FLTRNN: Faithful Long-Horizon Task Planning for Robotics with Large Language Models
Authors:
- 13 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6680-6686
Abstract
Recent planning methods based on Large Language Models typically employ the In-Context Learning paradigm. Complex long-horizon planning tasks require more context(including instructions and demonstrations) to guarantee that the generated plan can be executed correctly. However, in such conditions, LLMs may overlook(unfaithful) the rules in the given context, resulting in the generated plans being invalid or even leading to dangerous actions. In this paper, we investigate the faithfulness of LLMs for complex long-horizon tasks. Inspired by human intelligence, we introduce a novel framework named FLTRNN. FLTRNN employs a language-based RNN structure to integrate task decomposition and memory management into LLM planning inference, which could effectively improve the faithfulness of LLMs and make the planner more reliable. We conducted experiments in VirtualHome household tasks. Results show that our model significantly improves faithfulness and success rates for complex long-horizon tasks. Website at https://tannl.github.io/FLTRNN.github.io/Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 17 references indexed in Scilit:
- LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models2023
- TidyBot: Personalized Robot Assistance with Large Language Models2023
- RFFCE: Residual Feature Fusion and Confidence Evaluation Network for 6DoF Pose Estimation2023
- KGNet: Knowledge-Guided Networks for Category-Level 6D Object Pose and Size Estimation2023
- ProgPrompt: Generating Situated Robot Task Plans using Large Language Models2023
- Visual Language Maps for Robot Navigation2023
- Entity-Based Knowledge Conflicts in Question Answering2021
- VirtualHome: Simulating Household Activities Via Programs2018
- Working MemoryScience, 1992
- Learning and reasoning by analogyCommunications of the ACM, 1980