213 results about "Gait (human)" patented technology

The invention relates to a Fourier descriptor and gait energy image fusion feature-based gait identification method. The method comprises the steps of performing graying preprocessing on a single frame of image, updating a background in real time by using a Gaussian mixture model, and obtaining a foreground through a background subtraction method; performing binarization and morphological processing on each frame, obtaining a minimum enclosing rectangle of a moving human body, performing normalization to a same height, and obtaining a gait cycle and key 5 frames according to cyclic variation of a height-width ratio of the minimum enclosing rectangle; extracting low-frequency parts of Fourier descriptors of the key 5 frames to serve as features I; centralizing all frames in the cycle to obtain a gait energy image, and performing dimension reduction through principal component analysis to serve as features II; and fusing the features I and II and performing identification by adopting a support vector machine. According to the method, the judgment whether a current human behavior is abnormal or not can be realized; the background is accurately modeled by using the Gaussian mixture model, and relatively good real-time property is achieved; and the used fused feature has strong representability and robustness, so that the abnormal gait identification rate can be effectively increased.

The invention discloses an active-passive type two-degrees-of freedom ankle joint prosthesis, comprising a carbon fiber energy storage sole, a motor, a speed reducer, a motor fixing supporting seat, a belt pulley transmission device, a carbon fiber pipe, a ball screw, an energy storage springs, joint bearings, energy storage rubber rings and joint supporting seats, wherein the carbon fiber energy storage sole is connected with the carbon fiber pipe through the joint supporting seats; the motor fixing supporting seat is connected with the carbon fiber pipe through an active pin; the motor is fixedly arranged on one end of the motor fixing supporting seat; the ball screw is fixedly arranged on the other end of the motor fixing supporting seat; two ends of the motor fixing supporting seat are connected by the belt pulley transmission device; the energy storage springs areis connected with a ball screw nut; and the energy storage rubber rings are connected with the joint bearings and the joint supporting seats through a shaft. The ankle joint prosthesis provided by the invention not only can completely provide required energy for human gait, but also can adapt to various landforms; in addition, the ankle joint prosthesis can completely imitate movement angles of a human ankle joint on a sagittal plane or a coronal plane; and therefore, the normal walking requirement of an amputation patient can be satisfied better.

The invention relates to an active stroke lower limb rehabilitation robot control method based on healthy side and affected side coupling. The method comprises the following steps that: a characteristic pathological gait correction strategy based on a characteristic pathological gait model is formulated; after the limbs of the patient begin to move, multi-sensor signals of the lower limbs of the healthy side of the patient are collected, and multi-sensor signal processing is conducted; constructing of a multi-sensor information fusion vector is carried out; the motion intention of the patientis acquired; the motion intention and the characteristic pathological gait correction strategy are coupled to obtain healthy side-affected side coupling information, and the healthy side-affected sidecoupling information is transmitted to a human body-rehabilitation robot closed-loop controller, so that the system function of the rehabilitation robot is controlled, and man-machine coordinated operation is guaranteed. According to the invention, feedback type motion replanning and control integration are carried out through accurate identification of the healthy side leg motion intention, coupling regulation and control of a man-machine system are achieved, and finally, the goal of healthy side and affected side coupling training is achieved.

The invention provides a lower limb gait rehabilitation training trolley based on a parallel mechanism. The lower limb gait rehabilitation training trolley comprises four parts including a trolley supporting frame, the parallel mechanism, wearable rehabilitation shoes and a body position lifting device. According to the lower limb gait rehabilitation training trolley, the parallel mechanism is introduced into the whole lower limb rehabilitation process, the ankle joint of a human body is driven by utilizing the characteristic of three-translation of a movable platform, so that the whole lowerlimbs are driven to perform rehabilitation training, common gait rehabilitation training can be carried out in the sagittal plane of the human body, furthermore, rehabilitation training can be carriedout in any plane perpendicular to the horizontal plane, the diversity of lower limb rehabilitation training actions is improved, only the ankle joint of the human body is constrained in the whole rehabilitation training process, the knee joint and the hip joint are not constrained, and the comfort of the rehabilitation training process is greatly improved. The whole device is provided with the body position lifting device, so that the device can be conveniently worn by a patient and meanwhile can well adapt to patients with different body types.

