This paper presents an approach for improving navigation in dynamic and interactive environments, which won the 1st place in the iGibson Interactive Navigation Challenge 2021. While the last few years have produced impressive progress on PointGoal Navigation in static environments, relatively little effort has been made on more realistic dynamic environments. The iGibson Challenge proposed two new navigation tasks, Interactive Navigation and Social Navigation, which add displaceable obstacles and moving pedestrians into the simulator environment. Our approach to study these problems uses two key ideas. First, we employ large-scale reinforcement learning by leveraging the Habitat simulator, which supports high performance parallel computing for both simulation and synchronized learning. Second, we employ a new data augmentation technique that adds more dynamic objects into the environment, which can also be combined with traditional image-based augmentation techniques to boost the performance further. Lastly, we achieve sim-to-sim transfer from Habitat to the iGibson simulator, and demonstrate that our proposed methods allow us to train robust agents in dynamic environments with interactive objects or moving humans. Video link: https://www.youtube.com/watch?v=HxUX2HeOSE4
翻译:本文介绍了一种在动态和互动环境中改进导航的方法,它在iGibson互动导航挑战2021年iGibson互动导航挑战中赢得了第一位。虽然过去几年在静态环境中的点目标导航工作取得了令人印象深刻的进展,但在更现实的动态环境中却相对没有做出多少努力。iGibson挑战提出了两项新的导航任务,即互动导航和社会导航,这增加了可移动的障碍,并将行人移动到模拟环境中。我们研究这些问题的方法有两个关键想法。首先,我们利用利用生境模拟器进行大规模强化学习,该模拟器支持高性能平行计算,用于模拟和同步学习。第二,我们采用新的数据增强技术,在环境中增加更多动态物体,还可与传统的图像增强技术相结合,以进一步提高性能。最后,我们实现了从生境向iGibson模拟器的模拟器的模拟传输。我们提出的方法允许我们在动态环境中用交互式物体或移动人类物体对强力剂进行培训。视频链接:https://www.youtube.com/watch=HXX2HHH。