Path Planning using Instruction-Guided Probabilistic Roadmaps

TL;DR

This paper introduces IG-PRM, a data-driven path planning method that incorporates natural language instructions into robot navigation by converting instructions into cost maps using large-language models, improving navigation flexibility.

Contribution

The paper proposes a novel instruction-guided probabilistic roadmap approach that integrates natural language instructions into path planning using LLMs to generate cost maps, enabling more adaptable robot navigation.

Findings

Effective in synthetic environments

Successful in real-world indoor navigation

Improves navigation flexibility with natural language instructions

Abstract

This work presents a novel data-driven path planning algorithm named Instruction-Guided Probabilistic Roadmap (IG-PRM). Despite the recent development and widespread use of mobile robot navigation, the safe and effective travels of mobile robots still require significant engineering effort to take into account the constraints of robots and their tasks. With IG-PRM, we aim to address this problem by allowing robot operators to specify such constraints through natural language instructions, such as ``aim for wider paths'' or ``mind small gaps''. The key idea is to convert such instructions into embedding vectors using large-language models (LLMs) and use the vectors as a condition to predict instruction-guided cost maps from occupancy maps. By constructing a roadmap based on the predicted costs, we can find instruction-guided paths via the standard shortest path search. Experimental results demonstrate the effectiveness of our approach on both synthetic and real-world indoor navigation environments.