39 results about "Gait types" patented technology

A landing shock absorbing device 18 provided in a foot mechanism 6 of a leg of a robot comprises an inflatable and compressible bag-like member 19 (a variable capacity element) on a bottom face side of the foot mechanism 6. The bag-like member 19 is constructed of an elastic material such as rubber. Air in the atmosphere can flow into and out of the bag-like member 19 by inflow / outflow means 20 provided with a solenoid valve 27 and the like. In a landing state of the foot mechanism 6 and in a state immediately after the foot mechanism shifts from the landing state to a lifting state, the solenoid valve 27 is closed to maintain the bag-like member 19 in a compressed state. Furthermore, during the bag-like member 19 in the inflating state during the lifting state of the foot mechanism 6, by controlling timing when the solenoid valve 27 is switched from a valve opening state to a valve closing state, a height of the bag-like member 19 in a compression direction is controlled to be a height suitable for a gait type of the robot. Thereby, posture stability of the robot can be secured easily while reducing a impact load in the landing motion of the leg of the legged mobile robot, and further, a lightweight configuration can be achieved.

A landing shock absorbing device 18 disposed in a foot mechanism 6 of a leg of a robot, wherein an inflatable bag-like member 19 (variable capacity element) is provided at a bottom face side of the foot mechanism 6. The bag-like member 19 is constructed of an elastic material such as rubber. The air in atmosphere may flow into and out of the bag-like member 19 by inflow / outflow means 20 equipped with a solenoid valve 27, and the like. In a lifting state of the foot mechanism 6, inflow of the air into the bag-like member 19 is controlled, thereby controlling the final height of the bag-like member 19 in an inflated state to the height in response to a gait type of the robot. While properly reducing an impact load during a landing motion of the leg of a legged mobile robot depending on the gait type of the robot, stability of a posture of the robot may easily be secured, resulting in allowing a configuration to be lighter in weight.

The invention discloses a gait type identification method based on a three-axis acceleration sensor and a neural network. The method specifically comprises steps as follows: step 1), establishing a database of gait acceleration signals; step 2), performing the segmentation stage of the signals in the corresponding period; step 3), removing a gravity factor; step 4), performing the gait feature extraction stage; step 5), performing gait presorting stage; step 6), performing dimensionality reduction operation of a gait feature set; and step 7), performing specific gait identification stage. According to the method, gait features are screened with a staged MIV (mean impact value) method, the gait type identification work is performed in combination of a BP (back propagation) neural network, the extracted features are taken as input independent variables of the neural network, six gait types of sitting, standing, walking in a low speed, walking in a high speed, going upstairs and going downstairs are effectively identified sequentially through the gait presorting stage and the specific gait identification stage, and the method can have higher accuracy and reliability through enlarging of a gait data capacity range and the optimized design of the neural network.

The invention discloses a support vector machine-based pedestrian gait classifying system and a support vector machine-based pedestrian gait classifying method. The system comprises a data acquiring module, a data processing module and an SVM (Storage Virtualization Management) module, wherein the SVM module is provided with a storage medium; the data acquiring module acquires gait training data and transmits the gait training data to the data processing module to be processed; the data processing module outputs the input quantity of the acquired gait training data to the SVM module to be studied to obtain an SVM classifier which is then stored in the storage medium; during real-time test, after real-time gait information is acquired in real time by the data acquiring module, data processing is preformed by the data processing module to acquire the input quantity of the test data; the input quantity of the test data is classified by the SVM module according to the SVM classifier to obtain real-time gait type. A static interval in a pedestrian moving process can be precisely detected by the system and the method, and the positioning precision is improved.

Methods and systems for determining a user's steps in portable device include deriving amplitudes from raw sensor data; comparing the amplitudes to an amplitude threshold, and counting a step when one of the amplitudes exceeds the amplitude threshold to obtain a step count; determining a current gait type based on the step count; dynamically adjusting the amplitude threshold in order to reduce effects of swinging movements and false steps; and applying a post filter to the step count based on time between steps and a minimum number of prior consecutive steps to derive a filtered step count that reduces false readings due to short bursts of rapid movement by the user.

