NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation

TL;DR

NaVid introduces a video-based vision-language model that enables agents to navigate using only monocular video streams, achieving state-of-the-art results and better generalization in unseen environments without relying on maps or depth sensors.

Contribution

NaVid is the first VLM to perform VLN tasks using only real-time video input, improving generalization and reducing reliance on traditional navigation aids.

Findings

NaVid achieves state-of-the-art navigation performance in simulation and real-world environments.

NaVid demonstrates superior cross-dataset and Sim2Real transfer capabilities.

NaVid effectively encodes spatio-temporal context from video streams for navigation.

Abstract

Vision-and-language navigation (VLN) stands as a key research problem of Embodied AI, aiming at enabling agents to navigate in unseen environments following linguistic instructions. In this field, generalization is a long-standing challenge, either to out-of-distribution scenes or from Sim to Real. In this paper, we propose NaVid, a video-based large vision language model (VLM), to mitigate such a generalization gap. NaVid makes the first endeavor to showcase the capability of VLMs to achieve state-of-the-art level navigation performance without any maps, odometers, or depth inputs. Following human instruction, NaVid only requires an on-the-fly video stream from a monocular RGB camera equipped on the robot to output the next-step action. Our formulation mimics how humans navigate and naturally gets rid of the problems introduced by odometer noises, and the Sim2Real gaps from map or depth inputs. Moreover, our video-based approach can effectively encode the historical observations of robots as spatio-temporal contexts for decision making and instruction following. We train NaVid with 510k navigation samples collected from continuous environments, including action-planning and instruction-reasoning samples, along with 763k large-scale web data. Extensive experiments show that NaVid achieves state-of-the-art performance in simulation environments and the real world, demonstrating superior cross-dataset and Sim2Real transfer. We thus believe our proposed VLM approach plans the next step for not only the navigation agents but also this research field.