Human-Robot Kinaesthetic Interaction Based on Free Energy Principle

TL;DR

This study explores human-robot kinaesthetic interaction using a PV-RNN model based on the free energy principle, revealing how interaction dynamics depend on model parameters and trained versus untrained movements.

Contribution

It demonstrates how the free energy principle can model kinaesthetic interactions and analyzes the influence of the meta-prior on interaction forces and robot behavior.

Findings

Larger meta-prior reduces force needed for trained transitions.

Untrained transitions require more force from the human experimenter.

Analysis clarifies how action gaps manifest as reaction forces.

Abstract

The current study investigated possible human-robot kinaesthetic interaction using a variational recurrent neural network model, called PV-RNN, which is based on the free energy principle. Our prior robotic studies using PV-RNN showed that the nature of interactions between top-down expectation and bottom-up inference is strongly affected by a parameter, called the meta-prior, which regulates the complexity term in free energy.The study also compares the counter force generated when trained transitions are induced by a human experimenter and when untrained transitions are induced. Our experimental results indicated that (1) the human experimenter needs more/less force to induce trained transitions when $w$ is set with larger/smaller values, (2) the human experimenter needs more force to act on the robot when he attempts to induce untrained as opposed to trained movement pattern transitions. Our analysis of time development of essential variables and values in PV-RNN during bodily interaction clarified the mechanism by which gaps in actional intentions between the human experimenter and the robot can be manifested as reaction forces between them.