LLM-based Robot Task Planning with Exceptional Handling for General Purpose Service Robots

TL;DR

This paper introduces a novel task planning approach for general purpose service robots using constrained LLM prompts and an exceptional handling module to ensure executable and environment-admissible action sequences, improving instruction comprehension and task execution.

Contribution

The paper presents a constrained LLM prompt scheme combined with an exceptional handling module to improve robot task planning accuracy and reliability, addressing hallucinations and semantic ambiguities.

Findings

High success rate in instruction comprehension.

Effective handling of LLM hallucinations.

Robust task execution in real-world scenarios.

Abstract

The development of a general purpose service robot for daily life necessitates the robot's ability to deploy a myriad of fundamental behaviors judiciously. Recent advancements in training Large Language Models (LLMs) can be used to generate action sequences directly, given an instruction in natural language with no additional domain information. However, while the outputs of LLMs are semantically correct, the generated task plans may not accurately map to acceptable actions and might encompass various linguistic ambiguities. LLM hallucinations pose another challenge for robot task planning, which results in content that is inconsistent with real-world facts or user inputs. In this paper, we propose a task planning method based on a constrained LLM prompt scheme, which can generate an executable action sequence from a command. An exceptional handling module is further proposed to deal with LLM hallucinations problem. This module can ensure the LLM-generated results are admissible in the current environment. We evaluate our method on the commands generated by the RoboCup@Home Command Generator, observing that the robot demonstrates exceptional performance in both comprehending instructions and executing tasks.