Load-bearing self-adaptive adjusting system and method based on posture recognition

By unifying clock synchronization and multimodal data fusion, combined with dynamic window switching and neural network prediction, the problems of perception stability and prediction lag in existing load adjustment systems are solved, and efficient and stable load adjustment of the exoskeleton system is achieved.

CN120697028AInactive Publication Date: 2025-09-26HAOQIANTU TECHNOLOGY (SHENZHEN) CO LTD
0 Cites 1 Cited by

Patent Information

Application Number
CN202511070375.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-31
Publication Date
2025-09-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing load-regulating systems rely on a single perception modality, resulting in insufficient stability in perception results. They are unable to cope with prediction lags during rapid posture changes and redundant history in slow, stable movements. They lack quantitative modeling of the coupling relationship between load signals and kinematic responses, and lack online evaluation of multimodal fusion consistency.

Method used

Through the synchronous data collection of the inertial measurement unit and the visual camera equipment under the unified clock, after spatial calibration and filtering, the three-axis acceleration, three-axis angular velocity and skeleton image information are integrated to calculate the four dynamic indicators of KLE, LMPL, BDR and SAC. Combined with the constant window timing coding and variable window timing control mechanism, the LSTM or GRU network is used for prediction, and real-time adjustment and feedback correction are carried out through the actuator.

Benefits of technology

It achieves high-precision alignment of visual and inertial data, reduces occlusion drift errors, improves the estimation stability of key joint angular velocity and load signals, quickly responds to high BDR sudden movements and suppresses jitter in the low-speed stable stage, improves the model's real-time response and robust prediction capabilities, and enhances the load comfort of the exoskeleton actuator.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a weight self-adaptive adjusting system and method based on posture recognition, and particularly relates to the technical field of man-machine cooperation and wearable robotics.The method comprises the steps that firstly, multi-modal data are obtained through an IMU and a visual camera device, and PTP clock synchronization, coordinate system calibration and Kalman filtering processing are completed; then, the system measures the action rhythm and the sensing credibility according to indexes such as KLE, LMPL, BDR and SAC, self-adaptive switching is conducted between a constant window sliding window mechanism and a variable window sliding window mechanism, and the window length is calculated in combination with the rate level under the variable window mechanism; the time sequence modeling adopts an LSTM / GRU network supporting variable-length input and a mask mechanism, and outputs an attitude evolution trend, load response pre-judgment and sudden action risks; and the control end generates a feed-forward adjustment instruction of multi-actuator cooperation based on a prediction result, and realizes self-correction and individualized parameter self-adaption through feedback monitoring.
Need to check novelty before this filing date? Find Prior Art