The invention relates to an auxiliary motion system and a lower limb exoskeleton control method. The auxiliary motion system comprises a lower limb exoskeleton supporting device and a data acquisitiondevice and a control device which are arranged on the lower limb exoskeleton supporting device, wherein the lower limb exoskeleton supporting device comprises a shank supporting part, a thigh supporting part and a hip supporting part; the data acquisition device comprises a first sensor arranged at the junction of the hip supporting part and the thigh supporting part and a second sensor arrangedat the shank supporting part, and the first sensor and the second sensor are used for collecting gait data and walking data which are related to human motion; the control device is arranged on the hipsupporting part, and is used for acquiring the gait data and walking data which are collected by the data acquisition device and determining a current gait type according to the gait data and a gaitclassification rule so that the real-time physical state of the patient can be analyzed according to the gait type and the walking data under the corresponding gait type.

A landing shock absorbing device 18 provided in a foot mechanism 6 of a leg of a robot comprises an inflatable and compressible bag-like member 19 (a variable capacity element) on a bottom face side of the foot mechanism 6. The bag-like member 19 is constructed of an elastic material such as rubber. Air in the atmosphere can flow into and out of the bag-like member 19 by inflow / outflow means 20 provided with a solenoid valve 27 and the like. In a landing state of the foot mechanism 6 and in a state immediately after the foot mechanism shifts from the landing state to a lifting state, the solenoid valve 27 is closed to maintain the bag-like member 19 in a compressed state. Furthermore, during the bag-like member 19 in the inflating state during the lifting state of the foot mechanism 6, by controlling timing when the solenoid valve 27 is switched from a valve opening state to a valve closing state, a height of the bag-like member 19 in a compression direction is controlled to be a height suitable for a gait type of the robot. Thereby, posture stability of the robot can be secured easily while reducing a impact load in the landing motion of the leg of the legged mobile robot, and further, a lightweight configuration can be achieved.

Disclosed are an apparatus and a method for gait type classification using a pressure sensor of a smart insole, which are capable of classifying pieces of gait data having various variances using only a pressure sensor. The apparatus for gait type classification includes a gait data measuring part configured to measure pieces of gait data using a pressure sensor, a pre-processor configured to define a section of a unit step in all the pieces of gait data, divide the pieces of gait data for each unit step, and normalize the pieces of divided gait data to equalize lengths of the pieces of divided gait data, and a feature extractor configured to extract features suitable for gait type classification from the pieces of pre-processed gait data, and a gait type classifier configured to receive the extracted features as an input and determine and classify a final gait type.

The invention provides a human body gait analysis-based system of safety door and a control method thereof. The gait safety door provided by the application is equipment which collects and recognizesgait features of human bodies, and controls door leaf opening and closing according to the gait features. According to the system of the safety door, on the one hand, multi-dimensional human body gaitrecognition technology is employed for identification of the gait features, and the technical problems of low recognition result accuracy, poor robustness, high realization difficulty and the like existing in single-dimensional gait recognition of videos, radar echoes or the like in the prior art are solved; and on the other hand, aggregation of passer gait types is realized on the basis of the multi-dimensional human body gait features, then suitable opening duration is set for the different gait types, and intellectualization and humanization of automatic door opening and closing of the safety door are improved.

