Learning implicit models during target pursuit

Chris Gaskett, Peter Brown, Gordon Cheng, Alexander Zelinsky

Publikation: Beitrag in FachzeitschriftKonferenzartikelBegutachtung

2 Zitate (Scopus)

Abstract

Smooth control using an active vision head's verge-axis joint is performed through continuous state and action reinforcement learning. The system learns to perform visual servoing based on rewards given relative to tracking performance. The learned controller compensates for the velocity of the target and performs lag-free pursuit of a swinging target. By comparing controllers exposed to different environments we show that the controller is predicting the motion of the target by forming an implicit model of the target's motion. Experimental results are presented that demonstrate the advantages and disadvantages of implicit modelling.

OriginalspracheEnglisch
Seiten (von - bis)4122-4129
Seitenumfang8
FachzeitschriftProceedings - IEEE International Conference on Robotics and Automation
Jahrgang3
PublikationsstatusVeröffentlicht - 2003
Extern publiziertJa
Veranstaltung2003 IEEE International Conference on Robotics and Automation - Taipei, Taiwan
Dauer: 14 Sept. 200319 Sept. 2003

Fingerprint

Untersuchen Sie die Forschungsthemen von „Learning implicit models during target pursuit“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren