I2O2I-Nav: A Benchmark with a Modular Agent for Long-Horizon Indoor-to-Outdoor-to-Indoor Navigation

arXiv:2610.18307 · cs.RO · Submitted 2026-10-13 · Read on arXiv

cs.RO

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: 28 pages. Project page: https://i2o2i-nav.github.io/

Code: https://github.com/nv-tlabs/3dgrut

Project page: https://i2o2i-nav.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation
• POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation
• VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
• LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
• NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation
• AgentVLN: Towards Agentic Vision-and-Language Navigation
• OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation
• HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation
• Bridging the Indoor-Outdoor Gap: Vision-Centric Instruction-Guided Embodied Navigation for the Last Meters

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies