Bridging the Indoor-Outdoor Gap: Vision-Centric Instruction-Guided Embodied Navigation for the Last Meters

TL;DR

This paper introduces a novel instruction-guided embodied navigation task bridging outdoor and indoor environments without relying on external priors, and proposes a vision-centric framework that outperforms existing methods.

Contribution

It formulates the first open challenge for outdoor-to-indoor navigation without external priors and presents a new vision-centric approach with an open-source dataset.

Findings

Our method achieves higher success rates than baselines.

It improves path efficiency in outdoor-to-indoor navigation.

The dataset enables future research in this area.

Abstract

Embodied navigation holds significant promise for real-world applications such as last-mile delivery. However, most existing approaches are confined to either indoor or outdoor environments and rely heavily on strong assumptions, such as access to precise coordinate systems. While current outdoor methods can guide agents to the vicinity of a target using coarse-grained localization, they fail to enable fine-grained entry through specific building entrances, critically limiting their utility in practical deployment scenarios that require seamless outdoor-to-indoor transitions. To bridge this gap, we introduce a novel task: out-to-in prior-free instruction-driven embodied navigation. This formulation explicitly eliminates reliance on accurate external priors, requiring agents to navigate solely based on egocentric visual observations guided by instructions. To tackle this task, we propose a vision-centric embodied navigation framework that leverages image-based prompts to drive decision-making. Additionally, we present the first open-source dataset for this task, featuring a pipeline that integrates trajectory-conditioned video synthesis into the data generation process. Through extensive experiments, we demonstrate that our proposed method consistently outperforms state-of-the-art baselines across key metrics including success rate and path efficiency.