Enhancement of long-horizon task planning via active and passive modification in large language models
Authors:
Open Access
- 28 February 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-21
Abstract
This study proposes a method for generating complex and long-horizon off-line task plans using large language models (LLMs). Although several studies have been conducted in recent years on robot task planning using LLMs, the planning results tend to be simple, consisting of ten or fewer action commands, depending on the task. In the proposed method, the LLM actively collects missing information by asking questions, and the task plan is upgraded with one dialog example. One of the contributions of this study is a Q&A process in which ambiguity judgment is left to the LLM. By sequentially eliminating ambiguities contained in long-horizon tasks through dialogue, our method increases the amount of information included in movement plans. This study aims to further refine action plans obtained from active modification through dialogue by passive modification, and few studies have addressed these issues for long-horizon robot tasks. In our experiments, we define the number of items in the task planning as information for robot task execution, and we demonstrate the effectiveness of the proposed method through dialogue experiments using a cooking task as the subject. And as a result of the experiment, the amount of information could be increased by the proposed method.Keywords
All Related Versions
Funding Information
- JSPS Grant-in-Aid for Early-Career Scientists (24K20877)
- Moonshot Research and Development Program (JPMJMS2031)
This publication has 41 references indexed in Scilit:
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration02024
- CAPE: Corrective Actions from Precondition Errors using Large Language Models2024
- Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?2024
- ChatGPT for Robotics: Design Principles and Model AbilitiesIEEE Access, 2024
- TidyBot: personalized robot assistance with large language modelsAutonomous Robots, 2023
- LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models2023
- Integrating action knowledge and LLMs for task planning and situation handling in open worldsAutonomous Robots, 2023
- VQA-based Robotic State Recognition Optimized with Genetic Algorithm2023
- Open-vocabulary Queryable Scene Representations for Real World Planning2023
- Code as Policies: Language Model Programs for Embodied Control2023