Autonomous Inverted Helicopter Flight via Reinforcement Learning

Autor:	Andrew Y. Ng, Eric Berger, Eric Liang, Mark Diel, Varun Ganapathi, Adam Coates, Jamie Schulte, Ben Tse
Rok vydání:	2006
Předmět:	Nonlinear system Low speed Control theory Computer science Nonlinear model Reinforcement learning ComputerSystemsOrganization_SPECIAL-PURPOSEANDAPPLICATION-BASEDSYSTEMS ComputerApplications_COMPUTERSINOTHERSYSTEMS Control engineering Reinforcement learning algorithm GeneralLiterature_MISCELLANEOUS
Zdroj:	Springer Tracts in Advanced Robotics ISBN: 9783540288169 ISER
Popis:	Helicopters have highly stochastic, nonlinear, dynamics, and autonomous helicopter flight is widely regarded to be a challenging control problem. As helicopters are highly unstable at low speeds, it is particularly difficult to design controllers for low speed aerobatic maneuvers. In this paper, we describe a successful application of reinforcement learning to designing a controller for sustained inverted flight on an autonomous helicopter. Using data collected from the helicopter in flight, we began by learning a stochastic, nonlinear model of the helicopter’s dynamics. Then, a reinforcement learning algorithm was applied to automatically learn a controller for autonomous inverted hovering. Finally, the resulting controller was successfully tested on our autonomous helicopter platform.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::fbb5bbf396e1dcc5c720ca74dac0002f https://doi.org/10.1007/11552246_35 Zobrazit plný text záznamu