Self-Regulation in Self-Organising Multi-Agent Systems for Adaptive and Intelligent Manufacturing Control

G. Clair , Marie-Pierre Gleizes (1) , Elsy Kaddoum (1) , Gauthier Picard (2)

1 IRIT - Institut de recherche en informatique de Toulouse
2 SMA-ENSMSE - Département Systèmes Multi-Agents

In this paper, we explore the potential of distributed satisfaction techniques as to provide self-regulated manufacturing control. This work relies on a DisCSP-based modeling distributed among agents (e.g. machines) having enough and reasoning capabilities to cooperate and negotiate for a committed schedule. This approach is used to dynamically regulate the system (the network of machines) when perturbations occur (machine break-out, operator or container unavailability, or even priority command). Thus, for these machines, embodied intelligence and autonomy are a mean to provide a more flexible and adaptive manufacturing network. In this paper, we present two different multi-agent models and two extensions of well-known DisCSP solvers. Experiments using a dedicated simulation platform, MASC, are presented and discussed.

G. Clair, Marie-Pierre Gleizes, Elsy Kaddoum, Gauthier Picard. Self-Regulation in Self-Organising Multi-Agent Systems for Adaptive and Intelligent Manufacturing Control. Second IEEE International Conference on Self-Adaption and Self-Organization (SASO 2008), Oct 2008, Venise, Italy. p. 107 - 116, ⟨10.1109/SASO.2008.19⟩. ⟨hal-00405592⟩