I2O2I-Nav：一种配备模块化智能体的长程室内-室外-室内导航基准测试集
I2O2I-Nav: A Benchmark with a Modular Agent for Long-Horizon Indoor-to-Outdoor-to-Indoor Navigation
AI总结：
本文提出I2O2I-Nav基准测试集及MODULAR-Agent，评估长程室内-室外-室内导航的连续组合能力，该智能体大幅提升跨域任务成功率，但完整任务仍面临挑战。
摘要：
服务机器人和配送机器人常需完成跨越室内外环境的长程导航任务。现有具身导航基准主要评估孤立阶段或部分跨域旅程，难以评估异构导航能力在连续执行中的组合效果。本文提出I2O2I-Nav，这是一个基于物理的基准测试集，包含20个真实复合场景，覆盖多栋建筑及楼层，总面积超115000平方米，配有对齐的3DGS渲染与碰撞几何。其三级评估从独立基元、两阶段组合到完整四阶段I2O2I任务逐步推进，每个阶段从前一阶段的实际终点开始，阶段条件指标跟踪任务完成情况并定位失败环节。本文还提出MODULAR-Agent，该智能体通过完成验证、阶段交接和受限恢复来协调冻结的导航策略。对1374个回合的评估凸显了连续组合的难度：MODULAR-Agent在单个基元上的成功率为40.5%-76%，但完整I2O2I任务的成功率仍较低；与使用相同底层策略的固定策略链相比，其在室内-室外（I2O）和室外-室内（O2I）任务上的成功率提高了一倍以上，完整任务成功率从1.15%提升至4.02%。阶段分析显示，MODULAR-Agent使更多任务能到达最终的对象导航阶段，而该阶段的条件成功率仍较低，揭示了长程阶段执行和完成决策的挑战。
英文摘要：
Service and delivery robots often need to complete long-horizon navigation missions spanning indoor and outdoor environments. Existing embodied navigation benchmarks primarily evaluate isolated stages or partial cross-domain journeys, providing limited support for assessing how heterogeneous navigation capabilities compose under continuous execution. We introduce I2O2I-Nav, a physics-enabled benchmark of 20 real-world composite scenes spanning over 115,000 square meters across multiple buildings and floors, with aligned 3DGS rendering and collision geometry. Its three-level evaluation progresses from independent primitives to two-stage compositions and complete four-stage I2O2I missions. Each stage starts from its predecessor's actual endpoint, while stage-conditional metrics track completion and localize failures along the mission. We further propose the MODULAR-Agent that coordinates frozen navigation policies through completion verification, stage handoffs, and bounded recovery. Evaluation across 1,374 episodes highlights the difficulty of continuous composition. The MODULAR-Agent achieves 40.5-76% success on individual primitives, but full I2O2I success remains low. Compared with a fixed policy chain using the same underlying policies, it more than doubles success on both Indoor-to-Outdoor (I2O) and Outdoor-to-Indoor (O2I), while improving full-mission success from 1.15% to 4.02%. Stage-wise analysis shows that the MODULAR-Agent enables more missions to reach the final object-navigation stage, where conditional success remains low, revealing challenges in both long-horizon stage execution and completion decisions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
