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.

中文翻译：

---

在真实环境中具有自动课程学习的具身视觉导航

我们提出了 NavACL，这是一种为导航任务量身定制的自动课程学习方法。NavACL 易于训练并使用几何特征高效地选择相关任务。在我们的实验中，使用 NavACL 训练的深度强化学习代理明显优于使用统一采样（当前标准）训练的最先进代理。此外，我们的代理可以仅使用 RGB 图像在未知的杂乱室内环境中导航到语义指定的目标。避障策略和冻结的特征网络支持转移到看不见的现实世界环境，无需任何修改或再培训要求。我们在模拟中以及在地面机器人和四旋翼无人机的现实世界中评估我们的策略。补充材料中提供了真实结果的视频。