Aerospace Control and Guidance Systems Committee

Announcements


You must first log in to access prior meeting presentations, register for a meeting, or nominate some for the Ward Award.


If you do not have a login account, or cannot remember the email address associated with your account, please click on the Application Form link below.

 
 

Login

 

E-mail: 

 

Password: 


Forgot your password?

Application Form


 

Site Search

Search our site:
 
 

Upcoming Events


Register for Meeting 133
(please log in first)

 
 

Photos


Meeting Highlights New!

Subcommittee S

 
 

Prior Meetings

Abstracts may be viewed by anyone. Presentations are only available to active members who have logged in.

Meeting 133
(coming soon)

Meeting 132
(coming soon)

Meeting 131

Meeting 130

Meeting 129

Meeting 128

Meeting 127

Meeting 126

Meeting 125

Meeting 124

Meeting 123

Meeting 122

Meeting 121

Meeting 120

Meeting 119

Meeting 118

Meeting 117

Meeting 116

Meeting 115

Meeting 114

Meeting 113

Meeting 112

Meeting 111

Meeting 110

Meeting 109

Meeting 108

Meeting 107

Meeting 106

Meeting 105

Meeting 104

Meeting 103

Meeting 102

Meeting 101

Meeting 100

Meeting 99

Meeting 98

Meeting 97

Meeting 96

Meeting 95

Meeting 94

Meeting 93

Meeting 92

 
HomeWard Memorial AwardPlanning Advisory BoardDownloadsConstitution and By-LawsAboutHistoryContact Us

  ← Return to agenda

MeetingACGS Committee Meeting 107 - Boulder - March 2011
Agenda Location7 SUBCOMMITTEE D – DYNAMICS, COMPUTATIONS, AND ANALYSIS
7.4 Autonomous Extreme Aerobatics with RC helicopters Rotorcraft
TitleAutonomous Extreme Aerobatics with RC helicopters Rotorcraft ** Best Presentation Award **
PresenterPieter Abbeel
AffiliationUC Berkeley
Available Downloads*presentation
*Downloads are available to members who are logged in and either Active or attended this meeting.
AbstractPieter Abbeel
Department of Electrical Engineering and Computer Sciences
University of California, Berkeley

Abstract

For many robotic systems human operators still significantly outperform autonomous operation. "Apprenticeship Learning" is a new approach to high-performance robot control based on learning for control from ensembles of expert human demonstrations. In this talk I'll present the theory of our apprenticeship learning algorithms as well as experimental results in autonomous helicopter flight. Apprenticeship learning has enabled the most advanced helicopter aerobatics to-date, including maneuvers such as chaos, tic-tocs, and auto-rotation landings which only exceptional expert human pilots can fly.



Copyright © 2024 | Question? webmaster@acgsc.org