Model predictive game control for personalized and targeted interactive assistance

TL;DR

A new game-theoretic controller for contact robots improves human-robot interaction by predicting and adapting to human movements.

Contribution

The novel model-predictive game controller enables optimal human-robot co-adaptation by predicting human motor control.

Findings

MPG interaction remains stable while reducing human effort.

The robot adapts to humans by identifying individual interaction behaviors.

Humans adapt to the robot's assistance meta-parameter.

Abstract

Contact robots are increasingly used to assist humans in physical training and manufacturing tasks. However, their effectiveness is currently limited as control methods focus on system performance without considering the upcoming human user’s control. Here, we present a differential game-based controller for contact robots ensuring optimal interaction by predicting human motor control over their finite planning horizon. Using this model-predictive game (MPG) controller, we investigated human-robot co-adaptation in experiments, demonstrating that: (a) MPG interaction remains stable while reducing human effort; (b) the robot adapts to humans, identifying time-consistent individual interaction behaviors; (c) humans adapt to the robot, and their behavior can be modulated through an assistance meta-parameter adjusting the robot’s propensity to minimize human effort. These findings indicate that humans understand and adapt to a partner’s control strategy aligning with game theory principles. Furthermore, the assistance meta-parameter’s ability to guide humans toward specific interaction behaviors enables versatile robot-assisted systems for physical training and rehabilitation.

Contact robots assist humans in physical tasks but most existing controllers ignore future human actions. Abdelwaheb Hafs and colleagues propose a game-theoretic controller to fill this gap and enable optimal human-robot co-adaptation.

Figures