Spatio-temporal Matching for Urban Transportation Applications

In this work we present a search problem in which mobile agents are searching for static resources. Each agent wants to obtain exactly one resource. Both agents and resources are spatially located on a road network and the movement of the agents is constrained to the road network. This problem applies to various transportation applications including: vehicles (agents) searching for parking (resources) and taxicabs (agents) searching for clients to pick up (resources). In this work, we design search algorithms for such scenarios. We model the problem in different scenarios that vary based on the level of information that is available to the agents. These scenarios vary from: scenarios in which agents have complete information about other agents and resources, to scenarios in which agents only have access to a fraction of the data about the availability of resources (uncertain data). We also propose pricing schemes that incentivize vehicles to search for resources in a way that benefits the system and the environment. Our proposed algorithms were tested in a simulation environment that uses real-world data. We were able to attain up to 40% improvements over greedy approaches that were tested against our algorithms.