Agent-Based Integrated Decision Making for Autonomous Vehicles in Urban Traffic

We present an approach for integrated decision making of vehicle agents in urban traffic systems. The planning process for a vehicle agent is broken down into two stages: strategic planning for selection of the optimal route and tactical planning for passing the current street in the most optimal manner. Vehicle routing is considered as a stochastic shortest path problem with imperfect knowledge about network conditions. Tactical planning is considered as a problem of collaborative learning with neighbor vehicles.We present planning algorithms for both stages and demonstrate interconnections between them; as well, an example illustrates how the proposed approach may reduce travel time of vehicle agents in urban traffic.