论文标题
在真实环境中使用自动课程学习的体现视觉导航
Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments
论文作者
论文摘要
我们提出NAVACL，这是一种针对导航任务量身定制的自动课程学习方法。 NAVACL易于训练并有效地使用几何特征选择相关任务。在我们的实验中，经过NAVACL训练的深钢筋学习剂显着超过了经过统一抽样的训练的最先进的代理 - 当前标准。此外，我们的代理人可以仅使用RGB图像浏览未知的杂物室内环境到语义指定的目标。避免障碍物的策略和冷冻特征网络支持转移到看不见的现实环境，而没有任何修改或再培训要求。我们在模拟中评估了我们的策略，以及在地面机器人和四型无人机上的现实世界中评估我们的政策。现实世界结果的视频可在补充材料中获得。
We present NavACL, a method of automatic curriculum learning tailored to the navigation task. NavACL is simple to train and efficiently selects relevant tasks using geometric features. In our experiments, deep reinforcement learning agents trained using NavACL significantly outperform state-of-the-art agents trained with uniform sampling -- the current standard. Furthermore, our agents can navigate through unknown cluttered indoor environments to semantically-specified targets using only RGB images. Obstacle-avoiding policies and frozen feature networks support transfer to unseen real-world environments, without any modification or retraining requirements. We evaluate our policies in simulation, and in the real world on a ground robot and a quadrotor drone. Videos of real-world results are available in the supplementary material.