The invention belongs to the technical field of biometric recognition, and particularly relates to a gait abnormality classification method based on a deep convolution neural network. The method includes the following steps that a IMU worn on human body is used for collecting signals of normal walking and simulating typical abnormal gait walking, and triaxial acceleration information under different gaits is obtained; according to the typical walking frequency of a target, original data is subjected to windowing cutting pretreatment, and each data queue is correspondingly labeled according tothe gait type, wherein the CNN deep convolution neural network includes a first convolution layer, a second convolution layer, a first pooling layer, a second pooling layer, a full connection layer and a soft max output layer; finally, data labels are divided into a training set and a test set, the training set is sent to the CNN for training, and the test set is used for evaluating the model classification effect after training. The method omits complicated gait cycle division and feature extraction engineering, improves the classification accuracy of various abnormal gaits, reduces the workload of data preprocessing, and improves the classification accuracy.

The embodiment of the invention provides a gait recognition model building method based on myoelectric signals, a recognition method and a device. The model building method comprises the following steps of collecting the myoelectric signals; reducing the noise; adding a class tag and extract the following EMG signal characteristics: slope change rate, Willison amplitude, logarithm of variance, waveform length, and characteristics DB7-MAV; calculating the DBI index and SCAT index and obtaining the comprehensive evaluation results. The comprehensive evaluation result are randomly divided into atraining sample group and a test sample group according to a predetermined proportion, and input them into the LightGBM model for training and testing. The parameters in LightGBM model are adjusted according to the error of training set and test set, and grouped, trained, tested and adjusted repeatedly until the error of model test results accords with the data model of predetermined standard, andthe corresponding relationship between human gait type and comprehensive evaluation results is stored in the data model. The embodiment of the invention can efficiently and accurately establish a data model, and the gait recognition rate is high and the recognition result is more reliable.

A tunable rigidity insole with interchangeable stiffeners includes an arch pad main body and three rigid stiffeners. The arch pad main body includes a set of first to third engaging holes, and at least one or two of these three rigid stiffeners will be selected to assemble into the engaging holes on the arch pad main body. The three rigid stiffeners provide supports to lateral longitudinal, central and medial longitudinal arch portions respectively. The first, second and third rigid stiffeners have at least two engagement members for each stiffener, and the engagement members have engagement extensions with a partial length component toward another engagement extensions at the end of stiffeners thereof respectively. The engagement members engage with the arch pad main body corresponding to the engaging holes respectively. By selecting and assembling different stiffeners, the present invention can have different rigidities of arch supports to match with various foot biomechanics and gait types in order to provide different arch supports thereto properly.

The invention provides a gait control method, comprising: providing gait model and reference information; collecting original gait information and judging gait type according to the gait model; collecting the state information of the booster module and converting the state information into the parameter information; invoking the reference information and the parameter information to compare according to the gait type; and sending an adjustment instruction to the booster module so that the parameter information conforms to the reference information. The gait model of the gait control method ofthe present invention includes a foot-flattening model, heel off-ground model and toe off-ground model, at the stage when the wearer needs power assistance or adjustment, the comparison basis is provided, and the reference information is combined to enable the gait control method to realize the control of the power assistance module without re-determining the gait period, thereby avoiding the problem of tracking speed and precision degradation caused by continuously re-determining the gait period. The invention also provides a gait control system for realizing the gait control method.

A landing shock absorbing device 18 disposed in a foot mechanism 6 of a leg of a robot, wherein an inflatable bag-like member 19 (variable capacity element) is provided at a bottom face side of the foot mechanism 6. The bag-like member 19 is constructed of an elastic material such as rubber. The air in atmosphere may flow into and out of the bag-like member 19 by inflow / outflow means 20 equipped with a solenoid valve 27, and the like. In a lifting state of the foot mechanism 6, inflow of the air into the bag-like member 19 is controlled, thereby controlling the final height of the bag-like member 19 in an inflated state to the height in response to a gait type of the robot. While properly reducing an impact load during a landing motion of the leg of a legged mobile robot depending on the gait type of the robot, stability of a posture of the robot may easily be secured, resulting in allowing a configuration to be lighter in weight.

