一种基于认知负荷的自适应导纳控制方法及系统
By constructing a multidimensional feature tensor and a hybrid neural network to evaluate the cognitive load index, generating high-frequency smooth control commands, and combining a virtual energy pool and safety constraints, the problems of signal distortion and mechanical shock in existing admittance control are solved, thus achieving stability and safety of the human-machine collaborative system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ANHUI UNIV OF SCI & TECH
- Filing Date
- 2026-05-12
- Publication Date
- 2026-07-17
AI Technical Summary
Existing variable parameter admittance control methods suffer from information loss and phase distortion when processing operator physiological signals, leading to oscillations in cognitive load assessment results. They also suffer from mechanical shock and failure of safety assurance mechanisms.
By constructing a multidimensional feature tensor, a hybrid neural network model is used to evaluate the cognitive load index. Nonlinear smooth mapping and high-order spline interpolation are used to generate high-frequency smooth control commands. Combined with a virtual energy pool and safety constraint strategies, the system stability and security are ensured.
It achieves stable compliance and physical collision safety of human-machine collaborative system under complex working conditions, avoids mechanical shock and safety protection failure, and improves the accuracy of cognitive load assessment and high-frequency stability of system.
Smart Images
Figure CN122194693B_ABST