75 results about "Gait phase" patented technology

A method of matching a pose of a synthesised representation of a human or animal body to a captured image of that human or animal body is provided, which can be used to generate a graphical model of the body when disposed on a plane, such as a synthesised model of a football player on a field of play. The method includes receiving the captured image data, determining from the captured image data a plurality of limb position estimates, each position estimate corresponding to an amount by which limbs of the body are separated with respect to each other and deriving from the plurality of limb positions an estimated gait phase of the body. The estimated gait phase is then applied to a basis gait model in order to provide an estimated pose of the body, the basis gait model comprising data which defines a displacement of the limbs or parts thereof with respect to a gait cycle period. The estimated pose is then matched to that of the synthesised representation of the body.

The invention relates to a gait analysis method based on a plantar pressure. The gait analysis method comprises the steps of: (1) collecting plantar pressure signals through four pressure sensors; (2) carrying out gait phase analysis for the collected plantar pressure signals, comparing the total value of pressures collected by the four pressure sensors with a preset threshold value, the planta is in a swing phase when the total value of the pressures collected by the four pressure sensors is less than the preset threshold value, otherwise, the planta is in a supporting phase; (3) judging whether the gait phase analysis result is switched with the previous gait phase analysis result or not according to the plantar pressure signals, and entering into the next step at the point in time if the switching of gait phases happens; (4) carrying out an lower limb movement mode analysis based on the gait phases within the switching time of the gait phases; and (5) judging whether the gait analysis needs to be stopped or not according to a lower limb movement mode analysis result, and returning to the step (1) if not. The gait analysis method based on the plantar pressure, disclosed by the invention, can supply abundant human body movement information for the control of intelligent lower artificial limbs, and can be widely applied to the field of gait mode recognition.

This invention relates generally to footwear and methods for making the same, and more particularly to an athletic shoe with a reactive midsole. In one aspect of the invention, the midsole provides a continuously increasing offset between a heel center of pressure and a ball-of-foot center of pressure between the loading and a toe off gait phases.

The invention provides a gait phase distinguishing method based on lower limb joint movement information. The phase distinguishing method based on the lower limb joint movement information includes receiving angle information by angle sensors on the portion of thighs, cruses and foot faces; obtaining a lower limb joint movement parameter through an angle information processing system, particularly including angle information of knee joints and ankle joints, and angle speed information of the knee joints; obtaining gait phase of existing lower limbs by judging angle mark positions and angle speed of the knee joints. The angle information is collected by the three angle sensors which are arranged on the thighs, the cruses and the foot faces, so that phase judgment on the lower limbs is completed. The phase distinguishing method based on the lower limb joint movement information can simply, conveniently, and accurately judge the gait phase of the lower limbs, and improves control rapidity and accuracy of an artificial limn knee joint.

Disclosed herein is a gait monitoring apparatus and method. The gate monitoring apparatus includes a preprocessing unit for receiving data from a gait detection sensor and preprocessing the data. A swing detection unit detects, based on the data output from the preprocessing unit, whether a current gait phase is a swing phase in which a foot of a pedestrian is lifted from ground and swings in air when the foot moves forwards. A stance detection unit detects, based on the output data, whether a current gait phase is a stance phase in which the foot is in contact with the ground. A heel-strike detection unit detects, based on the output data, whether a current gait phase is a heel-strike phase in which the heel of the pedestrian strikes ground. A control unit determines the current gait phase, analyzes the gait of the pedestrian, and outputs gait analysis information.

The invention relates to a lower limb rehabilitation exoskeleton system and a walking control method thereof, and belongs to the technical field of medical robots. The walking control method comprisesa real-time data acquisition step, a gait phase recognition step and an exoskeleton control step, wherein the exoskeleton control step comprises the following operations: controlling a main supporting leg of an exoskeleton to be kept in a nearly upright state in a swinging process that a swing leg of the exoskeleton is to leave away from the ground up until the swing leg is to touch the ground; and controlling the swing leg of the exoskeleton to conduct a swinging action in a mode of leaving away from the ground when the exoskeleton is kept in a gait phase that the swing leg is to leave awayfrom the ground and after a weight transfer criterion is satisfied, wherein the weight transfer criterion is that an inclination angle of the upper body of an exoskeleton wearer is located within a first preset interval and plantar pressure of the exoskeleton wearer is located within a second preset interval. On the basis of the walking control method, a lateral overturning moment can be effectively eliminated, so that stable walking of the exoskeleton wearer can be guaranteed; and the exoskeleton system can be widely applied to rehabilitation training of patients with lower limb weakness or hemiplegia.

