20 results about "Stride length" patented technology

The invention relates to the technical field of blind guiding robot gait stability control, and particularly discloses a blind guiding robot gait stability control method fusing IMU and foot end force perception, and the method comprises the steps: collecting three-dimensional point cloud data through a head depth camera, analyzing topographic features, and generating topographic safety confidence; the physical rigidity of the dielectric elastomer ankle joint is further adjusted; in the single-foot supporting stage, plantar pressure and trunk inertia data are synchronously collected, a real-time plantar interaction snapshot is generated, and when the instability risk is detected, the ankle joint rigidity is immediately locked to resist abnormal rotation; then, the plantar pressure abnormal direction is recognized, and the mass center compensation adjustment amount is calculated to stabilize the body posture; and finally, according to the amplitude and frequency of mass center compensation, evaluating the matching degree of the gait strategy and the road condition, dynamically adjusting the stride and the leg lifting height, and generating optimized gait parameters. The invention aims to improve the walking stability and safety of the robot in a complex environment.

A controlling method of an electronic apparatus, the method comprising obtaining main motion data and sub motion data, obtaining synthetic data by combining the main motion data and the sub motion data, obtaining a threshold value based on a magnitude of a signal waveform of the synthetic data and a running mean of the synthetic data, identifying a plurality of critical points in the synthetic data based on the threshold value, identifying signal patterns, based on the plurality of critical points, in each axis of a plurality of axes in the main motion data of a 3-Dimension (3D) coordinate system, obtaining at least one similarity in the signal patterns based on a plurality of inter-axis features extracted from the synthetic data, obtaining a degree of symmetry between each axis of the plurality of axes based on the at least one similarity, and obtaining a user's movement information based on the degree of symmetry and the synthetic data.

Disclosed is a gait analysis device using artificial intelligence (AI) technology, according to some embodiments of the present invention. The gait analysis device may comprise: a camera unit for capturing an image of the gait of a target user in response to a user interaction through a display unit; a gait analysis unit for generating a gait analysis result obtained by analyzing the gait of the target user on the basis of the captured gait image, wherein the gait analysis result includes at least one of a stride length, a gait speed, a swing angle of both arms, an upper body angle, a hip joint angle of both legs, or a knee angle of the target user; and the display unit for outputting the gait analysis result.

A system and method for collecting and analyzing real-time walking and balance data from mobile device users through an opt-in mechanism integrated with smartphone operating systems (iOS and Android). Users voluntarily share their mobility data, including gait speed, stride length, and balance stability, which is anonymized and analyzed using machine learning algorithms. The system provides personalized health insights, such as real-time warnings about fall risks, and generates population-level health trend reports. Aggregated, anonymized data helps public health organizations and healthcare providers identify emerging trends, such as regional increases in fall risks or correlations between medication use and mobility issues. This dual-purpose system bridges individual health monitoring and population-level public health analysis, offering proactive interventions to improve well-being. The system ensures privacy compliance while enabling early detection and prevention of health risks for both individuals and broader communities.

The present invention relates to a virtual reality-based task-oriented gait training system and method, in which the virtual reality-based task-oriented gait training system according to the present invention includes a gait detection unit that detects a walking movement of a trainee, a projector unit that projects virtual walking environment information for inducing a gait training of the trainee, and a control unit that executes a walking training program to change the virtual walking environment information according to the detected walking movement of the trainee, in which the virtual walking environment information includes a background constructing a virtual space and a walking training object appearing in the virtual space, and the gait training object includes a virtual obstacle for disturbing the walking movement of the trainee according to a preset level of difficulty or a gait inducing object for inducing gait of the trainee with a predetermined stride length. According to the present invention, there is an advantage that the trainee can perform gait training with interest and receive trainee-customized treatments through real-time interaction in virtual reality implemented closer to a real ground walking environment.

Disclosed are example embodiments of systems and methods for exercise including an exercise machine including a multiple directional force component configured to apply a multiple directional force to an exercise machine-human body interface, the multiple directional force component further configured to provide a divergent intensity to the exercise machine-human body interface to provide the human body with a resistance during a physical exercise and an artificial intelligence (AI) component configured to control the multiple directional force component. In an example, the AI component may control the multiple directional force component based on morphological characteristics and variability of running speed parameters including at least one of stride length, stride frequency, explosive drive force, and arm drive.

The present disclosure relates to an apparatus and a method for estimating a user's height by using walking information, wherein the user's height may be estimated by collecting walking information of the user and applying the walking information of the user to a height estimation model. The operation of collecting the walking information of the user comprises the operations of: acquiring inertial information, atmospheric pressure information, and GPS information; determining whether it is in a state in which the walking information of the user can be accurately collected; and when it is determined, as a result of the determination, that the walking information of the user can be accurately collected, estimating a step count, walking speed consistency, undulation information indicating vertical movement that occurs during walking, and a stride length by using at least one of the inertial information, the atmospheric pressure information, and the GPS information.

