Paper Image

Interactive robot planning via questioning

Paper Authors:

Kazuki Hori,

Kanata Suzuki,

Tetsuya Ogata

Bullets

Key Details

Proposes interactive planning method for robots using LLM questioning

LLM analyzes uncertainties in its own action plan, asks humans clarifying questions

Cooking tasks show method reduces instruction design costs, improves plan precision

Challenges emerged like unimportant questions, assuming crucial info without asking

Work provides insights on utilizing LLMs for robotics planning

AI generated summary

Interactive robot planning via questioning

This paper proposes an interactive robot action planning method where a large language model (LLM) analyzes uncertainties in its own plan and asks humans clarifying questions. Through cooking task experiments, the method reduced instruction design costs and generated more precise plans. Challenges emerged too, like unimportant questions and assuming crucial info without asking. The work sheds light on utilizing LLMs for robotics.

Answers from this paper

Comments

No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up