The invention discloses a support vector machine-based pedestrian gait classifying system and a support vector machine-based pedestrian gait classifying method. The system comprises a data acquiring module, a data processing module and an SVM (Storage Virtualization Management) module, wherein the SVM module is provided with a storage medium; the data acquiring module acquires gait training data and transmits the gait training data to the data processing module to be processed; the data processing module outputs the input quantity of the acquired gait training data to the SVM module to be studied to obtain an SVM classifier which is then stored in the storage medium; during real-time test, after real-time gait information is acquired in real time by the data acquiring module, data processing is preformed by the data processing module to acquire the input quantity of the test data; the input quantity of the test data is classified by the SVM module according to the SVM classifier to obtain real-time gait type. A static interval in a pedestrian moving process can be precisely detected by the system and the method, and the positioning precision is improved.

The invention discloses a snake-like robot hybrid three-dimensional gait control method. The snake-like robot mixed three-dimensional gait is three-dimensional movement generated by cross-mixing of basic motions such as plane wave motion, linear peristalsis, lateral winding and the like, and the device dominant mechanism is that different movement gait is adopted at different parts of the snake-like robot body. Different snake-like robot motions have different movement characteristics and terrain adaptability due to different movement mechanisms, the novel mixing can effectively integrate themovement characteristics and advantages of various gait, meanwhile, the disadvantages of the single gait are made up, and the snake-like robot can simultaneously have the advantages of multiple motiongait. According to the novel hybrid three-dimensional gait, the motion gait types of the snake-like robot can be expanded, the motion capability of the snake-like robot is greatly improved, and the flexibility and adaptability of the snake-like robot in different environments are effectively improved.

The invention discloses a planning method for a foot end track of a rhythm gait of a hexapod robot. The method comprises the following steps: determining a land occupation coefficient and a swing period number in one gait period according to three rhythm gait types; planning a walking stride and a single step length of the rhythm gait; planning a hexapod robot foot end motion track interpolation function based on a trigonometric function and an S-shaped function; planning an instantaneous step length interpolation function expression of a swing phase and a support phase; and solving the instantaneous coordinates of the foot end of the hexapod robot relative to a machine system. According to the rhythm gait foot end track planning method, parameters can be adjusted in real time, a smooth foot end motion track can be obtained, and the method is suitable for all-dimensional motion of rhythm gaits of a hexapod robot under different terrains.

The embodiment of the invention provides a gait detection method and system based on plantar pressure. The gait detection method is characterized in that arranging a pressure sensor in a plantar treading component; dividing the plantar treading component into different evaluation areas, and calculating an actual gait detection value of a user by a processor according to a pressure value of each evaluation area; setting standard values of various gaits through the processor, and comparing a set standard value of a certain gait with an actual detection value of the gait; and judging the gait type of the user according to a comparison result. The gait detection method and device provided by the invention are simple in technical design, easy to implement, low in power consumption, suitable forwearable gait detection equipment and capable of being applied to the fields of gait recognition, related disease pre-judgment and the like.

The invention provides a lower limb prosthesis hierarchical control system and method based on healthy side leg multi-source information, which comprises a man-machine system module, a sensing system module, a signal preprocessing module and a hierarchical controller. The sensing system module is mounted on one side of a healthy leg of a human body of the man-machine system module; the hierarchical controller is composed of a top-layer controller module, a middle-layer controller module and a bottom-layer controller module. The input end of the signal preprocessing module is the signal output of the sensing system module, and the output of the signal preprocessing module is divided into two parts which are respectively connected with the top-layer controller module and the middle-layer controller module; the output of the top-layer controller module is connected with the middle-layer controller module; the output of the middle-layer controller module is connected with the bottom-layer controller module; and the bottom-layer controller module and the prosthesis side of the man-machine system module perform bidirectional interaction. According to the invention, the gait discrete switching of different gait types in actual use can be realized, and the walking speed can be continuously adjusted in real time according to the human body intention in the same gait period.