The invention discloses lower limb rehabilitation training equipment and a biped end executor thereof. The biped end executor comprises two sets of execution devices which have the same structure andare arranged in parallel; each execution device comprises a linear motion mechanism used for achieving forward and backward motion of the corresponding foot, a lifting mechanism connected with the linear motion mechanism and used for achieving height lifting of the foot, and an ankle joint rotating mechanism connected with the lifting mechanism and used for achieving ankle joint rotation. The lower limb rehabilitation training equipment comprises a supporting frame, a weight reduction supporting mechanism used for carrying out weight reduction control on a human body during training, a biped end executor used for carrying out gait training, and a pelvis pose adjusting mechanism used for carrying out cooperative adjustment on a position and a pose of the pelvis of the human body during gaittraining of the lower limbs of the human body so as to achieve balance. The lower limb joint movement can be realized, and the pelvis cooperative movement can also be realized; and the walking capability and the balance capability of a patient can be effectively improved.

The invention relates to a semi-passive light-weight lower limb exoskeleton. The lower limb exoskeleton comprises a waist assembly and a pair of lower limb motion mechanisms arranged at the two ends of the waist assembly respectively; the waist assembly comprises a first baffle and a second baffle hinged to the first baffle, and the two lower limb motion mechanisms are connected with the first baffle and the second baffle and each comprises a hip joint driving assembly, a thigh assembly, a knee joint assembly, a shank assembly and an ankle assembly which are sequentially arranged on the corresponding waist assembly from top to bottom. Compared with the prior art, the light-weight and submissive design and the semi-passive driving mode are adopted, only the hip joints are driven actively, the knee joints and the ankle joints adopt the passive freedom degree, own energy of the human body is used fully, the gait meets that of the normal human body, the weight and size of the lower limb exoskeleton are obviously reduced, and the semi-passive light-weight lower limb exoskeleton is suitable for lower limb rehabilitation and assisted walk of people with light lower limb dysfunction.

The invention discloses a new abnormal gait analysis method and system. The method comprises steps that S1, a moving human target is tracked, footprints of three consecutive steps in an image are corrected to acquire the image pixel position (ui<M>, vi<M>) of the corrected footprints in a straight line; S2, according to the image pixel position (ui<M>, vi<M>) of the corrected footprints, the observation distance of two adjacent corrected footprints in the image and observation step size ratios A and B between two adjacent steps after correction are calculated; S3, step sizes of an unilateral leg are supposed to be basically identical, namely L3<Real>=L1<Real>, and the ratio of the actual step size L2<Real> of a second step to the actual step size L1<Real> of a first step is calculated; andS4, clustering statistics of adjacent step size ratios of a monitored object is carried out, and the real-time adjacent step size ratio of the monitored object is compared with a clustering center ofthe clustering result. The method is advantaged in that the application scope is wider, the method is suitable for general straight line conditions, compared with a no-correction gait method and an MGM system, estimation accuracy of the adjacent step size ratio is higher, and the error is reduced.

The invention provides a boosted exoskeleton motion intent and pace planning method based on multi-sensing information. The method comprises the following steps: S1. acquiring vertical-direction acceleration signals of legs of a human body and oxygen consumption data of the human body, and acquiring surface electromyographic signals from muscles of the legs; S2. taking characteristic parameters ofthe acceleration signals, characteristic parameters of the oxygen consumption data and characteristic parameters of the surface electromyographic signals as inputs of a training model; and S3. establishing an LSTM deep learning network so as to obtain a corresponding relationship between the characteristic parameters of the surface electromyographic signals and a pace plan, a corresponding relationship between the characteristic parameters of the surface electromyographic signals and an exoskeleton boosting grade, and a corresponding relationship between the characteristic parameters of the surface electromyographic signals and a motion mode, and taking the boosting grade, the motion mode and the pace plan as outputs of the model. According to the method provided by the invention, key parameters required by a boosted exoskeleton control system can be comprehensively presented, the resolving efficiency of real-time intents is increased, and rapid and accurate sharing, decision making and executing can be achieved.

