NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation

2026-07-21

AI Summary

Existing navigation benchmarks are fragmented across indoor and outdoor environments and often neglect robot execution details, making it difficult to evaluate adaptability and safety in cross-environment navigation. To address this gap, this work proposes NavVerse—the first unified, continuous embodied navigation benchmark spanning 100 indoor, 50 outdoor, and 50 transitional scenes, offering 10,000 semantic goal navigation tasks. Built upon a physics-based simulation platform, NavVerse integrates an executable robot interface supporting ObjectNav, Vision-and-Language Navigation (VLN), and PlaceNav tasks. Experimental results reveal significant performance bottlenecks for current methods in cross-environment settings: end-to-end Vision-Language-Action (VLA) models achieve the highest success rates, modular approaches demonstrate superior safety, and PlaceNav exhibits markedly degraded performance in transitional scenes, highlighting critical challenges in environmental adaptability.

Abstract

Robots deployed in delivery, campus, and emergency-response settings often need to navigate from buildings to streets within a single continuous episode. Existing benchmarks usually evaluate indoor and outdoor navigation separately, and many abstract away robot execution, leaving exit finding, boundary traversal, adaptation, and kinodynamic failures underexplored. We introduce NavVerse, a physics-enabled benchmark for indoor-to-outdoor embodied navigation. NavVerse contains 100 indoor scenes, 50 urban outdoor scenes, and 50 indoor-to-outdoor scenes, and 10,000 episodes spanning Object Navigation, Vision-and-Language Navigation, and Place Navigation tasks, where agents search for semantic points of interest such as restaurants or banks. Agents are evaluated through executable robot interfaces using task-success, path-efficiency, and safety metrics. Zero-shot experiments with RL, VLA, and modular baselines show that current agents remain far from solving cross-context navigation: end-to-end VLAs obtain the highest zero-shot success, while the modular method provides the strongest safety profile. PlaceNav further reveals a clear drop from outdoor to indoor-to-outdoor scenes, indicating that adaptation remains major bottleneck.

Problem

• indoor-to-outdoor navigation
• embodied navigation
• robot simulation
• cross-context adaptation
• navigation benchmark

Innovation

• embodied navigation
• indoor-to-outdoor
• physics-based simulation
• cross-context adaptation
• executable robot interface