動的障害物の追加でナビゲーションエージェントを頑健化：2021 iGibsonチャレンジ優勝手法のベンチマーク
Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge
訓練時に動的障害物をシーンに追加するとテスト時の汎化性能が大きく向上し、画像拡張との併用やsim-to-sim転移への頑健性も示した。CVPR 2021 iGibsonチャレンジのInteractive Navigation部門で1位を獲得した手法。
著者: Naoki Yokoyama, Qian Luo, Dhruv Batra, Sehoon Ha
分類: cs.RO, cs.AI
原文アブストラクト
Recent advances in deep reinforcement learning and scalable photorealistic simulation have led to increasingly mature embodied AI for various visual tasks, including navigation. However, while impressive progress has been made for teaching embodied agents to navigate static environments, much less progress has been made on more dynamic environments that may include moving pedestrians or movable obstacles. In this study, we aim to benchmark different augmentation techniques for improving the agent's performance in these challenging environments. We show that adding several dynamic obstacles into the scene during training confers significant improvements in test-time generalization, achieving much higher success rates than baseline agents. We find that this approach can also be combined with image augmentation methods to achieve even higher success rates. Additionally, we show that this approach is also more robust to sim-to-sim transfer than image augmentation methods. Finally, we demonstrate the effectiveness of this dynamic obstacle augmentation approach by using it to train an agent for the 2021 iGibson Challenge at CVPR, where it achieved 1st place for Interactive Navigation. Video link: https://www.youtube.com/watch?v=HxUX2HeOSE4
