Bio-inspired Decentralized Self-coordination Algorithms for Multi-heterogeneous Specialized Tasks Distribution in Multi-Robot Systems - Foundations on Natural and Artificial Computation - page 38

5.2 Task Allocation
After making the distribution of 10 robots in 4 regions, taking into account that
each region has 3 types of tasks, we make the task allocation to robots using
equation 1, obtaining as result the probability that the robot r i will perform
task j of type t . In Fig. 4 we present the evolution of the system performance
index for each type of task and for each region.
Each time that a sub-team of robots completes all tasks associated with a
region, the current probability of that region is set to 0, for not taking into
account the region in the next distribution of robots.
6 Conclusions and Further Work
In this paper we have proposed an experimental scenario in which several het-
erogeneous and specialized tasks distributed in different regions have to be exe-
cuted by a team of heterogeneous mobile robots. We have focused our interest
on truly decentralized solutions in the sense that the robots have to select in
an autonomous and individual manner the existing tasks so that all the tasks
are optimally executed without the intervention of any global and central tasks
scheduler. We have shown that the bio-inspired threshold model can be eciently
applied to solve this self-coordination problem in multi-robot systems.
We also plan to experiment in the future with alternative methods like Learn-
ing Automata-based probabilistic reinforcement learning algorithms [20] as we
believe they are well tailored to solve hard on-line learning problems like the one
tackled in this paper.
References
1. Parker, L.E.: Multiple Mobile Robot Systems. In: Bruno, S., Oussama, K. (eds.)
Springer Handbook of Robotics, pp. 921-941. Springer, Heidelberg (2008)
2. Braunl, T.: Embedded Robotics: Mobile Robot Design and Applications with Em-
bedded Systems, p. 246 (2006)
3. Huntsberger, T., Trebi-Ollennu, A., Aghazarian, H., Schenker, P.: Distributed Con-
trol of Multi-robot System Engaged in Tightly Coupled Tasks. journal autonomous
robots, 79-92 (2004)
4. Farinelli, A., Locchi, L., Nardi, D.: Multirobot Systems: A Classification Focused
on Coordination. IEEE Transactions on Systems, Man and Cybernetics, 2015-2028
(2004)
5. Oster, G., Wilson, E.: Caste and Ecology in the Social Insects. In: Monographs in
Population Biology. Princeton Univ. Press, Princeton (1978)
6. Robinson, G.: Regulation of Division of Labor in Insect Societies. Annu. Rev.
Entomol., 637-665 (1992)
7. Price, R., Tino, P.: Evaluation of Adaptive Nature Inspired Task Allocation Against
Alternate Decentralised Multiagent Strategies. In: Yao, X., Burke, E.K., Lozano,
J.A., Smith, J., Merelo-Guervos, J.J., Bullinaria, J.A., Rowe, J.E., Tino, P., Kaban,
A., Schwefel, H.-P. (eds.) PPSN 2004. LNCS, vol. 3242, pp. 982-990. Springer,
Heidelberg (2004)