Autonomous Drone Racing with Deep Reinforcement Learning

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1205–1212

Abstract

In many robotic tasks, such as autonomous drone racing, the goal is to travel through a set of waypoints as fast as possible. A key challenge for this task is planning the timeoptimal trajectory, which is typically solved by assuming perfect knowledge of the waypoints to pass in advance. The resulting solution is either highly specialized for a single-track layout, or suboptimal due to simplifying assumptions about the platform dynamics. In this work, a new approach to near-time-optimal trajectory generation for quadrotors is presented. Leveraging deep reinforcement learning and relative gate observations, our approach can compute near-time-optimal trajectories and adapt the trajectory to environment changes. Our method exhibits computational advantages over approaches based on trajectory optimization for non-trivial track configurations. The proposed approach is evaluated on a set of race tracks in simulation and the real world, achieving speeds of up to 60kmh−1with a physical quadrotor.

Authors 4

1. Yunlong Song

   University of Zurich · ETH Zurich

   Affiliation as printed

   Robotics and Perception Group, University of Zurich

   University of Zurich and ETH Zurich, Switzerland

2. Mats Steinweg Aachen

   University of Zurich · ETH Zurich · RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

   Robotics and Perception Group, University of Zurich

   University of Zurich and ETH Zurich, Switzerland

3. Elia Kaufmann

   University of Zurich · ETH Zurich

   Affiliation as printed

   Robotics and Perception Group, University of Zurich

   University of Zurich and ETH Zurich, Switzerland

4. Davide Scaramuzza

   University of Zurich · ETH Zurich

   Affiliation as printed

   Robotics and Perception Group, University of Zurich

   University of Zurich and ETH Zurich, Switzerland