Autonomous Drone Racing with Deep Reinforcement Learning
Authors:
Top Cited Papers
- 27 September 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 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 −1 with a physical quadrotor.Keywords
All Related Versions
Funding Information
- European Research Council
This publication has 24 references indexed in Scilit:
- A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Moving PlatformJournal of Intelligent & Robotic Systems, 2018
- Control of a Quadrotor With Reinforcement LearningIEEE Robotics and Automation Letters, 2017
- Minimum-Time Trajectory Generation for Quadrotors in Constrained EnvironmentsIEEE Transactions on Control Systems Technology, 2017
- Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates2017
- Estimation, Control, and Planning for Aggressive Flight With a Small Quadrotor With a Single Camera and IMUIEEE Robotics and Automation Letters, 2016
- Optimization‐based autonomous racing of 1:43 scale RC carsOptimal Control Applications and Methods, 2014
- Kinodynamic RRT*: Asymptotically optimal motion planning for robots with linear dynamics2013
- Sampling-based algorithms for optimal motion planningThe International Journal of Robotics Research, 2011
- Minimum snap trajectory generation and control for quadrotors2011
- Motion planning through policy search2003