| Autor: |
Eftekhar, Ainaz, Weihs, Luca, Hendrix, Rose, Caglar, Ege, Salvador, Jordi, Herrasti, Alvaro, Han, Winson, VanderBil, Eli, Kembhavi, Aniruddha, Farhadi, Ali, Krishna, Ranjay, Ehsani, Kiana, Zeng, Kuo-Hao |
| Rok vydání: |
2024 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
Modern robots vary significantly in shape, size, and sensor configurations used to perceive and interact with their environments. However, most navigation policies are embodiment-specific; a policy learned using one robot's configuration does not typically gracefully generalize to another. Even small changes in the body size or camera viewpoint may cause failures. With the recent surge in custom hardware developments, it is necessary to learn a single policy that can be transferred to other embodiments, eliminating the need to (re)train for each specific robot. In this paper, we introduce RING (Robotic Indoor Navigation Generalist), an embodiment-agnostic policy, trained solely in simulation with diverse randomly initialized embodiments at scale. Specifically, we augment the AI2-THOR simulator with the ability to instantiate robot embodiments with controllable configurations, varying across body size, rotation pivot point, and camera configurations. In the visual object-goal navigation task, RING achieves robust performance on real unseen robot platforms (Stretch RE-1, LoCoBot, Unitree's Go1), achieving an average of 72.1% and 78.9% success rate across 5 embodiments in simulation and 4 robot platforms in the real world. (project website: https://one-ring-policy.allen.ai/) |
| Databáze: |
arXiv |
| Externí odkaz: |
|