The invention discloses a sole capable of improving boosting force. The sole comprises at least one elastic layer and at least one supporting layer, wherein the elastic layer and the supporting layerhave different elasticity and hardness, and are arranged in an overlapped mode to form a sole body; a hollow structure is arranged at the middle foot portion of the sole body; and the hollow structureenables the middle foot portion of the sole body to generate elastic deformation. According to the sole capable of improving the boosting force and a shoe in the invention, the whole sole is providedwith a linkage type force feedback mechanism, energy generated when a wearer treads the ground in every step can be recycled and released again when the wearer steps on the ground, and therefore, theboosting force of the sole is improved; the sole is good in supporting effect, better conforms to the movement gait of the foot of the human body, feels comfortable and has good elastic performance;and the shock absorption performance of the sole is good, and better buffer protection can be provided for the wearer.

The invention discloses a wearable Tai Chi movement gait evaluating and training system based on a cloud platform. The system comprises a gait parameter collecting module, a gait parameter processingmodule, a gait movement function evaluating and training module and a cloud platform module. An attitude sensor, a plantar pressure sensor and a surface electromyography sensor are adopted to acquiregait data in Tai Chi movement of a human body in real time, and transverse and longitudinal comparison of user Tai Chi movement gait training is realized based on a cloud platform data fusion algorithm. Meanwhile, a big data deep mining algorithm is adopted to realize reverse analysis from electromyographic signals to gait specifications. Based on the human-computer interaction function of multiple users, clear digital visual guidance can be provided for Tai Chi teaching, and objective quantitative reference can also be provided for scoring of competitive Tai Chi competition judges. Through the packaging integration design of the devices, the system is portable, wearable, easy to use and reliable, and has good market value.

The invention relates to a regeneration power mechanical skeleton system. The regeneration power mechanical skeleton system is designed to solve the technical problems that existing like products are in shortage of data signal pre-catching and collecting, real-time monitoring, restoration gait position information and feedback compensation amount. The regeneration power mechanical skeleton system comprises a mechanical system and a data collection system. The mechanical system comprises a lower limb servo mechanism and a connection mechanism. The regeneration power mechanical skeleton system is characterized in that according to the mechanical system, a rotational joint between a hip joint connection plate and a thigh plate and a rotational joint between the thigh plate and a shank plate are each provided with a hall angle sensor; the hall angle sensors are used for collecting ground angle signals of the lower limbs and the waist of the human body and obtaining angle values of all the joints through foot angle difference calculation, the joint angles and torque signals of the human body are pre-caught and stored in a control system of the mechanical skeleton system, and a user independently selects a control pattern; and the posture of the human body is monitored in real time through the control system, and limb position information and the feedback compensation amount are provided for the human body gait restoration control process.

The invention relates to the field of physical exercise analysis, human body gait research, orthopedic rehabilitation walking function evaluation and the like, and discloses a device and method for onsite static calibration of a three-dimensional force platform. The method comprises the steps of firstly carrying out onsite calibration on the three-dimensional force platform by using the device for the onsite static calibration of the three-dimensional force platform, then inputting various parameters after the calibration into a formula of a calibration algorithm to obtain a calibration coefficient C, and finally carrying out verification on a calibration result. The device and method for the onsite static calibration of the three-dimensional force platform can calculate the calibration coefficient on site through the formula, enables factory returning for recalibration to be needless, solve the problem of inaccurate calibration coefficients caused by the using period of equipment, improper mounting or collision, and have certain market prospects and application value.

