Maintaining ethical resolution in distributed constraint reasoning

Multi-agent systems (MAS) consist of autonomous agents that parcel out different tasks and make decisions in dynamic environments. Distributed constraint satisfaction problem (DisCSP) is the most effective and applicative MAS framework. In DisCSP, each agent is connected to the other agents via constraints and holds its own local constrained problem. Those agents find solutions satisfying their own constraints and the linking ones too by collaborating and exchanging messages holding their instantiations. This formalism does not take into consideration the possibility of the presence of unethical agents which can make irrelevant or even dangerous decisions, especially when human agents are involved in the resolution. In this paper, we propose an extension of the DisCSP into an ethical formalism “E-DisCSP”. It allows to control agents, detect intrusions and apply the convenient actions when an unethical agent is picked up. All these functionalities are done via control framework, in order to maintain the DisCSP resolution as normal as possible. Experimental results show the efficiency of our contribution. The detection rate of unethical agents achieves up to 100%. And the convenient actions’ application allows, to go from 45 to 0% of wrong solutions.