We consider the real-time routing of driverless vehicles in an on-demand transit transportation system with time window. Because fast dispatching decisions are required, decentralized decisions system are generally used in these contexts. For that purpose, we introduce a new multi agent-based simulation model where intelligent vehicle agents determine their specific routes and which transportation requests to serve. They interact with passengers, who strive for minimum waiting time. Our approach offers several advantages: it is fast, make it easy for vehicles to determine their specific routes and needs little information for vehicles. We propose also a specific algorithm for the independent vehicles’agent in order to determine their specific routes. Preliminaries computational tests of our multi-agent model and our developed algorithm prove that our approach is very promising.