Decentralized consensus-making mechanisms based on immune system-application to a behavior arbitration of an autonomous mobile robot

Abstract

Conventional artificial intelligence (AI) systems have been criticized for their brittleness under hostile/dynamically changing environments. Therefore, recently, much attention has been focused on reactive planning systems such as behavior-based AI systems. However, in behavior-based AI approaches, the way to construct a mechanism that realizes adequate arbitration among competence modules is still an open question. In this paper, we propose a new decentralized consensus-making system, inspired by biological immune systems, and we apply our proposed method to a behavior arbitration of an autonomous mobile robot as a practical example. To verify the feasibility of our method, we carry out some experiments. In addition, we propose an adaptation mechanism and try to construct a suitable immune network for adequate action selection.