Research on robot motion control based on local weighted kNN-TD reinforcement learning

Author

Han, Fei ; Jin, Lu ; Yang, Yuequan ; Cao, Zhiqiang ; Zhang, Tianping

Author_Institution

Coll. of Inf. Eng., Yangzhou Univ., Yangzhou, China

fYear

2012

fDate

6-8 July 2012

Firstpage

3648

Lastpage

3651

Abstract

Learning is an important capability for an individual robot, which provides an effective way for understanding, planning, and decision-making in a complex environment. For robot motion control, a local weighted k-nearest neighbors states selection method based on environment information and task information is presented. Based on this method, TD reinforcement learning algorithm is combined to reduce the misclassified probability of kNN-TD method, which is finally verified by the simulations.

Keywords

decision making; learning (artificial intelligence); mobile robots; motion control; probability; decision making; environment information; local weighted k-nearest neighbor states selection method; local weighted kNN-TD reinforcement learning; misclassified probability reduction; robot motion control; task information; Automation; Computer science; Educational institutions; Learning; Markov processes; Robot motion; k-nearest neighbors; motion control; reinforcement learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation (WCICA), 2012 10th World Congress on

Conference_Location

Beijing

Print_ISBN

978-1-4673-1397-1

Type

conf

DOI

10.1109/WCICA.2012.6359080

Filename

6359080