Search papers, labs, and topics across Lattice.
The paper introduces NavVerse, a comprehensive benchmark designed to evaluate indoor-to-outdoor embodied navigation in continuous robot simulation, addressing the limitations of existing benchmarks that treat indoor and outdoor navigation separately. By incorporating 100 indoor scenes, 50 urban outdoor scenes, and 50 indoor-to-outdoor scenarios across 10,000 episodes, it assesses agents on task success, path efficiency, and safety metrics. The findings reveal that current navigation agents struggle with cross-context scenarios, with a notable performance drop when transitioning from outdoor to indoor-to-outdoor environments, highlighting adaptation as a critical challenge.
Current navigation agents falter in cross-context scenarios, with a significant performance drop when moving from outdoor to indoor-to-outdoor environments.
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.
