Please use this identifier to cite or link to this item: https://doi.org/10.1109/TRO.2001.855992
Title: COBOS: Cooperative backoff adaptive scheme for multirobot task allocation
Authors: Fua, C.-H.
Ge, S.S. 
Keywords: Cooperative backing off
Disjoint networks
Fault tolerance
Multirobot tasks
Task allocation
Issue Date: Dec-2005
Source: Fua, C.-H., Ge, S.S. (2005-12). COBOS: Cooperative backoff adaptive scheme for multirobot task allocation. IEEE Transactions on Robotics 21 (6) : 1168-1178. ScholarBank@NUS Repository. https://doi.org/10.1109/TRO.2001.855992
Abstract: In this paper, the cooperative backoff adaptive scheme (COBOS) is proposed for task allocation amongst a team of heterogeneous robots. The COBOS operates in regions with limited communication ranges, and is robust against robot malfunctions and uncertain task specifications, with each task potentially requiring multiple robots. The portability of tasks across teams (or when team demography changes) is improved by specifying tasks using basis tasks in a matrix framework. The adaptive feature of COBOS further increases the flexibility of robot teams, allowing robots to adjust their actions based on past experience. In addition, we study the properties of COBOS: operation domain; communication requirements; computational complexity; and solution quality; and compare the scheme with other task-allocation mechanisms. Realistic simulations are carried out to verify the effectiveness of the proposed scheme. © 2005 IEEE.
Source Title: IEEE Transactions on Robotics
URI: http://scholarbank.nus.edu.sg/handle/10635/55311
ISSN: 15523098
DOI: 10.1109/TRO.2001.855992
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

46
checked on Dec 14, 2017

WEB OF SCIENCETM
Citations

28
checked on Nov 18, 2017

Page view(s)

26
checked on Dec 17, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.