We propose (CAD)$^2$RL, a flight controller for Collision Avoidance via Deep Reinforcement Learning that can be used to perform collision-free flight in the real world although it is trained entirely in a 3D CAD model simulator. Our method uses only single RGB images from a monocular camera mounted on the robot as the input and is specialized for indoor hallway following and obstacle avoidance. In contrast to most indoor navigation techniques that aim to directly reconstruct the 3D geometry of the environment, our approach directly predicts the probability of collision given the current monocular image and a candidate action. To obtain accurate predictions, we develop a deep reinforcement learning algorithm for learning indoor navigation, which uses the actual performance of the current policy to construct accurate supervision. The collision prediction model is represented by a deep convolutional neural network that directly processes raw image inputs. Our collision avoidance system is entirely trained in simulation and thus addresses the high sample complexity of deep reinforcement learning and avoids the dangers of trial-and-error learning in the real world. By highly randomizing the rendering settings for our simulated training set, we show that we can train a collision predictor that generalizes to new environments with substantially different appearance from the training scenarios. Finally, we evaluate our method in the real world by controlling a real quadrotor flying through real hallways. We demonstrate that our method can perform real-world collision avoidance and hallway following after being trained exclusively on synthetic images, without ever having seen a single real image at the training time. For supplementary video see: https://fsadeghi.github.io/CAD2RL

本文提出了一个使用CAD模型进行学习的深度卷积神经网络，能够在通过单目摄像头传输的图像训练之后，实现在真实环境下进行无碰撞室内飞行的过程。通过高度随机的3D渲染和MC策略评估算法的使用，我们证明了该方法可以推广到真实世界，而不需要模拟器的特别真实或高保真度。

CAD2RL: 单图像飞行仿真