Wearable Power Assist Robot Interference Force Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power assist systems struggle to accurately measure interference forces between a user and a robot, limiting the user's ability to freely manipulate the robot according to their intention, especially when force sensor measurements are difficult.
Innovation Solution
A power assist system that includes a disturbance observer and an Echo State Network (ESN) learning model to estimate interference forces, using a reservoir computing technique with stochastically assigned weights, allowing for high-accuracy admittance control and intention-based power assist.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a force sensor is used to measure interference force, then measurement accuracy is improved, but device complexity and difficulty of detection increase
Solution Approach 1:
The patent introduces an intermediary estimation system comprising a disturbance observer and ESN learning model that indirectly estimates interference force through robot state observations (position, velocity, acceleration), avoiding the need for direct force sensor measurement while achieving accurate interference force detection
Solution Approach 2:
The patent replaces the mechanical force sensor measurement system with a computational estimation system using disturbance observer and Echo State Network learning model, substituting physical measurement with mathematical modeling and machine learning-based inference
2Stability of the object's composition
If AAN control follows a predetermined target trajectory, then control stability is improved, but user freedom of manipulation deteriorates
Solution Approach 1:
The patent implements feedback control by continuously estimating interference force from user intention and adjusting robot assistance accordingly, allowing the system to adapt to user needs while maintaining stable control through the admittance control mechanism
Solution Approach 2:
The patent transitions from static predetermined trajectory control to dynamic intention-based control, where the target trajectory is continuously adjusted based on real-time estimation of user intention through the ESN learning model, enabling both stability and user freedom
Data Source
AI summary
A power assist system according to the present disclosure includes: a robot that is worn by a user, the robot including a drive source that assists action of the user; an interference force estimation unit that estimates an interference force given from the user to the robot; an admittance model that generates a target velocity in a virtual object having a predetermined dynamic characteristic, the target velocity corresponding to the interference force estimated by the interference force estimation unit; and a control unit, in which the interference force estimation unit includes: a disturbance observer that detects a disturbance based on the momentum of the robot; and an estimation unit that estimates the interference force depending on the disturbance detected by the disturbance observer, using an ESN learning model for which learning about the interference force depending on the disturbance is performed while weights in a reservoir layer are stochastically assigned.