Enhanced Shortest Path Computation for Multiagent-based Intermodal Transport Planning in Dynamic Environments

This paper addresses improved urban mobility using multiagent simulation. We provide a description of the agent model and the routing infrastructure as a step towards a rich model of the interactions that happen in intermodal transport planning tasks. The multiagent model is generic in the sense that different public and individual transport agents and transportation agencies can be added and parameterized on-the-fly. It integrates planning with execution. We show that a sequence of calls to Dijkstra’s single-source shortest-paths algorithm is crucial for planning and provide an efficient memory-less implementation with radix heaps in order to make this application feasible with respect to scalability. As a case study, we implement a scenario for Bangalore (India), starting on a higher level of abstraction and drilling down to a running program.