Print Email Facebook Twitter Autonomous Navigation in Partially Observable Environments Using Hierarchical Q-Learning Title Autonomous Navigation in Partially Observable Environments Using Hierarchical Q-Learning Author Zhou, Y. (TU Delft Control & Simulation) van Kampen, E. (TU Delft Control & Simulation) Chu, Q. P. (TU Delft Control & Simulation) Date 2016 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. To reference this document use: http://resolver.tudelft.nl/uuid:7b5c16a1-080e-48ee-83b9-ca4189d10994 Publisher IEEE Embargo date 2018-01-01 Source Proceedings of the International Micro Air Vehicles Conference and Competition 2016: Beijing, China Event International Micro Air Vechicle Competition and Conference 2016, 2016-10-17 → 2016-10-21, Beijing, China Part of collection Institutional Repository Document type conference paper Rights © 2016 Y. Zhou, E. van Kampen, Q. P. Chu Files PDF C2_Incremental_Model_Base ... ontrol.pdf 443.84 KB Close viewer /islandora/object/uuid:7b5c16a1-080e-48ee-83b9-ca4189d10994/datastream/OBJ/view