一种预测控制的人形机器人防摔倒方法及系统
By predicting the trajectory of the zero-torque point and assessing the state of the contact surface, anti-fall pre-adjustment commands are generated, which solves the response lag problem of existing humanoid robot anti-fall control, realizes stable movement in complex terrain, and improves the efficiency and robustness of robot anti-fall control.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TIANJIN SKY STAR TECH DEV CO LTD
- Filing Date
- 2026-04-20
- Publication Date
- 2026-07-17
AI Technical Summary
Existing humanoid robot fall prevention control fails to anticipate and predict terrain environmental features and contact surface friction characteristics, resulting in delayed response, insufficient posture adjustment accuracy, poor stability and robustness, and difficulty in maintaining stable movement in complex terrain.
By acquiring real-time motion and environmental data, the trajectory of the zero-moment point and the state of the contact surface are predicted. Combined with stability boundary assessment, fall prevention pre-adjustment instructions are generated. The center of mass position and trunk posture compensation are derived in reverse, gait planning is optimized, and the plantar joint angle is adjusted.
It enables forward prediction of the robot's motion state, improves the accuracy and responsiveness of fall prevention control, ensures the robot maintains stable movement in complex terrain, and enhances the efficiency and robustness of fall prevention control.
Smart Images
Figure CN122064106B_ABST
Abstract
Citation Information
Patent Citations
Method, device and system for self-adaption balance control of humanoid robot in complex terrain
CN108858208A
Robot dog control method and device, electronic equipment and computer readable medium
CN121625169A