The invention discloses a system and method for judging human body motion behaviors based on an intelligent shoe. The system comprises the intelligent shoe and a data processing module; the intelligent shoe comprises a sole, an insole, an inertia measuring module, a pressure measuring module, a power supply module and a wireless micro-control module; the inertia measuring module comprises first tofourth inertia measuring units disposed within the sole; the pressure measuring module comprises first to tenth pressure sensors disposed within the insole. When in operation, the wireless micro-control module provides a clock signal, and the measurement data of the first to fourth six-axis inertia measuring units and the first to tenth pressure sensors is wirelessly transmitted to the data processing center; the data processing center extracts the human body motion mechanics data according to the received data, and judges the human body motion behaviors. According to the system and method for judging human body motion behaviors based on the intelligent shoe, the gait parameters such as the posture of the foot, the pressure of the sole and the like can be measured when the human body is in motion, the gait data can be analyzed, and the motion behaviors can be detected and identified.

The invention discloses a gait recognition and intention perception method, and the method comprises the steps: employing a data collection system which is used for collecting the plantar pressure, ankle joint acceleration and angular velocity information; the method comprises the steps of establishing an actual measurement database by utilizing actual data information acquired by a data acquisition system; performing human body model motion simulation by utilizing AnyBody software to obtain corresponding relations among plantar pressure, ankle joint acceleration, angular velocity informationand corresponding human body postures, and establishing a simulation database; estimating a mapping relation between an actual measurement database and a simulation database through feature extractionand feature matching, gait recognition and intention sensing are performed by using a convolutional neural network algorithm, and the current posture of a human body can be obtained under the condition that the posture of the human body at a place is not clearly reflected, so that the purposes of gait recognition and human body intention sensing are achieved. The problems that in the prior art, the pressure collection range is not comprehensive, the feature is single, the human body posture cannot be predicted, and the real-time recognition accuracy and speed are low are solved.

The invention discloses an active and passive hybrid type artificial limb knee joint. The knee joint comprises a supporting and fixing assembly, a motor, an artificial limb shank fixing part, a synchronous pulley assembly, a lead screw assembly, a damping cylinder, six self-holding electromagnets, a connecting rod assembly and an on-knee socket fixing part. Switching of active and passive modes isperformed by telescopic rod structures controlled by the self-holding electromagnet, by use of a passive telescopic rod, a multi-rod structure in the passive mode can simulate human gaits, by use ofthe active telescopic rod structure, rotation of a thigh fixing part can have larger force arm during active drive, the passive structure adopts the multi-rod structure of the damping cylinder and canbetter simulate human gaits, and the active drive structure adopts the motor to drive the synchronous pulleys so as to drive lead screw drive. The knee joint is precise in drive and convenient to maintain.

The application provides an ankle joint boosting exoskeleton. The ankle joint boosting exoskeleton comprises a foot supporting plate, an ankle wearing component, a thigh wearing component and an electromagnetic driving mechanism, wherein the bottom of the ankle wearing component is fixedly connected with the foot supporting plate, the thigh wearing component is rotatably connected with the top ofthe ankle wearing component, and the electromagnetic driving mechanism is used for driving the ankle wearing component to rotate relative to the thigh wearing component; and the electromagnetic driving mechanism comprises a guiding cylinder, a driving rod slidably mounted in the guiding cylinder, a magnet member for driving the driving rod to move and an electromagnetic coil for driving the magnetmember to move along the guiding cylinder, the electromagnetic coil sleeves the outer side of the guiding cylinder, the magnet member is located in the electromagnetic coil, one end of the driving rod is arranged in the guiding cylinder and is connected with the magnet member, and the other end of the driving rod extends out of the guiding cylinder. According to the ankle joint boosting exoskeleton provided by the application, the electromagnetic driving mechanism is used for driving the ankle wearing component to rotate relative to the thigh wearing component, thus, the boosting response speed is high, the waiting time is shortened, a boosting force can be provided timely when a foot of a user thrusts against the ground, and lower limbs of a human body can keep natural-pace walking.

The invention discloses a gait recognition method and a gait evaluation system based on a human body key point detection algorithm. The method comprises the following steps: step 1, carrying out key point detection on each frame in a 3m standing walking experiment video shot by a single camera from the side surface of a human body, and extracting position change information of key points along with time so as to obtain a key point sequence; step 2, selecting a key frame for the video according to the key point sequence; wherein the key frame is used as a demarcation point of different actionsin the video; and step 3, extracting gait parameters according to the key point sequence in the video and the selected key frame. Through key point detection, key frames capable of serving as demarcation points of different actions in a video are obtained, and then gait parameter estimation is carried out. According to the method, automatic analysis is carried out by using an algorithm, and the consistency of gait evaluation is ensured.

