical rehabilitation, and the method comprises the steps: collecting sole state data and electromyographic signal data of a patient end through a sensor network; determining a target gait mode and gait parameters according to the sole state data, and summarizing to obtain real-time gait data; determining muscle strength and muscle coordination degree according to the electromyographic signal data, and summarizing to obtain muscle state data; constructing an ankle motion function abnormity prediction model, and determining an ankle fault score according to the real-time gait data and the muscle state data; the ankle fault grade is judged according to the ankle fault score, and a personalized ankle rehabilitation strategy is made based on the ankle fault grade and sent to the visual display terminal, so that the ankle movement data can be accurately collected, a personalized rehabilitation exercise scheme is customized, the rehabilitation effect of a patient is improved in combination with an exercise auxiliary structure, and the rehabilitation effect of the patient is improved. The rapid recovery of the ankle function is promoted.

A method for pose and gait classification and motion prediction using spatio-temporal relationships between body joints includes capturing a sequence of images or video frames of a subject; applying a neural network-based pose estimation algorithm to the sequence of images or video frames to detect landmark positions of anatomical joints; constructing a spatio-temporal graph from the detected landmark positions of the one or more anatomical joints, wherein nodes of the spatio-temporal graph correspond to the anatomical joints and the landmark positions, spatial edges of the spatio-temporal graph represent anatomical connections between the anatomical joints within a single image or frame, and temporal edges connect the one or more anatomical joints across successive images or frames of the sequence of images or video frames; and inputting the constructed spatio-temporal graph into a spatio-temporal graph convolutional network (ST-GCN) to classify pose and gait patterns and predict motion or stability states.

The invention relates to the technical field of intelligent control, and discloses a hip joint exoskeleton control method and system based on gait mode prediction and gait phase estimation, a terminal and a storage medium, and the method comprises the steps: constructing and training an initial unsupervised terrain detection model, and obtaining a target unsupervised terrain detection model; inputting the environment binary image into a target unsupervised terrain detection model to obtain a terrain detection result, and obtaining a gait mode prediction result based on a majority voting strategy; according to the hip joint angular velocity, target gait phase estimation is obtained based on a self-adaptive oscillator system; on the basis of the expected auxiliary torque curve, net auxiliary torque is obtained according to the gait mode prediction result and target gait phase estimation, and hip joint exoskeleton assistance modes are switched according to the net auxiliary torque. According to the method, marking of a large amount of data is avoided through the unsupervised terrain detection model, terrain detection and exoskeleton control are combined, and the terrain self-adaptive walking capacity of the exoskeleton is enhanced.

The invention provides a biped robot gait planning method and device for a step terrain, and belongs to the technical field of robot gait planning, the method comprises the following steps: based on a linear inverted pendulum model, respectively establishing walking modes of an upper step and a lower step of a biped robot; based on a walking mode, mapping the linear inverted pendulum model under the step terrain into a segmented virtual height linear inverted pendulum model under the plane terrain; based on a segmented virtual height linear inverted pendulum model, gait planning of the biped robot under the stepped terrain is achieved through model prediction control. According to the biped robot gait planning method and device for the step terrain, the linear inverted pendulum model with the virtual centroid height is used, the gait mode is established according to the terrain elevation information and the landing point information of the step environment, and the method and device can adapt to the irregular step terrain with the variable height and the variable length; and the gait has good terrain adaptability.

The invention provides a freezing gait assessment method, device and system. The frozen gait evaluation method comprises the following steps: generating a kinematics feature set, a dynamics feature set and a space-time parameter feature set of gaits of a detected object; for each feature set, constructing an attribute graph for representing the feature set, and performing feature extraction on the attribute graph to obtain a corresponding graph feature and an importance score of each gait feature in the feature set; based on the weight value corresponding to each feature set, carrying out fusion and feature extraction on the graph features corresponding to each feature set to obtain global features; inputting the global features into a prediction module to obtain a frozen gait severity score of the detected object; and for each gait feature, determining the gait score of the gait feature based on the normalized feature value of the gait feature, the importance score and the weight value corresponding to the feature set where the gait feature is located, and generating a radar map for representing the gait mode of the detected object based on the gait scores of all the gait features.

