Aarhus University Seal / Aarhus Universitets segl

Erdal Kayacan

Planning swift maneuvers of quadcopter using motion primitives explored by reinforcement learning

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

In this work, we propose a novel, learning-based approach for swift maneuver planning of unmanned aerial vehicles using motion primitives. Our approach is composed of two main stages: learning a set of motion primitives during offline training first, and utilization of them for online planning of fast maneuvers thereafter. We propose a compact disposition of motion primitives which consists of roll, pitch, and yaw motions to build up a simple yet effective representation for learning. Thanks to this compact representation, our method retains an easily transferable, reproducible, and referable knowledge which caters for real-time swift maneuver planning. We compare our approach with the current state-of-the-art methods for planning and control, and show improved navigation time performance up to 25 % in challenging obstacle courses. We validate our approach through software-in-the-loop Gazebo simulations and real flight tests with Diatone FPV250 Quadcopter equipped with PX4 FMU.

TitelProceedings of the American Control Conference : 2019 American Control Conference, ACC 2019
Antal sider7
ISBN (Elektronisk)9781538679265
StatusUdgivet - 2019
Begivenhed2019 American Control Conference, ACC 2019 - Philadelphia, USA
Varighed: 10 jul. 201912 jul. 2019


Konference2019 American Control Conference, ACC 2019
SponsorBoeing, et al., GE Research, General Motors co, Mitsubishi Electric Research Laboratory (MERL), United Technologies Research Center (UTRC)

Se relationer på Aarhus Universitet Citationsformater

ID: 172716335