Modeling intelligent transportation systems with multi-agent on SOA

摘要

Intelligent transportation systems (ITS) based on multi-agent technology are becoming a important approach to solve complex transportation problems. The geographically distributed nature of agents in heterogeneous environments leads to implementation difficulties such as interoperability among agents, which makes demand for a unified software platform as an underlying infrastructure. This paper presents a model of intelligent transportation systems with multi-agent based on SOA. The model comprises four main parts: infrastructure, services, element agents, and coordination agents. The agents in this model are categorized into different levels and groups including organization agent, regional control agent, road intersection agent, road segment control agent, vehicle agent to accomplish different functions and targets. The paper discusses the architecture of agents and interaction mechanism among the agents. The multi-agent ITS based on SOA can achieve platform-independent, loosely coupled, and interoperability and legacy reuse in distributed and heterogeneous transportation systems over internet.