The application relates to the technical field of intelligent control, and discloses a hip exoskeleton control method and system based on gait pattern prediction and gait phase estimation, a terminal and a storage medium, the method comprising the following steps: constructing an initial unsupervised terrain detection model and training the model to obtain a target unsupervised terrain detection model; inputting an environment binary image into the target unsupervised terrain detection model to obtain a terrain detection result, and obtaining a gait pattern prediction result based on a majority voting strategy; obtaining a target gait phase estimation based on an adaptive oscillator system according to a hip joint angular velocity; obtaining a net auxiliary torque based on an expected auxiliary torque curve, a gait pattern prediction result and the target gait phase estimation, and switching a hip exoskeleton assistance mode according to the net auxiliary torque. The unsupervised terrain detection model avoids labeling a large amount of data, the terrain detection is combined with the exoskeleton control, and the terrain self-adaptive walking capability of the exoskeleton is enhanced.

Methods and systems for managing a data processing system are disclosed. Motion data for the data processing system may be usable to characterize a gait pattern for a person transporting the data processing system while the motion data is obtained. A management controller of the data processing system may perform a motion analysis process using the motion data to determine whether the gait pattern of the motion data is expected for the data processing system. If the gait pattern is not expected for the data processing system, then the data processing system may be subject to unauthorized transport, which may negatively impact the security of the data processing system. In response, the management controller may initiate performance of an action set in order to place the data processing system in an elevated security state.

The invention discloses an exoskeleton driving method based on real moment constraint and continuous gait phase modeling, which comprises the following steps: acquiring multi-modal signal data in the gait process of a subject by using a multi-sensor synchronous acquisition system, including IMU signals, EMG signals, plantar pressure signals and optical motion capture data; preprocessing the multi-mode signal data to obtain a preprocessed signal; performing continuous gait phase prediction and gait pattern recognition according to the preprocessed signal; estimating a joint instantaneous moment by using a pre-trained moment estimation network based on the predicted gait phase and gait mode; and converting the obtained instantaneous moment of the joint into a driving signal of an exoskeleton actuator. According to the method, discrete event triggering is replaced by continuous gait phase modeling, so that the smoothness and robustness of control are ensured; meanwhile, a mechanical real constraint and individualized moment estimation mechanism is introduced, stable man-machine cooperative control is achieved, and the adaptability and use experience of the exoskeleton in a complex environment are remarkably improved.

The invention discloses an interpretable abnormal gait detection method and model based on multi-task graph fusion learning. The method comprises the steps that gait graphs are constructed, and a plurality of gait graphs are arranged according to time to obtain a time sequence gait graph; an LRP-MGG neural network model is constructed; gait time dependence features are extracted from the time sequence gait image through an accumulative GRU block of an LRP-MGG neural network model; local space features embedded in a time-dependent feature space are obtained from the gait time-dependent features by using a deep GCN module; carrying out gait mode classification based on a graph through a DiffPool module; interpretable abnormal gait information is obtained by learning through a CNN deep convolutional neural network model by using gait time-space significant difference features; the importance score of each feature is calculated by adopting hierarchical correlation propagation (LRP); according to the method, training of a plurality of tasks is combined, the data amount and complexity are reduced, and therefore the generalization ability and prediction ability of the model are improved.

The invention provides a gait evaluation method and system based on a human body nonlinear system analysis technology, and the method comprises the steps: collecting a gait cycle six-channel high-precision time sequence signal outputted by a wearable inertial measurement unit, eliminating noise and gait difference through wavelet threshold denoising and Z-score standardization, extracting a chaotic feature vector composed of a Lyapunov index spectrum and a Kolmogorov entropy value, and carrying out the recognition of a gait signal, a wavelet neural network is adopted to realize nonlinear mapping of chaotic features and phase-space reconstruction parameters, and a self-adaptive feedback mechanism is introduced to dynamically optimize modeling parameters, so that the accuracy and personalized matching capability of gait pattern recognition and stability evaluation are effectively improved; quantitative characterization of the gait chaos level and real-time online model optimization can be achieved, and high-robustness support is provided for rehabilitation training and exercise aided decision making.

The invention discloses a robot gait control method and device suitable for walking on a slippery road surface and a biped robot. A reinforcement learning and MPC combined control mode is adopted, the robot is controlled to carry out normal gait walking, and data of joint motors and foot sensors are collected in real time; the state of the robot is judged, specifically, when the robot possibly overturns, the robot enters a slow gait mode, and the judgment standard that overturning possibly occurs is that the states of n steps in the future are deduced in the simulation deduction environment, and whether the n step presents the overturning trend or not is judged; and when the robot overturns, the robot enters a high-frequency gait mode, and a related gait regulation and control mode is designed. The problem that the biped robot easily slips on a wet and slippery road surface is solved; and when slipping occurs, the problem is difficult to remedy. And the stable walking capability of the robot on a complex road surface is improved.

