OmniVLN: Omnidirectional 3D Perception and Token-Efficient LLM Reasoning for Visual-Language Navigation across Air and Ground Platforms

TL;DR

OmniVLN introduces a zero-shot navigation framework combining omnidirectional 3D perception with hierarchical reasoning, significantly enhancing spatial understanding and navigation accuracy for aerial and ground robots in complex indoor environments.

Contribution

The paper presents OmniVLN, a novel system that fuses omnidirectional sensing with token-efficient hierarchical reasoning, enabling improved visual-language navigation without extensive prior training.

Findings

Navigation success improved by up to 11.68% over baseline.

Spatial referring accuracy increased from 77.27% to 93.18%.

Reduced prompt tokens by up to 61.7% in cluttered environments.

Abstract

Language-guided embodied navigation requires an agent to interpret object-referential instructions, search across multiple rooms, localize the referenced target, and execute reliable motion toward it. Existing systems remain limited in real indoor environments because narrow field-of-view sensing exposes only a partial local scene at each step, often forcing repeated rotations, delaying target discovery, and producing fragmented spatial understanding; meanwhile, directly prompting LLMs with dense 3D maps or exhaustive object lists quickly exceeds the context budget. We present OmniVLN, a zero-shot visual-language navigation framework that couples omnidirectional 3D perception with token-efficient hierarchical reasoning for both aerial and ground robots. OmniVLN fuses a rotating LiDAR and panoramic vision into a hardware-agnostic mapping stack, incrementally constructs a five-layer Dynamic Scene Graph (DSG) from mesh geometry to room- and building-level structure, and stabilizes high-level topology through persistent-homology-based room partitioning and hybrid geometric/VLM relation verification. For navigation, the global DSG is transformed into an agent-centric 3D octant representation with multi-resolution spatial attention prompting, enabling the LLM to progressively filter candidate rooms, infer egocentric orientation, localize target objects, and emit executable navigation primitives while preserving fine local detail and compact long-range memory. Experiments show that the proposed hierarchical interface improves spatial referring accuracy from 77.27\% to 93.18\%, reduces cumulative prompt tokens by up to 61.7\% in cluttered multi-room settings, and improves navigation success by up to 11.68\% over a flat-list baseline. We will release the code and an omnidirectional multimodal dataset to support reproducible research.