Champion-level drone racing using deep reinforcement learning
Top Cited Papers
Open Access
- 30 August 2023
- journal article
- research article
- Published by Springer Nature in Nature
- Vol. 620 (7976) , 982-987
Abstract
First-person view (FPV) drone racing is a televised sport in which professional competitors pilot high-speed aircraft through a 3D circuit. Each pilot sees the environment from the perspective of their drone by means of video streamed from an onboard camera. Reaching the level of professional pilots with an autonomous drone is challenging because the robot needs to fly at its physical limits while estimating its speed and location in the circuit exclusively from onboard sensors1. Here we introduce Swift, an autonomous system that can race physical vehicles at the level of the human world champions. The system combines deep reinforcement learning (RL) in simulation with data collected in the physical world. Swift competed against three human champions, including the world champions of two international leagues, in real-world head-to-head races. Swift won several races against each of the human champions and demonstrated the fastest recorded race time. This work represents a milestone for mobile robotics and machine intelligence2, which may inspire the deployment of hybrid learning-based solutions in other physical systems.Keywords
This publication has 41 references indexed in Scilit:
- A New Approach to Time-Optimal Path Parameterization Based on Reachability AnalysisIEEE Transactions on Robotics, 2018
- Perception, Guidance, and Navigation for Indoor Autonomous Drone Racing Using Deep LearningIEEE Robotics and Automation Letters, 2018
- Mastering the game of Go without human knowledgeNature, 2017
- The IROS 2016 Competitions [Competitions]IEEE Robotics & Automation Magazine, 2017
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Human-level control through deep reinforcement learningNature, 2015
- Infinitesimal Plane-Based Pose EstimationInternational Journal of Computer Vision, 2014
- Visual-inertial navigation, mapping and localization: A scalable real-time causal approachThe International Journal of Robotics Research, 2011
- The vestibular systemCurrent Biology, 2005