The invention discloses a man-machine interaction intelligent control method of a load maneuvering exoskeleton and an exoskeleton system. The method comprises the following steps: firstly, modeling a human body and the load maneuvering exoskeleton into a five-connecting-rod model consisting of a trunk, a left thigh, a right thigh, a left shank and a right shank; dividing the five-connecting-rod model into a supporting leg model and a swinging leg model, and respectively establishing kinetic equations of the two models by utilizing a Lagrange motion equation; and then designing a hybrid control method combining position control and AIA control based on a tracking differentiator, applying the position control to the supporting leg model in a gait period, enabling the joint angle of an exoskeleton to track the joint angle of the human body in real time, applying the AIA control based on the tracking differentiator to the swinging leg model, enabling the exoskeleton to adapt to the human body movement and environment of a wearer by self, achieving the two control methods alternately according to a supporting phase and a swinging phase of the gait cycle, so that the exoskeleton tracks the position of the human body in real time. Coordinated movement of the exoskeleton and the human body can be achieved.

The invention provides a power-assisted ankle joint exoskeleton, comprising an ankle wearing assembly connected with a foot boots, a leg wearing assembly connected with a shank and a power assisting device, wherein the ankle wearing assembly is rotationally connected with the leg wearing assembly through a pivot; the power assisting device comprises a Bowden cable used for driving the ankle wearing assembly and the leg wearing assembly to rotate relatively, a power device used for driving the Bowden cable to stretch, and a waistband used for binding the power device to the waist of a user; andwhen a human body walks, the power device drives a steel wire rope of the Bowden cable, and the steel wire rope pulls the ankle wearing assembly to rotate relative to the leg wearing assembly under the guidance of a wire sleeve, so assistance is provided for plantar flexion movement of an ankle joint of a user and the user is assisted in walking normally. The power-assisted ankle joint exoskeleton provided by the invention is compact in structure, small in size and light in weight, the load of the lower limb of the user at the ankle joint is reduced, influence on human motion is small, and the user can keep natural gait and walk normally.

The invention relates to a flexible functional outwear body for assisting lower limbs. The flexible functional outwear body is worn on the lower limbs of a human body and can assist one or two of theanteflexion motion and rear protraction motion of hip joints and the toe bending motion and back stretching motion of ankle joints, totally eight assisting manners are achieved, and the proper assisting manner is selected according to the needs of healthy people or lower limb dyskinesia patients. The functional outwear body comprises a bottom layer outwear, a waist ring belt, a thigh ring belt, acrus ring belt, a foot ring belt, a Bowen cable unit, an inertial sensor, a tension sensor and the like. The corresponding ring belt is dragged by the Bowen cable unit, and assisting force is transmitted to the hip joints or the ankle joints. The functional outwear body has the advantages of being light, good in man-machine compatibility and the like, and meanwhile gait detecting and assisting force measuring functions are integrated; the positions of an upper anchoring point fixing unit and a lower anchoring point fixing accessory are replaced, the placing position of a Bowen cable is changed, and therefore different kinds of expected joint motion are assisted.

The invention discloses a gait recognition method, a device, equipment and a readable storage medium. The method comprises the following steps: acquiring detection data of a sensor which is arranged at a leg of a gait recognition target; according to the detection data, extracting the angle of the leg relative to the ground; and according to the angle, recognizing current gaits of the leg with thesensor. Triaxial posture angles and acceleration speeds of the leg can be detected by using the sensor, the angle of an abscissa axis of the leg relative to the ground can be extracted through detection data of an IMU (inertial measurement unit), then a current movement state of the human leg with the sensor can be judged, and furthermore, current gaits can be recognized. Compared with a gait recognition method depending on sole pressure, the gait recognition method is accurate in gait recognition based on angles.