Title :
Autonomous UUV control via tunably decentralized algorithms
Author :
Sullivan, Keith M. ; Luke, Sean
Author_Institution :
Systems Planning & Anal., Inc., Alexandria, VA, USA
Abstract :
We apply previous studied control algorithms to the cooperative target observation (CTO) task for multiple UUVs. The algorithms are based on k-means clustering and hill climbing, and each are scalable in the degree of decentralization. In the underwater formulation of the CTO problem, k-means is not sensitive to the degree of decentralization, while the hill climber is sensitive. Unlike in previous work, K-means outperformed hill-climbing across all environmental parameters.
Keywords :
decentralised control; mobile robots; multi-robot systems; pattern clustering; remotely operated vehicles; underwater vehicles; autonomous vehicle; cooperative target observation task; hill climbing; k-means clustering; multiple unmanned underwater vehicle; tunably decentralized algorithm; Algorithm design and analysis; Centralized control; Clustering algorithms; Distributed control; Mobile agents; Path planning; Remotely operated vehicles; Sampling methods; Testing; Underwater vehicles;
Conference_Titel :
Autonomous Underwater Vehicles, 2004 IEEE/OES
Print_ISBN :
0-7803-8543-8
DOI :
10.1109/AUV.2004.1431192
