LGR: LLM-Guided Ranking of Frontiers for Object Goal Navigation
This work addresses a specific challenge in robot navigation for unknown or dynamic environments, representing an incremental enhancement to modular mapless OGN systems.
The study tackled the problem of determining the visiting order in frontier-based exploration for mapless Object Goal Navigation by framing it as a frontier ranking problem, leveraging LLMs for relative value evaluation, and achieved validation in Habitat-Sim.
Object Goal Navigation (OGN) is a fundamental task for robots and AI, with key applications such as mobile robot image databases (MRID). In particular, mapless OGN is essential in scenarios involving unknown or dynamic environments. This study aims to enhance recent modular mapless OGN systems by leveraging the commonsense reasoning capabilities of large language models (LLMs). Specifically, we address the challenge of determining the visiting order in frontier-based exploration by framing it as a frontier ranking problem. Our approach is grounded in recent findings that, while LLMs cannot determine the absolute value of a frontier, they excel at evaluating the relative value between multiple frontiers viewed within a single image using the view image as context. We dynamically manage the frontier list by adding and removing elements, using an LLM as a ranking model. The ranking results are represented as reciprocal rank vectors, which are ideal for multi-view, multi-query information fusion. We validate the effectiveness of our method through evaluations in Habitat-Sim.