The invention relates to a wearable foot bottom pressure acquisition device for artificial limb control, and the device s characterized by comprising an insole, and a pressure sensing module and a signal transmission module both integrated in the insole, wherein the pressure sensing module comprises four pressure sensors which are arranged in the insole; and the four pressure sensors convert detected foot bottom pressure signals into variable resistance values and transmit the variable resistance values to the signal transmission module for transmission measurement. The invention provides the wearable foot bottom pressure acquisition device for artificial limb control aiming at the insufficiency of control signals for smart artificial lower limbs and overcoming the existing technical shortcomings. The acquisition system realizes real-time acquisition of time sequence and distribution information of foot bottom pressure, and is capable of providing policy basis in a plurality of aspects such as gait phase, movement model and body gesture for the control decision of the smart artificial limb after processing the information, thereby assisting the smart artificial limb to well replace the lost limb of the disabled. The wearable foot bottom pressure acquisition device for artificial limb control can be widely applied to artificial limb control.

The invention relates to a method for determining abnormal gait comprising the following steps: (a) measuring ground reaction force generated during walking by a plurality of sensors arranged on the left-foot and the right-foot respectively; (b) applying measurements from each of the plurality of sensors to a predetermined fuzzy membership function to transform the measurements into the first fuzzy values; (c) applying the first fuzzy values to a predetermined fuzzy logic to generate the second fuzzy values for a plurality of gait phases; and (d) comparing the second fuzzy values with pre-stored data of normal gait to determine whether it is abnormal gait or not. Therefore, it is possible to determine abnormal gait more accurately even with fewer sensors.

The invention discloses a functional muscle electrical stimulation walk-assisting device based on gait recognition and a control method. An IOT (Internet of Things) cloud server is connected with gait rehabilitation systems, and each gait rehabilitation system comprises a cellphone or a PC, a wireless router, a gait collection system, and a functional muscle electrical stimulator, wherein the signal input end of the cellphone or PC is connected with the signal output end of the gait collection system through the wireless router, a control signal output end of the cellphone or PC is connected with the control signal input end of the functional muscle electrical stimulator through the wireless router, the signal output end of the cellphone or PC is in wireless connection with the IOT cloud server, and the output end of the functional muscle electrical stimulator is connected with a surface muscle stimulation electrode. Different parts of a human body are connected with the signal collection ends of the gait collection systems. The device collects the gait phase big data, builds a gait time phase curve standard library, analyzes the gait variation characteristics of a patient, generates a gait regulation and control decision, and adjusts the muscle action state of the patient through employing the functional muscle electrical stimulators during the gait rehabilitation training. The device achieves a purpose that the patient can carry out the rehabilitation training at home.

The invention relates to a passive body weight supporting exoskeleton device based on gait phase self-unlocking. The passive body weight supporting exoskeleton device comprises a seat mechanism and supporting mechanisms arranged at the two sides of the seat mechanism; each supporting mechanism comprises a thigh mechanism, a knee joint mechanism and a shank mechanism; the seat mechanism comprises an arc seat, sliding block plates, thigh connecting rods, pulleys, limiting hooks and pull rings, the limiting hooks are installed on the bottom face of the seat, a guide rail groove is formed in the seat, the pulleys are fixedly connected with the corresponding sliding block plates through screws and are movably clamped in the guide rail groove of the seat, the pull rings are movably arranged on the side faces of the sliding block plates, and the upper portions of the thigh connecting rods are rotationally connected with the sliding block plates; the thigh mechanisms are connected with the corresponding thigh connecting rods in a fastened mode, and the pull rings are connected with the thigh mechanisms through steel wires; the lower portions of the thigh mechanisms are connected with the upper portions of the knee joint mechanisms in a fastened mode, and the lower portions of the knee joint mechanism are connected with the shank mechanisms in a fastened mode. Self-unlocking of knee joints can be completed automatically according to the gait phase without manual operation.

