Autonomous Drone Racing with Deep Reinforcement Learning02:54

In many robotic tasks, such as 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 minimum-time trajectory, which is typically solved by assuming perfect knowledge of the waypoints to pass in advance. The resulting solutions are 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 minimum-time trajectory generation for quadrotors is presented. Leveraging deep reinforcement learning and relative gate observations, this approach can adaptively compute near-time-optimal trajectories for random track layouts. Our method exhibits a significant computational advantage 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 17 m/s with a physical quadrotor.

Reference:
Y. Song*, M. Steinweg*, E. Kaufmann, D. Scaramuzza
“Autonomous Drone Racing with Deep Reinforcement Learning”
arXiv 2021 PDF: http://rpg.ifi.uzh.ch/docs/Arxiv21_Yunlong.pdf

For more information about our research, visit these pages:
1. Drone Racing: http://rpg.ifi.uzh.ch/research_drone_racing.html
2. Aggressive Flight: http://rpg.ifi.uzh.ch/aggressive_flight.html
3. Machine Learning: http://rpg.ifi.uzh.ch/research_learning.html

Affiliations:
Y. Song, M. Steinweg, E. Kaufmann, D. Scaramuzza are with the Robotics and Perception Group, Dep. of Informatics, University of Zurich, and Dep. of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland. M. Steinweg is also with RWTH Aachen University, Germany.

Music Credits: Epic Inspiration from AShamaluevMusic