MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model

TL;DR

This paper introduces MLDT, a multi-level decomposition approach that improves open-source large language models' ability to plan complex, long-horizon robotic tasks by decomposing tasks and training on a challenging new dataset.

Contribution

The paper proposes a novel multi-level decomposition method for robotic task planning and a goal-sensitive data generation process to enhance LLMs' planning capabilities.

Findings

MLDT significantly improves planning accuracy on complex tasks.

The new LongTasks dataset effectively evaluates long-horizon planning.

MLDT outperforms existing methods in virtual robot environments.

Abstract

In the realm of data-driven AI technology, the application of open-source large language models (LLMs) in robotic task planning represents a significant milestone. Recent robotic task planning methods based on open-source LLMs typically leverage vast task planning datasets to enhance models' planning abilities. While these methods show promise, they struggle with complex long-horizon tasks, which require comprehending more context and generating longer action sequences. This paper addresses this limitation by proposing MLDT, theMulti-Level Decomposition Task planning method. This method innovatively decomposes tasks at the goal-level, task-level, and action-level to mitigate the challenge of complex long-horizon tasks. In order to enhance open-source LLMs' planning abilities, we introduce a goal-sensitive corpus generation method to create high-quality training data and conduct instruction tuning on the generated corpus. Since the complexity of the existing datasets is not high enough, we construct a more challenging dataset, LongTasks, to specifically evaluate planning ability on complex long-horizon tasks. We evaluate our method using various LLMs on four datasets in VirtualHome. Our results demonstrate a significant performance enhancement in robotic task planning, showcasing MLDT's effectiveness in overcoming the limitations of existing methods based on open-source LLMs as well as its practicality in complex, real-world scenarios.