Provided is a method and device for assisting walking of a user that may receive a pressure value applied to a sole of a user from a pressure sensor, acquire acceleration information associated with a movement of the user from an acceleration sensor, determine a gait phase based on the pressure value and the acceleration information, determine an assist torque corresponding to the determined gait phase, and control a driver to output the assist torque.

A functional electrical stimulation system (1) for correction of drop-foot, comprising: a device (3) to be placed on a paretic leg, provided with a plurality of multi-pad electrodes (315) on one side (31), at least one of said electrodes (315) being configured to provide a stimulating electric signal on the point of the leg on which it is positioned, wherein said corresponding stimulating electric signals form a stimulation pattern; and at least one sensor (8) to be positioned on either said leg or corresponding foot, the sensor (8) being configured to, measure information during movement and emit sensor signals indicative thereof. The system further comprises means (6) for calculating a foot trajectory from said sensor signals, for detecting gait phase from said foot trajectory, for evaluating the quality of gait from said foot trajectory and for, if the quality of gait is below a certain threshold, modifying said stimulation pattern; and means (7) for selectively activating at least one of said electrodes (315) according to said modified stimulation pattern. Method, use and computer program product.

The invention provides a gait phase analysis method for segmented local peak detection, and relates to the field of gait analysis, in particular to a gait phase analysis method related to the foot angular velocity. The gait phase analysis method for segmented local peak detection is disclosed to solve the problem that a double-peak detection method used for gait phase division according to inertial data is poor in self-adaptability. The method is technically characterized by comprising the two steps that pitch angular velocity data of a foot in a gait movement is obtained; according to movement characteristics of a swing stage and a landing stage in the gait movement, the non-forward swing angular velocity is segmented by extracting the forward swing angular velocity. Local extreme valuesare extracted to replace a traditional peak detection method, and extraction of information of two key points including a heel contact point and a toe-off point during the gait movement is achieved. The method can be applied to the field of gait analysis.

A method and apparatus for assisting walking of a user is provided. Information related to a motion of a user wearing a walking assistance apparatus is measured by an inertial measurement unit (IMU), a gait phase of the user corresponding to the measured information is predicted using data learned in advance through machine learning, an assistance torque to be provided to the user is determined based on the predicted gait phase, and a driver is controlled to output the assistance torque.

The invention relates to a gait phase recognition method and system based on plantar pressure. The method is characterized by comprising the following steps that 1) a plurality of pieces of ground reaction force data of normal gaits of a plurality of objects are obtained; 2) walking exercise data and joint angle data of each object are obtained; 3) according to the obtained walking exercise data and an established gait phase, a hidden Markov model is constructed; 4) a plurality of pieces of the ground reaction force data of the objects are taken as input values to solve the hidden Markov modelfor identifying the gait phase of each object. The gait phase recognition method and system based on the plantar pressure can be widely applied to the technical field of gait detection.

The invention discloses an online gait generation control system for exoskeleton robot opposite side training. The online gait generation control system comprises a healthy side pre-motion data acquisition module, a sensor signal acquisition and processing module, a healthy side and affected side data conversion module and an affected side gait correction module. A gait phase specimen set is established through data acquired by the healthy side pre-motion data acquisition module, healthy side motion data is acquired through the sensor signal acquisition and processing module, and the healthy side and affected side data conversion module predicts affected side motion data by combining the healthy side motion data and the gait phase specimen set. The prediction result is corrected through the affected side gait correction module, and finally, the output positions and interpolation time of an affected side hip joint direct-current servo motor and an affected side knee joint direct-currentservo motor are obtained. According to the invention, an affected side exoskeleton system carries out pre-generation processing on affected side bionic healthy side walking data, and carries out online correction according to gravity center change, so that the naturalness and balance requirements of lower limb rehabilitation training movement of a stroke patient can be met, and a human body is more stable and comfortable to walk.

The invention relates to a plantar pressure measuring device and method. The device comprises a circuit layer and an insole, wherein the circuit layer is arranged in the insole; the circuit layer comprises a flexible printed circuit board and a plurality of pressure sensors connected with the flexible printed circuit board; the pressure sensors include a first sensor, a second sensor, a third sensor, and a fourth sensor. The insole comprises a toe portion, a sole portion, and a heel portion. The first sensor is arranged in the heel portion, the second sensor is arranged on one side of the sole portion, the third sensor is arranged on the other side of the sole portion, and the fourth sensor is arranged in the toe portion. Pressure data when a person walks is calculated and obtained through the four sensors arranged in the toe portion, the sole portion, and the heel portion respectively, and then the gait phase of the person is calculated according to the pressure data. The device has the advantages that the whole device is light, wearing is convenient, and the flexible design better meets dressing requirements of the person, so that the person feels more comfortable when wearing the device; the number of the sensors is small, so that the cost of production is reduced.

