Interactively Robot Action Planning with Uncertainty Analysis and Active Questioning by Large Language Model

TL;DR

This paper presents an interactive robot action planning approach using Large Language Models that actively ask humans questions to clarify uncertainties, reducing instruction design effort and improving task execution in robotics.

Contribution

It introduces a novel interactive method enabling LLMs to analyze and gather missing information through questioning, enhancing robot planning with minimal instruction design cost.

Findings

Effective in cooking task scenarios

Challenges include asking unimportant questions

Identifies issues in assumption of missing info

Abstract

The application of the Large Language Model (LLM) to robot action planning has been actively studied. The instructions given to the LLM by natural language may include ambiguity and lack of information depending on the task context. It is possible to adjust the output of LLM by making the instruction input more detailed; however, the design cost is high. In this paper, we propose the interactive robot action planning method that allows the LLM to analyze and gather missing information by asking questions to humans. The method can minimize the design cost of generating precise robot instructions. We demonstrated the effectiveness of our method through concrete examples in cooking tasks. However, our experiments also revealed challenges in robot action planning with LLM, such as asking unimportant questions and assuming crucial information without asking. Shedding light on these issues provides valuable insights for future research on utilizing LLM for robotics.