Recent work has explored the problem of autonomous navigation by imitating a
teacher and learning an end-to-end policy, which directly predicts controls
from raw images. However, these approaches tend to be sensitive to mistakes by
the teacher and do not scale well to other environments or vehicles. To this
end, we propose Observational Imitation Learning (OIL), a novel imitation
learning variant that supports online training and automatic selection of
optimal behavior by observing multiple imperfect teachers. We apply our
proposed methodology to the challenging problems of autonomous driving and UAV
racing. For both tasks, we utilize the Sim4CV simulator that enables the
generation of large amounts of synthetic training data and also allows for
online learning and evaluation. We train a perception network to predict
waypoints from raw image data and use OIL to train another network to predict
controls from these waypoints. Extensive experiments demonstrate that our
trained network outperforms its teachers, conventional imitation learning (IL)
and reinforcement learning (RL) baselines and even humans in simulation. The
project website is available at this https URL and
a video at this https URL

提出了一种支持在线训练和自动选择最佳行为的新型模仿学习变体 ——OIL，应用于自动驾驶和无人机比赛的挑战性问题，使用 Sim4CV 仿真器进行大量合成训练数据的生成和在线学习和评估，并使用感知网络来预测路点和 OIL 来训练控件预测网络。实验表明，我们的训练网络在模拟中的表现优于其老师 / 人类以及传统的模仿学习和强化学习基线模型。