This walking assist device incorporates a function to adjust the heel height based on the user's walking pattern, thereby suppressing user discomfort from changing heel height while simultaneously improving stride length and walking speed, and reducing fatigue. [Solution] The system is configured to acquire the wearer's walking state and control the heel height adjustment unit 5 located on the sole of the wearer's shoe, thereby adjusting the heel height, which is the relative height of the heel to the toes on the sole of the wearer's foot, based on the wearer's walking state.

The present invention seeks to protect a pedestrian dead reckoning method based on pedestrian motion state recognition. In view of the fact that the traditional pedestrian dead reckoning (PDR) algorithm can only be used for a single state of normal walking and is difficult to meet the needs of actual applications, an improved PDR algorithm based on human motion state recognition is proposed. The algorithm divides the pedestrian motion mode into two states: walking and running. It fully considers the relationship between the peak acceleration and the motion state during the pedestrian motion process, obtains the peak acceleration under different motion states through experiments, and thus sets dynamic thresholds to achieve step detection and stride length estimation under different states. The improved PDR algorithm is applied to pedestrian positioning: the motion data of pedestrians while walking is obtained by the micro inertial measurement unit (IMU), and the improved peak detection method is used to perform step detection and state recognition on pedestrians. The step length is estimated using an adaptive step length estimation formula according to the pedestrian's motion state. Finally, the pedestrian's position information is obtained in combination with the calculated heading.

A control method of a control device for correcting walking habits according to one embodiment includes obtaining a user's body information, obtaining an arm swing angle value and a sole landing angle value while the user walks, calculating a linked reference stride length value based on the arm swing angle value and the sole landing angle value, obtaining the user's heel width value, calculating a gap value between left and right inner sides of soles of both feet based on the user's heel width value, obtaining a forward hand direction value while the user walks, calculating a linked reference direction value based on the gap value between the left and right inner sides of the soles of both feet and the forward hand direction value, and providing walking habit correction information based on the linked reference stride length value and the linked reference direction value.

This invention discloses a fully driven, multi-degree-of-freedom legged wall-climbing robot propulsion system, relating to the technical field of legged adhesive robots. It solves the problems of limited mobility and weak cross-wall transfer ability in adhesive legged robots during wall climbing. The system includes a torso module, multi-degree-of-freedom leg components, an air system, and a main control module. Each corner of the torso module is equipped with a multi-degree-of-freedom leg component for support and walking. The main control module controls the operation of the air system and the multi-degree-of-freedom leg components. The air system enables multiple multi-degree-of-freedom leg components to grip the ground. In this invention, when moving on a single vertical wall, it can achieve a larger stride length and more flexible turning methods. When transferring across walls, it ensures that at least three suction cups are simultaneously stressed, greatly improving safety during wall transfer. Furthermore, the transfer between walls is not subject to the angle between them.

The invention discloses a path planning method and device adaptive to physiological needs of children, a medium and a product. The method comprises the following steps: acquiring movement track data of the children in a target area; constructing a walking road network of the child according to the movement track data and a preset target location; identifying a child activity hot spot area based on the activity track data, and performing two-stage division on each path in the walking road network in combination with a preset child stride to generate a plurality of child-friendly road sections; calling a preset walking evaluation index system to score each child-friendly road section, and rejecting walking paths including road sections lower than a standard score to obtain a target path set; and adopting a weighted summation algorithm to predict the comprehensive score of each target path according to the road section score, and selecting the path with the highest score as the optimal child walking path. A safe, interesting and comfortable walking environment can be created for children, and the walking experience and safety of the children in the target area are improved.

An elliptical trainer with adjustable stride length, characterized by the fact that it includes: a machine frame; a crank which is rotatably arranged on the left and right sides of the rear end of the machine frame; Each a rocker arm, rotatably arranged on the left and right sides of the front end of the machine frame; an adjustable tube that extends longitudinally from front to back and is articulated to the rocker arm, thereby forming a first pivot point; a pedal tube extending longitudinally from front to back, with one end connected to the adjustment tube and the other end pivotally connected to the crank, a second pivot point is formed, with a footboard that can be moved along its longitudinal direction on the tread tube; a connecting rod located below the adjustment tube, with one end pivotally connected to the rocker lever and the other end to the footboard; wherein a stride length adjustment and locking structure is provided at the connection between the adjustment tube and the pedal tube, which serves to change the distance between the first and the second joint point in order to enable a stride length adjustment.

The invention discloses a video visible light-infrared pedestrian re-identification method based on human body analysis, and belongs to the technical field of pedestrian re-identification. According to the method, modal-invariant body shape features are extracted through human body analysis, high-order structure information of different parts of a pedestrian is modeled, and a similarity orthogonal decomposition mechanism is introduced, so that complementation and collaboration of appearance and body shape features are realized. Compared with the traditional method which only depends on appearance information which is easily influenced by camouflage, visual angle and illumination, the system provided by the invention models fine-grained body type dynamic characteristics representing individual height, weight, stride length, gravity center movement and the like. On the basis, appearance and body shape features are decoupled and fused, so that the model has discriminative texture expression ability and robust structure recognition ability at the same time, and the cross-modal video pedestrian retrieval precision is remarkably improved. Experimental results verify the excellent performance of the method in cross-equipment and all-weather pedestrian matching tasks in a complex monitoring environment, and richer and more stable identity recognition clues are provided for practical application.

