Aarhus Universitets segl

Event-based Navigation for Autonomous Drone Racing with Sparse Gated Recurrent Network

Publikation: Bidrag til bog/antologi/rapport/proceedingKonferencebidrag i proceedingsForskningpeer review

Event-based vision has already revolutionized the perception task for robots by promising faster response, lower energy consumption, and lower bandwidth without introducing motion blur. In this work, a novel deep learning method based on gated recurrent units utilizing sparse convolutions for detecting gates in a race track is proposed using event-based vision for the autonomous drone racing problem. We demonstrate the efficiency and efficacy of the perception pipeline on a real robot platform that can safely navigate a typical autonomous drone racing track in real-time. Throughout the experiments, we show that the event-based vision with the proposed gated recurrent unit and pretrained models on simulated event data significantly improve the gate detection precision. Furthermore, an event-based drone racing dataset11The code and data will be available at https://github.com/open-airlab/neuromorphic-au-drone-racing.git consisting of both simulated and real data sequences is publicly released.

Titel2022 European Control Conference (ECC)
Antal sider7
Udgivelsesåraug. 2022
ISBN (Elektronisk)9783907144077
StatusUdgivet - aug. 2022
Begivenhed2022 European Control Conference, ECC 2022 - London, Storbritannien
Varighed: 12 jul. 202215 jul. 2022


Konference2022 European Control Conference, ECC 2022
Serietitel2022 European Control Conference, ECC 2022

Bibliografisk note

Funding Information:
The authors are grateful to Daniel Gehrig, Nico Mes-sikommer, and Davide Scaramuzza for the fruitful scientific discussions and profound comments. This work is supported by Aarhus University, Department of Electrical and Computer Engineering (28173) and the European Union’s Horizon 2020 Research and Innovation Program (OpenDR) under Grant 871449. This publication reflects the authors’ views only. The European Commission is not responsible for any use that may be made of the information it contains.

Publisher Copyright:
© 2022 EUCA.

Se relationer på Aarhus Universitet Citationsformater

ID: 295279091