Language-Augmented Symbolic Planner for Open-World Task Planning

RSS 2024

Guanqi Chen1, Lei Yang1, Ruixing Jia1, Zhe Hu2, Yizhou Chen3, Wei Zhang4, Wenping Wang5, Jia Pan1,3
1The University of Hong Kong, 2University of Electronic Science and Technology of China, 3Centre for Transformative Garment Production, 4Southern University of Science and Technology, 5Texas A&M University
Paper

Abstract

Enabling robotic agents to perform complex longhorizon 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.


Introduction

intro

Symbolic planners require complete domain and problem knowledge to find valid solutions. However, due to human oversight or other factors, this knowledge may be incomplete, such as missing preconditions or objects, which can result in execution failure or an inability to find a solution. Our work aims to use commonsense knowledge in large language models to address these issues.


Methodology

pipeline

An overview of our proposed LASP, a task planning framework in the open world where the knowledge for planning is incomplete. The symbolic planner is responsible for finding a plan to accomplish the given task, and subsequently, the robot executes this plan. Given an initial, incorrect plan, the robot will encounter some errors during action execution. Our proposed method LASP will invoke the LLM to recursively refine the task planning problem by supplementing action knowledge to the planner. Moreover, if the planner is unable to find a plan afterward, the LLM can augment the planner’s task-specific knowledge with necessary objects to assist the planner in finding an error-free solution.


Results

table1

Comparison with language-driven planning methods.

table2

Comparison with COWP (combination of LLM and symbolic planner).

BibTeX


@inproceedings{chen2024lasp,
  title={Language-Augmented Symbolic Planner for Open-World Task Planning},
  author={Chen, Guanqi and Yang, Lei and Jia, Ruixing and Hu, Zhe and Chen, Yizhou and Zhang, Wei and Wang, Wenping and Pan, Jia},
  booktitle = "Robotics: Science and Systems",
  year={2024}
}