A reinforcement learning approach to lift generation in flapping MAVs: simulation results

TitleA reinforcement learning approach to lift generation in flapping MAVs: simulation results
Publication TypeConference Paper
Year of Publication2006
AuthorsMotamed, M., and J. Yan
Conference NameRobotics and Automation, 2006. ICRA 2006. Proceedings 2006 IEEE International Conference on
Pagination2150 -2155
Date Publishedmay.
Keywordsaerodynamics, aerospace control, flapping micro aerial vehicles, learning (artificial intelligence), lift generation, quasisteady aerodynamic model, reinforcement learning approach
Abstract

Flapping micro aerial vehicles are interesting in applications where maneuverability is needed in confined spaces. Yet aerodynamics of insect flapping flight is not completely known and the research in this area lacks a suitable aerodynamic model that can be used for control purposes. Reinforcement learning approach is proposed which is inspired from "how" the learning is achieved in real insects in nature. The reinforcement learning controller has been simulated using a quasi-steady aerodynamic model and shown to converge to a flapping motion. The learning capacity and advantages of this approach are also discussed

URLhttp://dx.doi.org/10.1109/ROBOT.2006.1642022
DOI10.1109/ROBOT.2006.1642022

a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949
Email:

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2018 The University of British Columbia