The application discloses a Parkinson gait evaluation method and system based on a millimeter wave radar signal. The method comprises the following steps: acquiring a millimeter wave radio frequency signal in an environment, performing data processing on the signal to obtain a distance spectrum of position change of a Parkinson patient's body and a Doppler spectrum reflecting the degree of change of the Parkinson patient's body; extracting a peak value at each moment from the distance spectrum through a filtering method, calculating a cross-correlation coefficient of the Doppler spectrum as an index of gait pattern matching, and dividing the Doppler spectrum according to each step; calculating gait features according to the filtered distance spectrum peak value and the divided Doppler spectrum; inputting the normalized gait features into a trained machine learning model for feature evaluation to obtain a UPDRS-III score of the patient. The application realizes non-invasive measurement and evaluation of Parkinson gait features in a low-cost manner, is convenient to operate, and is accurate in evaluation effect, thereby providing quantitative data and diagnosis reference for doctors.

The present invention proposes a visual gait recognition method and system based on deterministic learning. The method collects a gait sequence consisting of multiple frames, extracts three-dimensional gait variables from each frame of the gait sequence, forms a three-dimensional gait variable sequence, and plots a three-dimensional gait phase space trajectory. The three-dimensional gait variable sequence is input into a trained RBF neural network to obtain a gait dynamic feature sequence and time-invariant knowledge. The time-invariant knowledge is used to construct a gait pattern library, and the dynamic trajectory is plotted. The three-dimensional gait variable sequence of the gait sequence to be identified is extracted, and a state estimator is constructed using the time-invariant knowledge in the gait pattern library. The dynamics of the gait sequence to be identified are quickly compared with the dynamics of each gait in the gait pattern library to obtain the final gait recognition result. The present invention can accurately reflect the spatiotemporal characteristics of each individual, keenly capture changes in gait patterns, improve the accuracy of gait recognition, and has strong robustness across perspectives.

The invention relates to a method for automated device control for use in a vehicle (400) comprising steps (S100 to 180): - Identification and localization of a person by means of at least one sensor (200) for detecting the vehicle's surroundings (400), - Determining parameters for assessing a person's emotional state, - Determining the person's emotional state based on the parameters, - Establishing a response learned by an algorithm from previously recorded emotional states and associated interactions of the person with the vehicle (400) and / or at least one vehicle system, and - automated control of the vehicle (400) and / or the vehicle systems according to the specified response, wherein - the parameters for recording the person's emotional state are determined when the person moves towards the vehicle (400) and an intention to interact is detected by means of a posture and / or at least one gesture, - and data on the person's posture and / or gait pattern and / or movement speed are used as parameters for recording the person's emotional state and - the person's emotional state is determined based on data relating to posture and / or gait and / or speed of movement.

Described herein are methods, systems and computer-program products for intra- and inter-gait classification for both symmetric and asymmetric gait patterns using images.

The control device (10) according to this disclosure switches parameters that affect the ground reaction force at the feet of the robot's (20) legs (22) in response to a change in the robot's (20) gait pattern, and outputs control information used to control the legs (22) based on the parameters.

The invention discloses a gait recognition method for a Parkinson's disease patient, a medium and equipment, and the method comprises the steps: collecting gait video data of a user, inputting a trained gait recognition model, and outputting a Parkinson's disease classification result. According to the model, space-time gait features are extracted by adopting a backbone network, and the focusing capability on PD typical gait features is enhanced in combination with a multi-scale attention mechanism module; according to the method, time sequence dimensions are compressed through a horizontal pooling module, feature normalization and classification optimization are carried out through a BNNeck module, and triple loss and cross entropy loss combined training is adopted so as to improve the discrimination capability of the model on a PD gait mode. And finally, a fine-grained identity recognition result is converted into binary classification output of Parkinson's disease patients and non-patients through a secondary discriminator. According to the method, automatic detection of PD gait abnormity is realized, the recognition precision of the model on a PD specific motion mode is effectively improved, and early screening and auxiliary diagnosis of Parkinson's disease are facilitated.

The application discloses an interpretable abnormal gait detection method and model based on multi-task graph fusion learning, and the method is: constructing a gait graph and arranging multiple gait graphs according to time to obtain a time sequence gait graph; constructing an LRP-MGG neural network model; extracting gait time dependence features through the cumulative GRU block of the LRP-MGG neural network model; obtaining local space features embedded in the time dependence feature space by using a deep GCN module; performing graph-based gait mode classification through a DiffPool module; learning interpretable abnormal gait information through a CNN deep convolutional neural network model by using gait space-time significant difference features; and calculating the importance score of each feature by using a hierarchical relevance propagation LRP. The application combines the training of multiple tasks, reduces the amount and complexity of data, and thus improves the generalization ability and prediction ability of the model.

