Language-Augmented Symbolic Planner for Open-World Task Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Guanqi, Yang, Lei, Jia, Ruixing, Hu, Zhe, Chen, Yizhou, Zhang, Wei, Wang, Wenping, Pan, Jia
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917721530171392
author Chen, Guanqi
Yang, Lei
Jia, Ruixing
Hu, Zhe
Chen, Yizhou
Zhang, Wei
Wang, Wenping
Pan, Jia
author_facet Chen, Guanqi
Yang, Lei
Jia, Ruixing
Hu, Zhe
Chen, Yizhou
Zhang, Wei
Wang, Wenping
Pan, Jia
contents Enabling robotic agents to perform complex long-horizon tasks has been a long-standing goal in robotics and artificial intelligence (AI). Despite the potential shown by large language models (LLMs), their planning capabilities remain limited to short-horizon tasks and they are unable to replace the symbolic planning approach. Symbolic planners, on the other hand, may encounter execution errors due to their common assumption of complete domain knowledge which is hard to manually prepare for an open-world setting. In this paper, we introduce a Language-Augmented Symbolic Planner (LASP) that integrates pre-trained LLMs to enable conventional symbolic planners to operate in an open-world environment where only incomplete knowledge of action preconditions, objects, and properties is initially available. In case of execution errors, LASP can utilize the LLM to diagnose the cause of the error based on the observation and interact with the environment to incrementally build up its knowledge base necessary for accomplishing the given tasks. Experiments demonstrate that LASP is proficient in solving planning problems in the open-world setting, performing well even in situations where there are multiple gaps in the knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2407_09792
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Language-Augmented Symbolic Planner for Open-World Task Planning
Chen, Guanqi
Yang, Lei
Jia, Ruixing
Hu, Zhe
Chen, Yizhou
Zhang, Wei
Wang, Wenping
Pan, Jia
Robotics
Enabling robotic agents to perform complex long-horizon tasks has been a long-standing goal in robotics and artificial intelligence (AI). Despite the potential shown by large language models (LLMs), their planning capabilities remain limited to short-horizon tasks and they are unable to replace the symbolic planning approach. Symbolic planners, on the other hand, may encounter execution errors due to their common assumption of complete domain knowledge which is hard to manually prepare for an open-world setting. In this paper, we introduce a Language-Augmented Symbolic Planner (LASP) that integrates pre-trained LLMs to enable conventional symbolic planners to operate in an open-world environment where only incomplete knowledge of action preconditions, objects, and properties is initially available. In case of execution errors, LASP can utilize the LLM to diagnose the cause of the error based on the observation and interact with the environment to incrementally build up its knowledge base necessary for accomplishing the given tasks. Experiments demonstrate that LASP is proficient in solving planning problems in the open-world setting, performing well even in situations where there are multiple gaps in the knowledge.
title Language-Augmented Symbolic Planner for Open-World Task Planning
topic Robotics
url https://arxiv.org/abs/2407.09792