End-to-End Motion Planning of Quadrotors Using Deep Reinforcement Learning
This addresses motion planning for quadrotors in complex settings, offering a novel approach that bypasses traditional sensing-reconstructing-planning pipelines, though it appears incremental as it builds on deep reinforcement learning for specific navigation tasks.
The paper tackles quadrotor navigation in cluttered environments by proposing an end-to-end motion planning method that uses raw depth images to directly generate smooth motion primitives for obstacle avoidance, achieving promising results in AirSim simulations and real flights with a DJI F330 Quadrotor.
In this work, a novel, end-to-end motion planning method is proposed for quadrotor navigation in cluttered environments. The proposed method circumvents the explicit sensing-reconstructing-planning in contrast to conventional navigation algorithms. It uses raw depth images obtained from a front-facing camera and directly generates local motion plans in the form of smooth motion primitives that move a quadrotor to a goal by avoiding obstacles. Promising training and testing results are presented in both AirSim simulations and real flights with DJI F330 Quadrotor equipped with Intel RealSense D435. The proposed system in action can be found in https://youtu.be/pYvKhc8wrTM.