The invention discloses a neural network gait recognition system and method based on an array data acquisition strategy. The recognition system comprises a gait data acquisition module and a gait recognition module. The gait data acquisition module acquires gait data through 12 IMU (Inertial Measurement Unit) sensors in array layout; the gait recognition module carries out gait mode recognition through a parallel attention convolutional network based on coding-decoding; the parallel attention convolutional network based on coding-decoding comprises three parallel coding-decoding structures and a connection structure of multi-receptive field feature extraction and a fusion attention mechanism. The problem that a single sensor drifts in the installation and wearing process is solved through array sensing collection, and meanwhile the influence of the number difference of testers is made up. The accuracy and efficiency of gait recognition are improved through coding-decoding parallel attention convolutional network gait recognition.

A walker device is described herein including two side frames, each side frame including a front vertical support, a rear vertical support and at least one connecting member extending between the front and rear vertical supports. The walker device further includes a cross bar extending between the two side frames and pivotally connecting to the front vertical supports of the two side frames. The walker device also includes a tension device which applies a resistive force to the pivoting motion between the first cross bar and the two side frames. The walker device is therefore capable of a pivoting configuration which enables the user to learn or re-learn a more natural gait pattern including rotation of the upper and lower body. Some embodiments of the walker device include a second, auxiliary cross bar that is parallel to the first cross bar and horizontally offset from the first cross bar.

The invention provides an exoskeleton compliant control method and system based on deep learning prediction. The method comprises the following steps: acquiring IMU (Inertial Measurement Unit) data of a historical gait cycle of a user, and inputting the IMU data into a pre-constructed deep learning model for training; acquiring actual joint angle data of the user in the current gait cycle in real time, performing time alignment on the actual joint angle data and the joint angle data predicted by the trained deep learning model, and performing difference calculation based on the aligned joint angle data to obtain a joint angle offset; the joint angle offset serves as input, the control rate is obtained through fuzzy PID calculation, and the control rate serves as a control signal to softly control the exoskeleton. The method adapts to gait modes of different users, personalized and optimized exoskeleton control is achieved, the deep learning model is continuously optimized according to real-time feedback, and the effect of compliant control is achieved.

The present application relates to a fatigue gait pattern recognition device and method based on a multi-modal sensor, multi-modal sensor data is collected based on a multi-modal sensor, gait segmentation is performed after preprocessing, data samples after gait segmentation are obtained, including multi-modal sensor data and corresponding data features; an improved feature fusion model is constructed, and the model is trained to be stable with data samples; multi-modal sensor data is collected, and the preprocessed data is input into the trained model, and the fatigue gait pattern recognition result is output; the device includes two groups of multi-modal sensors for collecting multi-modal sensor data, and the synchronous transceiver device sends the corresponding two groups of multi-modal sensor data after matching; the controller acquires the multi-modal sensor data and recognizes the fatigue gait pattern. The present application realizes high-precision classification of fatigue gait pattern, and the accuracy is improved by 15%-20% compared with traditional single-mode method; based on dynamic threshold classification and multi-dimensional feature analysis, user-specific rehabilitation suggestions are generated, and walking ability and safety are improved.

This invention discloses an efficient gait control method for a quadruped robot dog based on biomechanical principles. By collecting and analyzing the gait characteristics of quadruped animals in nature, a more realistic reference can be provided for the design of the quadruped robot dog, making its gait closer to nature and improving the smoothness and stability of walking. By optimizing the gait model using simulation technology, an efficient and energy-saving gait pattern can be obtained, reducing energy consumption and improving walking speed and efficiency. At the same time, considering the hardware characteristics of the quadruped robot dog, the initial gait pattern is optimized through a gait generation algorithm to adapt it to different physical structures and movement capabilities, maintaining stable walking in complex environments. By applying specific calculation formulas and adjusting algorithm parameters, the energy consumption per step can be significantly reduced, improving overall energy efficiency. Multiple movement patterns can be generated to adapt to different environments and task requirements, effectively improving the robot dog's walking efficiency and reducing unnecessary energy consumption and movements.

