Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation
This addresses the challenge of teaching UAVs to fly in complex environments like racing, which is incremental as it builds on existing imitation learning with a focus on data augmentation.
The paper tackles the problem of autonomous UAV racing by training a deep neural network to predict controls from raw images using imitation learning with data augmentation, achieving performance that outperforms state-of-the-art methods and many human pilots in simulation.
Automating the navigation of unmanned aerial vehicles (UAVs) in diverse scenarios has gained much attention in recent years. However, teaching UAVs to fly in challenging environments remains an unsolved problem, mainly due to the lack of training data. In this paper, we train a deep neural network to predict UAV controls from raw image data for the task of autonomous UAV racing in a photo-realistic simulation. Training is done through imitation learning with data augmentation to allow for the correction of navigation mistakes. Extensive experiments demonstrate that our trained network (when sufficient data augmentation is used) outperforms state-of-the-art methods and flies more consistently than many human pilots. Additionally, we show that our optimized network architecture can run in real-time on embedded hardware, allowing for efficient on-board processing critical for real-world deployment. From a broader perspective, our results underline the importance of extensive data augmentation techniques to improve robustness in end-to-end learning setups.