# AR3n: A Reinforcement Learning-based Assist-As-Needed Controller for Robotic Rehabilitation

## TL;DR

AR3n is a reinforcement learning-based assist-as-needed controller designed for robotic handwriting rehabilitation, providing adaptive assistance without relying on patient-specific parameters, validated through simulations and human experiments.

## Contribution

Introduces AR3n, a novel RL-based AAN controller that generalizes across patients using a virtual model, eliminating the need for patient-specific tuning.

## Key findings

- AR3n effectively reduces robotic assistance in real-time.
- AR3n outperforms traditional rule-based controllers in assistance modulation.
- The virtual patient model enables generalization across multiple subjects.

## Abstract

In this paper, we present AR3n (pronounced as Aaron), an assist-as-needed (AAN) controller that utilizes reinforcement learning to supply adaptive assistance during a robot assisted handwriting rehabilitation task. Unlike previous AAN controllers, our method does not rely on patient specific controller parameters or physical models. We propose the use of a virtual patient model to generalize AR3n across multiple subjects. The system modulates robotic assistance in realtime based on a subject's tracking error, while minimizing the amount of robotic assistance. The controller is experimentally validated through a set of simulations and human subject experiments. Finally, a comparative study with a traditional rule-based controller is conducted to analyze differences in assistance mechanisms of the two controllers.