English

Text2Interaction: Establishing Safe and Preferable Human-Robot Interaction

Robotics 2024-10-21 v3

Abstract

Adjusting robot behavior to human preferences can require intensive human feedback, preventing quick adaptation to new users and changing circumstances. Moreover, current approaches typically treat user preferences as a reward, which requires a manual balance between task success and user satisfaction. To integrate new user preferences in a zero-shot manner, our proposed Text2Interaction framework invokes large language models to generate a task plan, motion preferences as Python code, and parameters of a safety controller. By maximizing the combined probability of task completion and user satisfaction instead of a weighted sum of rewards, we can reliably find plans that fulfill both requirements. We find that 83 % of users working with Text2Interaction agree that it integrates their preferences into the plan of the robot, and 94 % prefer Text2Interaction over the baseline. Our ablation study shows that Text2Interaction aligns better with unseen preferences than other baselines while maintaining a high success rate. Real-world demonstrations and code are made available at sites.google.com/view/text2interaction.

Keywords

Cite

@article{arxiv.2408.06105,
  title  = {Text2Interaction: Establishing Safe and Preferable Human-Robot Interaction},
  author = {Jakob Thumm and Christopher Agia and Marco Pavone and Matthias Althoff},
  journal= {arXiv preprint arXiv:2408.06105},
  year   = {2024}
}

Comments

Accepted for the Conference on Robot Learning (CoRL) 2024. Available at: https://openreview.net/forum?id=s0VNSnPeoA

R2 v1 2026-06-28T18:10:22.432Z