The invention provides a gait control method, comprising: providing gait model and reference information; collecting original gait information and judging gait type according to the gait model; collecting the state information of the booster module and converting the state information into the parameter information; invoking the reference information and the parameter information to compare according to the gait type; and sending an adjustment instruction to the booster module so that the parameter information conforms to the reference information. The gait model of the gait control method ofthe present invention includes a foot-flattening model, heel off-ground model and toe off-ground model, at the stage when the wearer needs power assistance or adjustment, the comparison basis is provided, and the reference information is combined to enable the gait control method to realize the control of the power assistance module without re-determining the gait period, thereby avoiding the problem of tracking speed and precision degradation caused by continuously re-determining the gait period. The invention also provides a gait control system for realizing the gait control method.

The invention discloses a human abnormal gait recognition method based on a smart phone. According to the method, human gait data can be effectively collected through the smart phone, the related feature information of different gait types of a human body is extracted, and the classification and recognition of different abnormal gait types are achieved. The limitation of a traditional abnormal gait analysis and detection method is overcome.

The invention discloses a method for training a gait recognition model of unbalanced data acquired in the real world, and relates to the technical field of gait recognition data analysis, and the method comprises the steps: obtaining experiment balance gait data and real-time gait data of a corresponding time point; according to the method, gait category real-time analysis and labeling are carried out on a balance data set and a real-time data set, a feature vector feature center point value under each gait type is calculated, and a mean square error is used for optimizing an error of the center point value between experimental balance gait data and real-time gait data at a corresponding time point; setting a judging and comparing program of the real-time feature vector and the balance feature vector, calculating the probability of belonging to the same class by adopting cosine similarity, taking the real-time feature vector after projection dimension reduction as input sample data of an initial gait recognition model, taking the balance feature vector of a balance data set as a supervision label, training the gait recognition model, and obtaining a real-time gait recognition model; therefore, accurate recognition of real-time gaits is realized.

The invention provides a general gait design and control method of a footed robot. The gait design includes determining the gait parameters: StepsInGait, NrLiftedPos, TLDivFactor, HalfLiftHeigth, and the position parameters of the starting key points of the gait cycle of each leg of the footed robot. These parameters are used to determine a set of key position points in the gait cycle. The control method obtains the position coordinates of the foot end of each step of each leg of the robot in a gait cycle, and solves the rotation angle of each joint of the leg according to the kinematic model and inverse kinematics. The invention simplifies the gait design into the setting of gait parameters, one set of gait parameters corresponds to one gait type, and a set of key position points in the gait cycle is determined; Height, fuselage height and other control variables, provide a set of general foot robot foot trajectory calculation method.

A gait analysis device, a gait analysis method, and a gait analysis program. In the gait analysis device, a step frequency change with respect to a running speed is acquired with respect to running of a subject. A step length change with respect to a running speed is acquired with respect to running of the subject. A determination section (80) calculates a principal component score from the slope of the step frequency change and the slope of the step length change of the subject, based on a principal component analysis model that is generated in advance based on measured values of a plurality of runners, and determines which of a plurality of gait types including a stride type and a step frequency type the running of the subject conforms to, based on the calculated principal component score.

The invention discloses a gait monitoring method and system based on a carbon nanotube flexible pressure sensor. The method comprises the following steps: receiving pressure distribution data acquired by the carbon nanotube flexible pressure sensor when a user walks; performing gait analysis on the pressure distribution data by using a hybrid neural network, judging a gait type of the user, and evaluating a walking posture; according to the gait type and the evaluation result, the sensitivity setting of the flexible pressure sensor is automatically adjusted to optimize the data acquisition process; and generating a personalized gait report, and sending the gait report to the user. By utilizing the embodiment of the invention, the limitation of the existing gait monitoring technology can be improved, and more accurate and personalized gait analysis can be provided to meet the requirements of different users and application scenes.

