Human-Robot Collaboration Control With Bounded Predictive Assistance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current human-robot collaboration control strategies are predominantly reactive, limiting robots to passive followers, lacking predictive assistance and resulting in increased human fatigue and reduced coordination efficiency, especially when handling large or awkwardly shaped objects.
Innovation Solution
A control architecture combining a passive, kinetic energy-dissipative reactive controller with a bounded predictive assistance component that infers human performance objectives from wrench-twist data, integrating a virtual damping system, historical state database, and predictive controller to provide proactive support.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a reactive control strategy is used where the robot follows human motion compliantly, then safety and prevention of excessive resistance are ensured, but the robot is confined to a passive follower role and human fatigue increases
Solution Approach 1:
The system performs preliminary action by predicting human intent and preparing compensatory forces in advance. The predictive controller anticipates future human movements and applies compensating forces before the human actually moves, reducing the effort the human needs to exert while maintaining safety through reactive compliance.
2Reliability
If a reactive control strategy is used where the robot follows human motion compliantly, then safety is ensured, but coordination efficiency and task execution speed are reduced
Solution Approach 1:
The system performs preliminary action by predicting human intent and preparing compensatory forces in advance. The predictive controller anticipates future human movements and applies compensating forces before the human actually moves, reducing the effort the human needs to exert while maintaining safety through reactive compliance.
Solution Approach 2:
The system uses feedback from force sensors and visual tracking to continuously monitor human interaction and update predictions. This feedback loop allows the predictive controller to adjust its compensatory forces in real-time based on actual human behavior, improving coordination efficiency while maintaining safety.
3Reliability
If a reactive control strategy is used where the robot follows human motion compliantly, then safety is ensured, but the robot is unable to anticipate human intent and provide proactive task support
Solution Approach 1:
The system performs preliminary action by predicting human intent and preparing compensatory forces in advance. The predictive controller anticipates future human movements and applies compensating forces before the human actually moves, reducing the effort the human needs to exert while maintaining safety through reactive compliance.
Solution Approach 2:
The system replaces pure mechanical reactive response with a predictive control system that uses machine learning models to anticipate human intent. This substitution allows the robot to proactively provide task support while maintaining the safety guarantees of reactive compliance control.
Data Source
AI summary
A control system for human-robot collaboration, including: a passive reactive control path implemented through a virtual damping system and configured to generate reactive control signals in response to human-applied interaction inputs; a predictive control path configured to generate predictive control signals based on predicted human performance objective inferred online from measured contact wrenches; and a signal blending component configured to combine the reactive control signals and the predictive control signals, wherein the predictive control signals are bounded in magnitude such that passivity of the reactive control path is preserved and stability of closed-loop human-robot interaction is maintained during collaboration.