English

Online Behavior Modification for Expressive User Control of RL-Trained Robots

Robotics 2024-09-02 v1 Artificial Intelligence

Abstract

Reinforcement Learning (RL) is an effective method for robots to learn tasks. However, in typical RL, end-users have little to no control over how the robot does the task after the robot has been deployed. To address this, we introduce the idea of online behavior modification, a paradigm in which users have control over behavior features of a robot in real time as it autonomously completes a task using an RL-trained policy. To show the value of this user-centered formulation for human-robot interaction, we present a behavior diversity based algorithm, Adjustable Control Of RL Dynamics (ACORD), and demonstrate its applicability to online behavior modification in simulation and a user study. In the study (n=23) users adjust the style of paintings as a robot traces a shape autonomously. We compare ACORD to RL and Shared Autonomy (SA), and show ACORD affords user-preferred levels of control and expression, comparable to SA, but with the potential for autonomous execution and robustness of RL.

Keywords

Cite

@article{arxiv.2408.16776,
  title  = {Online Behavior Modification for Expressive User Control of RL-Trained Robots},
  author = {Isaac Sheidlower and Mavis Murdock and Emma Bethel and Reuben M. Aronson and Elaine Schaertl Short},
  journal= {arXiv preprint arXiv:2408.16776},
  year   = {2024}
}

Comments

This work was published and presented at HRI 2024

R2 v1 2026-06-28T18:28:02.917Z