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 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 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.

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 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.