We consider an integrated decision making process of autonomous vehicles in agent-oriented simulation of urban traffic systems. In our approach, the planning process for a vehicle agent is separated into two stages: strategic planning and tactical planning. During the strategic planning stage the vehicle agents constructs the optimal route from source to destination; during the tactical planning stage the operative decisions such as speed regulation and lane change are considered. For strategic planning we modify the stochastic shortest path algorithm with imperfect knowledge about network conditions. For tactical planning we apply distributed multiagent reinforcement learning with other vehicles at the same edge. We present planning algorithms for both stages and demonstrate interconnections between them; an example illustrates how the proposed approach may reduce travel time of vehicle agents in urban traffic.
International audienceThis chapter addresses how agent organisations can improve and accelerate coordination processes in open environments. A state-of-art of recent proposals for describing agent organisations is given, relating the different methodologies and formal approaches for defining agent organisations in an explicit way. As example, four different proposals developed within the COST action IC0801 are detailed: (i) the MOISE organisation Model, which provides structural, functional and normative specifications of an organisation, and it is integrated in an Organisation Management infrastructure; (ii) the Virtual Organisation Model, which describes the structural, functional, dynamical, environmental and normative dimensions of an organisation, and it is complemented by the Virtual Organisation Formalization; (iii) the Agent-Oriented Modelling for sociotechnical systems, which are organisations consisting of human and man-made agents; and (iv) the AAOL agent architecture, in which groups of autonomous agents are organized in Localities. This chapter proposes a global comparison of different existing organisational models with the four detailed models in terms of the different description dimensions they propose
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.