The invention provides a gait feature extraction and generation method for ankle joint ligament injury and a system. The gait feature extraction and generation method includes the steps of ankle motion measurement, data preprocessing, gait phase segmentation, gait feature space construction, gait feature generating, authenticity and generative feature correlation evaluation and visual verificationof generative feature validity. The problems of low feature quality and insufficient sample size in an existing medical system are solved. By collecting gait data of a subject and aiming at the anklejoint ligament injury, a small sample data set of an injury group and a control group is established, feature refinement comparison and analysis are carried out based on an anthropometric method, a gait feature space of ankle joint injury is established, gait feature generation and validity verification are carried out, and a large amount of high-quality and efficient feature data support based on anthropometry is provided for research and application in related fields such as intelligent ankle injury diagnosis and decision-making based on big data, precise construction of rehabilitation programs, and development of assisted exoskeleton robots.

A wearable walking assist robot is provided that ensures high walking assistance performance without a complex calculation process by detecting a gait phase based on pressure distribution on feet and performing a corresponding control mode that is set in advance. The wearable walking assist robot includes a sensor unit that senses pressure on the soles of the feet of a wearer and a controller that determines gait phases of both a first leg to be operated and a second leg based on the sensed pressure. Additionally, the controller selects one of a plurality of control modes set in advance based on the determined gait phases and operates a joint-driving unit for the first leg to be operated.

The invention discloses a multi-channel sequential gait analysis algorithm based on direct feature extraction, and relates to the field of gait analysis methods.The method comprises the following steps: shooting gait video information of a plurality of subjects, segmenting all the video information into single separated gait periods, and adjusting the single separated gait periods to be the same length; calculating the distance of the standardized gait parameter Sz, and clustering the marked training data by using a k-nn algorithm and a parameter distance equation; classifying gait phases andreconstructing the gait phases, selecting a point with the maximum correlation coefficient in the current time sequence as a gait event, re-segmenting the gait according to the point, and iterating the above operations again: calculating the correlation coefficient between adjacent gaits according to the gait classification segmented by the gait event obtained by the previous iterative calculation, and finding out the point of the global maximum correlation coefficient as the gait event to optimize the gait classification of the last iteration until the classification converges. The method caneffectively improve the extraction efficiency and the calculation efficiency.

The invention discloses a gait balance training system based on a six-degree-of-freedom parallel platform. The system comprises six-degree-of-freedom platform mechanical hardware, inertial sensing acquisition nodes, an IMU sensor attitude acquisition system, a robot motion control system and a balance training system. The six-degree-of-freedom platform can provide various angle and displacement changes, apply external stimulation, provide acceleration, speed and angular speed stimulation in combination with related algorithms such as trajectory planning and somatosensory simulation of a robotmotion control system, and train the human body balance perception ability from sensory input. The inertia sensing acquisition nodes are combined with an IMU sensor attitude acquisition system to divide human body gait phases and extract human body key gait data such as stride frequency, stride speed and step length. The extracted human gait data can be used for balance ability evaluation and judgment before training and can also be used for guiding the motion form of the robot in the training process. Two training modes of a balance training system are combined, and active training and passive training of the human body are achieved. According to the invention, a multi-degree-of-freedom platform, motion data acquisition and analysis and related algorithms are introduced to realize a complete gait balance training robot, and the human body balance ability and gait characteristics can be evaluated and judged from feeling input. The blank of domestic related research is filled up, and anew gait balance training mode is added.

The invention discloses an exoskeleton-oriented gait phase classification method based on a TCN-HMM. The method comprises the following specific steps: 1, acquiring IMU data; 2, preprocessing the gaitdata acquired in the step 1; 3, constructing a training set and a test set; 4, constructing a hybrid TCN-HMM model, 5, training the hybrid TCNHMM model by using the training set, and 6, classifying the new walking IMU data by using the trained hybrid TCNHMM model. According to the method, the posterior probability of the state is obtained by innovatively utilizing the TCN network, and the emission probability required by the HMM model is obtained by utilizing the posterior probability, so that the hybrid TCNHMM model is formed, and the model organically combines the time characteristics and the space characteristics of the motion data together and discriminates the gait phase information. According to the method, a gait phase classification result with very high accuracy is obtained, andmeanwhile, wrong classification is inhibited.

