Experiments in learning helicopter control from a pilot
Buskey, Gregg, Roberts, Jonathan M., & Wyeth, Gordon (2003) Experiments in learning helicopter control from a pilot. In Proceedings International Conference on Field and Service Robotics (FSR 2003), Lake Yamanaka, Japan, pp. 77-82.
Administrators only | Request a copy from author
This paper details the development of a machine learning system which uses the helicopter state and the actions of an instructing pilot to synthesise helicopter control modules online. Aggressive destabilisation/restabilisation sequences are used for training, such that a wide state space envelope is covered during training. The performance of heading, roll, pitch, height and lateral velocity control learning is presented using our Xcell 60 experimental platform. The helicopter is demonstrated to be stabilised on all axes using the “learning from a pilot” technique. To our knowledge, this is the first time a “learning from a pilot” technique has been successfully applied to all axes.
Impact and interest:
Citation counts are sourced monthly from and citation databases.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
|Item Type:||Conference Paper|
|Additional Information:||Also available in Springer Tracts in Advanced Robotics, STAR, Field Service Robotics, 2006, Volume 24/2006, 267-276|
|Subjects:||Australian and New Zealand Standard Research Classification > ENGINEERING (090000) > AEROSPACE ENGINEERING (090100) > Aircraft Performance and Flight Control Systems (090104)
Australian and New Zealand Standard Research Classification > ENGINEERING (090000) > ELECTRICAL AND ELECTRONIC ENGINEERING (090600)
|Divisions:||Current > Schools > School of Electrical Engineering & Computer Science
Current > Institutes > Institute for Future Environments
Current > QUT Faculties and Divisions > Science & Engineering Faculty
|Copyright Owner:||Copyright 2003 [please consult author]|
|Deposited On:||06 Oct 2010 00:02|
|Last Modified:||07 Jun 2015 06:43|
Repository Staff Only: item control page