Search

Recent studies show that 85% of women have changed their traveled routes to avoid harassment and assault. Despite this, current mapping tools do not empower users with information to take charge of their personal safety. We propose SafeRoute, a novel solution to the problem of navigating cities and avoiding street harassment and crime. Unlike other street navigation applications, SafeRoute introduces a new type of path generation via deep reinforcement learning. This enables us to successfully optimize for multi-criteria path-finding and incorporate representation learning within our framework. Our agent learns to pick favorable streets to create a safe and short path with a reward function that incorporates safety and efficiency. Given access to recent crime reports in many urban cities, we train our model for experiments in Boston, New York, and San Francisco. We test our model on areas of these cities, specifically the populated downtown regions with high foot traffic. We evaluate SafeRoute and successfully improve over state-of-the-art methods by up to 17% in local average distance from crimes while decreasing path length by up to 7%. [ABSTRACT FROM AUTHOR]

We present the Virtual City Explorer (VCE), an online crowdsourcing platform for the collection of rich geotagged information in urban environments. Compared to other volunteered geographic information approaches, which are constrained by the number and availability of mapping enthusiasts on the ground, the VCE uses digital street imagery to allow people to virtually explore a city from anywhere in the world, using a browser or a mobile phone. In addition, contributions in VCE are designed as paid microtasks—small jobs that can be carried out without any specific knowledge of the local area or previous mapping expertise in exchange for a fee. We tested the VCE in two cities to map points of interest (PoIs) in transport and mobility, using FigureEight to recruit participants. We were able to show that our platform enables crowdworkers to submit PoI location seamlessly, cover almost all of the tested areas, and discover several PoIs not reported by other approaches. This allows the VCE to complement existing approaches that leverage experts or grassroot communities. [ABSTRACT FROM AUTHOR]