The invention discloses gait control method, device and equipment for a lower limb wearable robot. The method comprises the steps of obtaining ground interaction force information and joint angle information of the lower limb wearable robot; judging a next gait phase according to the ground interaction force information and the joint angle position information; and substituting a joint angle intoa joint torque model corresponding to the next gait phase to calculate a joint control signal, and performing torque control on the lower limb wearable robot. The next gait phase is judged according to the ground interaction force information and the joint angle information of the lower limb wearable robot, the ground interaction force information and the joint angle information can be collected through a sensor, the cost is low, control signals are calculated according to joint torque models corresponding to different gait phases, and the control method is simple.

The invention discloses a gait phase distinguishing method based on upper-and-lower limb movement information.The gait phase distinguishing method includes the steps that angle information is received through a neck angle sensor, large arm angle sensors, thigh angle sensors and shank angle sensors; the angles and the angular speeds of the shoulder joints and the angles and the angular speeds of the knee joints are obtained through an angle information processing system; the angular speeds of the shoulder joints and the angular speeds of the knee joints are judged to obtain a present gait phase.The gait phase distinguishing method aims at providing a method for setting the mapping relationship between the upper-and-lower limb movement in the human-body gait movement process in the biped walking process.According to the gait phase distinguishing method, the angle information on the horizontal plane, the coronal plane and the sagittal plane is received through the neck angle sensor, the large arm angle sensors, the thigh angle sensors and the shank angle sensors to complete gait phase judgment of the upper limbs and the lower climbs; the structure is simple, and installing is convenient.

The invention discloses a sensing and control system and method for a lower limb joint assisting exoskeleton system. The system comprises a joint angle encoder, a gait phase sensor, a joint angle position controller, and a joint torque controller, wherein the joint angle encoder measures a joint angle position, and transmits an output signal to the gait phase sensor, the joint angle controller andthe joint torque controller; the gait phase sensor performs gait phase judgment according to the joint angle signal and divides the gait phase into a support phase and a swing phase; when the gait phase sensor judges that a robot is currently in the support phase, a joint angle position control mode is adopted; and when the gait phase sensor judges that the robot is currently in the swing phase,a joint torque control mode is adopted. According to the sensing and control system, sensor configuration is simplified, reliability and rapidity of the sensing system are improved, wearable performance of other fittings is not influenced, active assistance is realized, and the man-machine following performance can be improved.

The invention relates to a gait analysis method based on a plantar pressure. The gait analysis method comprises the steps of: (1) collecting plantar pressure signals through four pressure sensors; (2) carrying out gait phase analysis for the collected plantar pressure signals, comparing the total value of pressures collected by the four pressure sensors with a preset threshold value, the planta is in a swing phase when the total value of the pressures collected by the four pressure sensors is less than the preset threshold value, otherwise, the planta is in a supporting phase; (3) judging whether the gait phase analysis result is switched with the previous gait phase analysis result or not according to the plantar pressure signals, and entering into the next step at the point in time if the switching of gait phases happens; (4) carrying out an lower limb movement mode analysis based on the gait phases within the switching time of the gait phases; and (5) judging whether the gait analysis needs to be stopped or not according to a lower limb movement mode analysis result, and returning to the step (1) if not. The gait analysis method based on the plantar pressure, disclosed by the invention, can supply abundant human body movement information for the control of intelligent lower artificial limbs, and can be widely applied to the field of gait mode recognition.

The invention discloses a gait recognition method and device. According to the method and the device, firstly the corresponding pressure state of the pelmatic toe parts, the arch parts and the heel parts under each gait phase is defined; and then the pressure state of the toe parts, the arch parts and the heel parts of the same time is acquired. According to the recognition method, the state of each part is divided into the high pressure state or the low pressure state, and the acquired pressure state of the toe parts, the arch parts and the heel parts of the same time is compared with that of the defined gait phase so that the gait phase of the moment can be judged and the more accurate judgment result can be acquired.