SPOC: シミュレーションでの最短経路模倣による実世界での効果的なナビゲーションと操作
SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World
シミュレーション内の最短経路プランナーを模倣することで、RGBのみを用いて実世界でナビゲーション・探索・物体操作ができるエージェントを訓練した研究。
著者: Kiana Ehsani, Tanmay Gupta, Rose Hendrix, Jordi Salvador, Luca Weihs, Kuo-Hao Zeng, Kunal Pratap Singh, Yejin Kim, Winson Han, Alvaro Herrasti, Ranjay Krishna, Dustin Schwenk, Eli VanderBilt, Aniruddha Kembhavi
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
Reinforcement learning (RL) with dense rewards and imitation learning (IL) with human-generated trajectories are the most widely used approaches for training modern embodied agents. RL requires extensive reward shaping and auxiliary losses and is often too slow and ineffective for long-horizon tasks. While IL with human supervision is effective, collecting human trajectories at scale is extremely expensive. In this work, we show that imitating shortest-path planners in simulation produces agents that, given a language instruction, can proficiently navigate, explore, and manipulate objects in both simulation and in the real world using only RGB sensors (no depth map or GPS coordinates). This surprising result is enabled by our end-to-end, transformer-based, SPOC architecture, powerful visual encoders paired with extensive image augmentation, and the dramatic scale and diversity of our training data: millions of frames of shortest-path-expert trajectories collected inside approximately 200,000 procedurally generated houses containing 40,000 unique 3D assets. Our models, data, training code, and newly proposed 10-task benchmarking suite CHORES are available in https://spoc-robot.github.io.
