Language-Augmented Symbolic Planner for Open-World Task Planning

TL;DR

This paper presents LASP, a novel approach that combines large language models with symbolic planning to enable robots to perform complex tasks in open-world environments with incomplete knowledge.

Contribution

LASP integrates LLMs with symbolic planners, allowing dynamic diagnosis and knowledge acquisition in open-world task planning scenarios.

Findings

LASP effectively solves open-world planning problems with incomplete knowledge.

LASP outperforms traditional symbolic planners in environments with knowledge gaps.

LASP demonstrates robustness in diagnosing errors and updating its knowledge base.

Abstract

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.