Autonomous Navigation in Partially Observable Environments Using Hierarchical Q-Learning

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientific

63 Downloads (Pure)

Abstract

Flapping-wing MAVs represent an attractive alternative to conventional designs with rotary wings, since they promise a much higher efficiency in forward flight. However, further insight into the flapping-wing aerodynamics is still needed to get closer to the flight performance observed in natural fliers. Here we present the first step necessary to perform a flow visualization study of the air around the flapping wings of a DelFly II MAV in-flight: a precision position control of flight in a wind-tunnel. We propose a hierarchical control scheme implemented in the open-source Paparazzi UAV autopilot software. Using a decoupling, combined feed-forward and feed-back control approach as a core, we were able to achieve a precision of 2:5 cm for several seconds, which is much beyond the requirements for a time resolved stereo PIV technique.
Original languageEnglish
Title of host publicationProceedings of the International Micro Air Vehicles Conference and Competition 2016
Subtitle of host publicationBeijing, China
PublisherIEEE
Pages70-76
Publication statusPublished - 2016
EventInternational Micro Air Vechicle Competition and Conference 2016 - Beijing, China
Duration: 17 Oct 201621 Oct 2016
http://www.imavs.org/2016/

Conference

ConferenceInternational Micro Air Vechicle Competition and Conference 2016
Abbreviated titleIMAV2016
CountryChina
CityBeijing
Period17/10/1621/10/16
Internet address

Fingerprint Dive into the research topics of 'Autonomous Navigation in Partially Observable Environments Using Hierarchical Q-Learning'. Together they form a unique fingerprint.

Cite this