Using learning to control artificial avatars in human motor coordination tasks

TL;DR

This paper presents a novel approach using Markov Chains and reinforcement learning to create artificial agents that can naturally coordinate motor actions with humans, with potential applications in healthcare rehabilitation.

Contribution

It introduces a new method to generate human-like motor behavior in virtual agents and integrates it into a control architecture for human-agent coordination.

Findings

The Markov Chain-based model can replicate human motor kinematic properties.

The reinforcement learning framework enables cyber-agents to mimic specific human behaviors.

Potential applications in healthcare for motor disorder rehabilitation.

Abstract

Designing artificial cyber-agents able to interact with human safely, smartly and in a natural way is a current open problem in control. Solving such an issue will allow the design of cyber-agents capable of co-operatively interacting with people in order to fulfil common joint tasks in a multitude of different applications. This is particularly relevant in the context of healthcare applications. Indeed, the use has been proposed of artificial agents interacting and coordinating their movements with those of a patient suffering from social or motor disorders. Specifically, it has been shown that an artificial agent exhibiting certain kinematic properties could provide innovative and efficient rehabilitation strategies for these patients. Moreover, it has also been shown that the level of motor coordination is enhanced if these kinematic properties are similar to those of the individual it is interacting with. In this paper we discuss, first, a new method based on Markov Chains to confer "human motor characteristics" on a virtual agent, so as that it can coordinate its motion with that of a target individual while exhibiting specific kinematic properties. Then, we embed such synthetic model in a control architecture based on reinforcement learning to synthesize a cyber-agent able to mimic the behaviour of a specific human performing a joint motor task with one or more individuals.