The application provides a gait parameter adaptive optimization method and system based on LSTM, which comprises the following steps: constructing a training set, wherein the training set comprises gait analysis data and joint angles of rescue personnel in various environments and gait modes on the well, and the gait analysis data comprises inertial measurement signals, electromyographic signals and plantar pressure signals; constructing a prediction model based on LSTM, training the prediction model by using the training set to obtain a trained prediction model; obtaining real-time gait analysis data of the current time step of the rescue personnel in the environment underground, inputting the real-time gait analysis data into the trained prediction model to output an initial value of the joint angle prediction of the next time step, combining the expected joint angle to enhance the electromyographic signals in the real-time gait analysis data, and then reusing the trained prediction model to output a target value of the joint angle prediction of the next time step, so as to adaptively adjust the gait parameters of the equipment worn by the rescue personnel based on the target value of the joint angle prediction in the next time step.

The present disclosure presents improved treadmill control systems and methods. One such method comprises initiating a recording a video sequence of a walking exercise by a subject on a treadmill device; extracting intra-gait phases of the subject from the recorded video sequence using a video temporal alignment with a neural network; generating a series of treadmill belt control settings for the treadmill device corresponding to each phase of the gait pattern of the subject; and signaling the series of treadmill belt control settings to a motor controller of the treadmill device. Other methods and systems are also provided.

The present invention provides a method, device, electronic device and storage medium for predicting human gait, and relates to the field of deep learning technology. The present invention can obtain the current surface electromyographic signal of the lower limbs of the human body, perform electromyographic feature learning and gait pattern prediction in multiple dimensions on the current signal window corresponding to the current surface electromyographic signal, and determine the target gait prediction result according to the current prediction result and the adjacent prediction results corresponding to multiple adjacent signal windows stored in advance. In this way, through multi-dimensional electromyographic feature learning, the potential mapping relationship between the surface electromyographic signal and the gait pattern can be fully explored, and by combining the adjacent prediction results corresponding to multiple adjacent signal windows, the stability and reliability of the prediction result can be improved. Therefore, the present invention can achieve high-accuracy gait prediction, thereby improving the real-time performance of gait recognition and realizing the timely switching of the power-assisting strategy of the exoskeleton mechanism.

Systems and methods for monitoring heart failure (HF) status in a patient are discussed. An exemplary system includes a gait analyzer circuit than can receive gait or balance information, and generate a gait feature such as gait speed or a gait pattern. The system includes a HF detector circuit that can detect patient HF status, or to predict patient risk of a future worsening heart failure (WHF) event, using the gait feature. In some examples, the system may trigger sensing physiologic information according to the detected gait, and detect patient HF status using the sensed physiologic information. The system can initiate or adjust a heart failure therapy according to the HF status or the WHF risk.

The invention discloses a biomechanical principle-based efficient gait control method for a quadruped robot dog, which can provide a more real reference for the design of the quadruped robot dog by collecting and analyzing the gait characteristics of the quadruped animal in the nature, so that the gait of the quadruped robot dog is closer to the nature, the walking fluency and stability are improved, and the safety of the quadruped robot dog is improved. A simulation technology is used for optimizing a gait model, an efficient and energy-saving gait mode can be obtained, energy consumption is reduced, the walking speed and efficiency are improved, meanwhile, hardware characteristics of the four-footed robot dog are considered, an initial gait mode is optimized through a gait generation algorithm, the four-footed robot dog is made to adapt to different physical structures and movement capacities, stable walking in a complex environment is kept, and the walking efficiency is improved. And by applying a specific calculation formula and adjusting algorithm parameters, the single-step energy consumption can be remarkably reduced, the overall energy efficiency is improved, multiple motion modes are generated to adapt to different environment and task requirements, the walking efficiency of the robot dog is effectively improved, and unnecessary energy consumption and actions are reduced.

The invention provides a method and a device for evaluating active substances to relieve chronic alcoholic brain injury. The method comprises the following steps: acquiring gait data of a normal group, a model group and an intervention group; carrying out preprocessing and feature extraction on the collected original gait data; training the gait data of the normal group and the model group, and establishing gait mode models in normal and injured states; and inputting the gait data of the intervention group into the gait mode model for similarity scoring, and evaluating the relieving effect of the active substances on the chronic alcoholic brain injury according to the scoring result. According to the method, the limitation of traditional single parameter comparison is broken through, and the improvement condition of active substances on the gait of the mouse with the chronic alcoholic brain injury is reflected more comprehensively and accurately on the whole; rapid and batch evaluation of various active substances and different doses is realized, and the drug research and development efficiency and the active substance screening efficiency are remarkably improved; the subjectivity in the evaluation process is reduced, and the reliability and comparability of the evaluation result are improved.