This invention provides a front-mounted elliptical trainer with a lifting function, including a frame. The frame is equipped with a flywheel system, a multi-link rotating mechanism, a lifting mechanism, and protective components. The flywheel system is located at the front of the frame. The multi-link rotating mechanism cooperates with the flywheel system and the lifting mechanism. The lifting mechanism is located at the rear of the frame. Protective components are provided on the outside of the flywheel system and at the front and rear ends of the frame. This invention allows adjustment of the incline of the elliptical trainer by adjusting the position of the multi-link rotating mechanism through the lifting mechanism. This allows for changes in stride length and the angle of force application. Different inclines can exercise different lower limb muscle groups. The protective components cover and shield the flywheel system and the front and rear of the frame to prevent injury to the user and improve safety.

This invention discloses an interactive sports training assessment method and system, belonging to the field of sports training assessment technology. The invention utilizes a data acquisition module to collect athletes' physical condition data, stride length data, stride frequency data, and center of gravity shift data in real time. Then, a data processing module sequentially calculates and outputs a stride length score (BH), an overall movement quality score (ZT), and a new ideal stride length (LB). new Using the results feedback and adjustment module, the new ideal stride length LB is adjusted. new The results are compared with the ideal stride length (LB) obtained from the stride length data, and the correction is evaluated. The new ideal stride length (LB) is then replaced with the new ideal stride length (LB) in the next training session. new This invention enables athletes to make targeted improvements, and reasonable stride length, coordinated stride frequency and stable body center control help improve running efficiency. The ideal stride length (LB) is optimized in real time based on the overall running motion quality, so that training can be flexibly interactive and adjusted according to the athlete's real-time performance, thereby continuously improving training effect and athletic performance.

The invention discloses an interactive physical training evaluation method and system, and belongs to the technical field of physical training evaluation.A data acquisition module is used for acquiring physical condition data, stride data, stride frequency data and gravity center shift data of athletes in real time, and then a data processing module is used for processing the data; and sequentially calculating and outputting a stride score BH, an overall action quality score ZT and a new ideal stride LBnew, performing result comparison and correction evaluation on the new ideal stride LBnew and an ideal stride LB of a stride data result by using a result feedback and adjustment module, and replacing the ideal stride LB with the new ideal stride LBnew during next training, so as to obtain a new ideal stride. According to the method, the athletes can be improved in a targeted mode, reasonable stride, coordinated stride frequency and stable body gravity center control are beneficial for improving running efficiency, the ideal stride LB is optimized in real time according to the overall running action quality, flexible interaction and adjustment can be conducted on training according to real-time performance of the athletes, and the training efficiency is improved. Therefore, the training effect and the exercise performance are continuously improved.

An elliptical machine with adjustable stride length and pedal elevation angle, aiming to enhance functionality and users' exercise experience. In particular, it can maintain stability under high-intensity use, making it suitable for long-term use in gyms and at home. The elliptical machine includes a chassis unit and an upright frame unit. The pedal trajectory can be adjusted through a stride adjustment mechanism, providing large-stride and small-stride exercise modes. At the same time, the front-rear height difference of the pedals can be changed through a pedal elevation angle adjustment mechanism to simulate the movement trajectories on different terrains. In addition, the frame design improves the ability of the equipment to remain stable during the adjustment process, and the pressurizing assembly is used to prevent the transmission belt from slipping, ensuring smooth exercise.

The present application is applicable to the field of indoor positioning technology and provides a stride length estimation method based on LSTM, comprising: collecting data from a head inertial sensor and a foot inertial sensor based on a preset sampling frequency, and performing time alignment and step alignment on the data to obtain multi-source motion data, wherein the multi-source motion data includes head motion data and foot motion data; obtaining a head feature vector based on the head motion data, and obtaining a stride length feature vector based on the foot motion data; constructing a stride length estimation model based on the head feature matrix and the stride length feature vector through a long short-term memory neural network, and obtaining a stride length estimation value through the step length estimation model. The present application improves the accuracy and robustness of stride length estimation.

The application discloses a video visible light-infrared pedestrian re-identification method based on human body analysis, and belongs to the technical field of pedestrian re-identification. The method extracts the body shape features which are invariant to modalities through human body analysis, models the high-order structure information of different parts of the pedestrian, and introduces a similarity orthogonal decomposition mechanism to make the appearance and body shape features complementary and collaborative. Compared with the traditional method which only relies on the appearance information which is easily affected by camouflage, view angle and illumination, the system models the fine-grained body dynamic features such as height, length, girth, stride length and center of gravity movement of the individual. On this basis, the appearance and body shape features are decoupled and fused, so that the model has both discriminative texture expression ability and robust structure recognition ability, thereby significantly improving the cross-modal video pedestrian retrieval accuracy. The experimental results verify that the application has superior performance in the cross-device and all-weather pedestrian matching task in the complex monitoring environment, and provides more abundant and stable identity recognition clues for practical application.