A Helicopter named Dolly : behavioural cloning for autonomous helicopter control


Autoria(s): Buskey, Gregg; Roberts, Jonathan M.; Wyeth, Gordon
Contribuinte(s)

Roberts, Jonathan

Wyeth, Gordon

Data(s)

2003

Resumo

This paper considers the pros and cons of using Behavioural cloning for the development of low-level helicopter automation modules. Over the course of this project several Behavioural cloning approaches have been investigated. The results of the most effective Behavioural cloning approach are then compared to PID modules designed for the same aircraft. The comparison takes into consideration development time, reliability, and control performance. It has been found that Behavioural cloning techniques employing local approximators and a wide state-space coverage during training can produce stabilising control modules in less time than tuning PID controllers. However, performance and reliabity deficits have been found to exist with the Behavioural Cloning, attributable largely to the time variant nature of the dynamics due to the operating environment, and the pilot actions being poor for teaching. The final conclusion drawn here is that tuning PID modules remains superior to behavioural cloning for low-level helicopter automation.

Formato

application/pdf

Identificador

http://eprints.qut.edu.au/32824/

Publicador

Australian Robotics and Automation Association Inc

Relação

http://eprints.qut.edu.au/32824/1/c32824.pdf

http://www.araa.asn.au/acra/acra2003/papers/41.pdf

Buskey, Gregg, Roberts, Jonathan M., & Wyeth, Gordon (2003) A Helicopter named Dolly : behavioural cloning for autonomous helicopter control. In Roberts, Jonathan & Wyeth, Gordon (Eds.) Proceedings of the 2003 Australasian Conference on Robotics and Automation, Australian Robotics and Automation Association Inc, Brisbane, Queensland.

Direitos

Copyright 2003 [please consult the authors]

Fonte

School of Electrical Engineering & Computer Science; Institute for Future Environments; Science & Engineering Faculty

Palavras-Chave #080101 Adaptive Agents and Intelligent Robotics
Tipo

Conference Paper