Nl2Hltl2Plan: Scaling Up Natural Language Understanding for Multi-Robots Through Hierarchical Temporal Logic Task Representation

TL;DR

Nl2Hltl2Plan leverages large language models to translate natural language commands into hierarchical temporal logic for efficient multi-robot task planning, improving success rates and handling complex instructions.

Contribution

The paper introduces a novel framework that uses hierarchical LTL representations derived from natural language via LLMs for multi-robot planning, enhancing accuracy and scalability.

Findings

Outperforms existing methods in success rate and cost efficiency

Handles more complex instructions effectively

Validated through simulation and real-world experiments

Abstract

To enable non-experts to specify long-horizon, multi-robot collaborative tasks, language models are increasingly used to translate natural language commands into formal specifications. However, because translation can occur in multiple ways, such translations may lack accuracy or lead to inefficient multi-robot planning. Our key insight is that concise hierarchical specifications can simplify planning while remaining straightforward to derive from human instructions. We propose Nl2Hltl2Plan, a framework that translates natural language commands into hierarchical Linear Temporal Logic (LTL) and solves the corresponding planning problem. The translation involves two steps leveraging Large Language Models (LLMs). First, an LLM transforms instructions into a Hierarchical Task Tree, capturing logical and temporal relations. Next, a fine-tuned LLM converts sub-tasks into flat LTL formulas, which are aggregated into hierarchical specifications, with the lowest level corresponding to ordered robot actions. These specifications are then used with off-the-shelf planners. Our Nl2Hltl2Plan demonstrates the potential of LLMs in hierarchical reasoning for multi-robot task planning. Evaluations in simulation and real-world experiments with human participants show that Nl2Hltl2Plan outperforms existing methods, handling more complex instructions while achieving higher success rates and lower costs in task allocation and planning. Additional details are available at https://nl2hltl2plan.github.io .