Research on Mental Coefficient of a Multi-Agent Negotiation Model

Abstract

In Multi-Agent system, negotiations model was commonly used by contract net. A multi-agent negotiation model based on the acquaintance coalition and the mental coefficient contract net protocol are presented to improve the efficiency of negotiation. The structure of the multi-agent negotiation model is given to support the acquaintance coalition contract net protocol. The trust degree parameter, familiar degree, reliability degree, busy degree of mental state, and the update rules are introduced. Finally, through an example and analysis of a Robot soccer system which uses the model, improvements of the negotiation efficiency and negotiation communication traffic is proven. © Springer-Verlag Berlin Heidelberg 2014.