LLM Granularity for On-the-Fly Robot Control

TL;DR

This paper investigates the viability of controlling assistive robots solely through language prompts of varying detail levels, especially when visual information is unreliable or unavailable, using experiments on a Sawyer cobot and a Turtlebot.

Contribution

It evaluates language-based robot control at different granularities and explores the feasibility of on-the-fly control without visual cues, advancing assistive robot autonomy.

Findings

Language prompts of varying granularity influence robot responses.

Controlling robots solely via language is feasible in certain scenarios.

Experimental results support the potential of linguomotor control for assistive robots.

Abstract

Assistive robots have attracted significant attention due to their potential to enhance the quality of life for vulnerable individuals like the elderly. The convergence of computer vision, large language models, and robotics has introduced the `visuolinguomotor' mode for assistive robots, where visuals and linguistics are incorporated into assistive robots to enable proactive and interactive assistance. This raises the question: \textit{In circumstances where visuals become unreliable or unavailable, can we rely solely on language to control robots, i.e., the viability of the `linguomotor` mode for assistive robots?} This work takes the initial steps to answer this question by: 1) evaluating the responses of assistive robots to language prompts of varying granularities; and 2) exploring the necessity and feasibility of controlling the robot on-the-fly. We have designed and conducted experiments on a Sawyer cobot to support our arguments. A Turtlebot robot case is designed to demonstrate the adaptation of the solution to scenarios where assistive robots need to maneuver to assist. Codes will be released on GitHub soon to benefit the community.