The application provides a lower limb rehabilitation exoskeleton robot control method and system, which comprises the following steps: collecting joint torque, lower limb joint angle, joint angular velocity and plantar pressure data of a patient to calculate a rehabilitation state evaluation index; collecting the angle difference of left and right hip joints, identifying the current gait type and the expected trajectory under the corresponding gait based on the gait phase variable, and optimizing the expected trajectory based on the rehabilitation state evaluation index to obtain a target optimized trajectory; calculating the nominal torque based on the acceleration of the trajectory and the parameters of the dynamics model, designing a sliding surface through the implementation of monitoring trajectory tracking error, generating a compensation torque, and calculating a control torque vector. By identifying the gait type and generating a personalized trajectory, and then decomposing the nominal torque and the compensation torque through the U-K controller, high-precision tracking is realized while the model uncertainty disturbance is inhibited, and the naturalness of human-machine cooperation and the safety of rehabilitation training are significantly improved.

The invention discloses a method and a device for waking up an intelligent device, which relate to the technical field of artificial intelligence and can solve the problem that in different application scenarios, the recognition strategies for waking up voices are the same, the flexibility is poor, and the use requirements cannot be met. The method of the present invention includes: collecting the current gait information of the user; using a preset gait recognition model to identify the gait type represented by the current gait information; determining the wake-up speech recognition strategy according to the gait type; when receiving When the voice wake-up word input by the user is detected, the voice wake-up word is recognized according to the wake-up voice recognition strategy, and the smart device is woken up based on the recognition result. The present invention is mainly applicable to the scenario where the smart device is awakened by voice.

The invention discloses a hybrid intelligent artificial limb control method and system. The method comprises the following steps: detecting gait information from a healthy limb through an artificial limb detection module, transmitting the gait information to a gait planning module, generating an artificial limb gait through the gait planning module, and transmitting the artificial limb gait to a hybrid driving mechanism. An artificial limb executing mechanism is driven by the hybrid driving mechanism to move, the ground-human-artificial limb interaction process is completed, and the gait information comprises gait parameters and gait types. The method has the beneficial effects that the motion intention of an amputated person can be sensed, the artificial limb controlled by a micro-processing unit can achieve any gait, and the other healthy leg of the amputated person can be accurately coordinated to act. The effectiveness and reliability of the system are higher, and in order to improve the man-machine interaction capability and adaptability of the system, the system can adapt to different users to freely and naturally walk under different road conditions and different walking modes.

The present invention provides a lower limb prosthesis hierarchical control system and method based on multi-source information of the healthy leg, comprising: a human-machine system module, a sensing system module, a signal preprocessing module and a hierarchical controller; the sensing system module is installed in a The human body healthy leg side of the human-machine system module; the layered controller consists of a top-level controller module, a middle-level controller module and a bottom-level controller module. The input of the signal preprocessing module is the signal output of the sensor system module, and its output is divided into two parts, which are respectively connected to the top controller module and the middle controller module; the output of the top controller module is connected to the middle controller module; the middle controller The output of the module is connected to the bottom controller module; the bottom controller module conducts two-way interaction with the prosthetic side of the human-machine system module. The invention can realize the discrete switching of gait of different gait types in actual use, and can continuously adjust the walking speed in real time according to the human body intention within the same gait cycle.

The present application relates to an auxiliary movement system and a lower limb exoskeleton control method. The auxiliary movement system includes a lower limb exoskeleton support device, and a data acquisition device and a control device arranged on the lower limb exoskeleton support device, and the lower limb exoskeleton support device includes a calf support part, a thigh support part and a hip support part . The data acquisition device includes a first sensor disposed at the connection between the hip support part and the thigh support part and a second sensor disposed at the calf support part, for collecting gait data and walking data related to human motion. The control device is arranged on the hip support part, and is used to obtain the gait data and walking data collected by the data acquisition device, and determine the current gait type according to the gait data and gait classification rules, so that it can be based on The gait type and the walking data under the corresponding gait type analyze the real-time physical state of the patient.