NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models
This work addresses the problem of improving LLM-based navigation for robotics applications, representing an incremental advancement by bridging the divide between existing paradigms.
The paper tackled the performance gap between large language models (LLMs) and specialized models in vision-and-language navigation (VLN) tasks by aligning visual content with a frozen LLM to enhance navigational reasoning, achieving data efficiency and eliminating the gap with state-of-the-art VLN specialists.
Capitalizing on the remarkable advancements in Large Language Models (LLMs), there is a burgeoning initiative to harness LLMs for instruction following robotic navigation. Such a trend underscores the potential of LLMs to generalize navigational reasoning and diverse language understanding. However, a significant discrepancy in agent performance is observed when integrating LLMs in the Vision-and-Language navigation (VLN) tasks compared to previous downstream specialist models. Furthermore, the inherent capacity of language to interpret and facilitate communication in agent interactions is often underutilized in these integrations. In this work, we strive to bridge the divide between VLN-specialized models and LLM-based navigation paradigms, while maintaining the interpretative prowess of LLMs in generating linguistic navigational reasoning. By aligning visual content in a frozen LLM, we encompass visual observation comprehension for LLMs and exploit a way to incorporate LLMs and navigation policy networks for effective action predictions and navigational reasoning. We demonstrate the data efficiency of the proposed methods and eliminate the gap between LM-based agents and state-of-the-art VLN specialists.