Safe Navigation in Urban Environments
Résumé
Advancements in mobile technology and computing have fostered the collection of a large number of civic datasets that capture the pulse of urban life. Furthermore, the open government and data initiative has led many local authorities to make these datasets publicly available, hoping to drive innovation that will further improve the quality of life for the city dwellers. In this paper, we develop a novel application that utilizes crime data to provide safe urban navigation. Given a model that allows us to estimate the relative probability of a crime on any road segment, we define two variants of the SafePaths problem where the goal is to find a short and low-risk path between a source and a destination locations. Since both the length and the risk of the path are equally important and they cannot be combined into a single objective, we approach the urban-navigation problem
as a biobjective shortest path problem. Our algorithms aim to output a small set of paths that provide tradeoffs between distance and safety. While the solution space of such biobjective problems can be exponentially large, we design efficient algorithms that effectively exploit its structure and geometry. We enhance these algorithms with early-stopping criteria, which in practice lead to four times shorter running times with minimal sacrifices in the information content they provide to the user. In addition, using crime data from Chicago and Philadelphia we develop the required risk model for their street urban networks. Our experiments with this data demonstrate the efficacy of our algorithms and their practical applicability.
Domaines
Intelligence artificielle [cs.AI]
Origine : Fichiers produits par l'(les) auteur(s)
Loading...