面向复杂环境的机器人自适应运动控制方法及装置
By identifying environmental conditions and switching control strategies, and using depth images and body sensor data to generate precise motion control commands, the problem of unstable movement of rescue robots in complex disaster environments has been solved, improving the stability and adaptability of the robots.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV OF SCI & TECH OF CHINA
- Filing Date
- 2026-04-27
- Publication Date
- 2026-07-17
AI Technical Summary
Existing rescue robots have poor motion control stability and adaptability in complex disaster environments. In particular, they are unable to obtain accurate motion control commands in extreme working conditions without vision, and they cannot adaptively adjust control strategies to cope with dynamic changes in the environment.
By acquiring depth image data from a depth camera, the system identifies environmental conditions and switches control strategies based on these conditions: it uses proprioceptive control in cases of no vision, visual perception control in cases of partial visibility, and multimodal fusion control in cases of time-varying visibility. It also combines reinforcement learning and multilayer perceptron networks to generate precise motion control commands.
It enables stable autonomous movement of robots in complex environments, improves the stability and adaptability of motion control, and enhances survival efficiency and rescue capabilities in disaster environments.
Smart Images
Figure CN122086030B_ABST