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

翻译：深度强化学习与可扩展逼真仿真的最新进展，推动了面向包括导航在内的各类视觉任务的具身智能日益成熟。然而，尽管在训练具身智能体在静态环境中导航方面取得了显著突破，但在包含移动行人或可移动障碍物等动态环境中的进展仍相对有限。本研究旨在系统性地比较不同数据增强技术，以提升智能体在这些具有挑战性环境中的表现。实验表明，在训练场景中引入多个动态障碍物可显著提升测试时的泛化能力，使成功率远超基线智能体。研究发现，该方法还可与图像增强技术结合使用，以达致更高成功率。此外，与图像增强方法相比，该方法在模拟器间迁移中展现出更强的鲁棒性。最终，我们通过将动态障碍物增强方法应用于2021年CVPR iGibson挑战赛的交互式导航任务训练智能体，验证了其有效性——该方案最终荣获赛事第一名。视频链接：https://www.youtube.com/watch?v=HxUX2HeOSE4