Navigating the Last Mile with Crowdsourced Driving Information

With digital maps of the transport network and realtime traffic updates, today's navigation services provide good quality routes in the major route level. Once entering the last mile near the destination, they unfortunately can be ineffective and, instead, local drivers often have a better understanding of the routes there. Given the deep penetration of 3G/4G mobile networks, drivers are now well connected anytime and anywhere; they are readily to access information from the Internet and share information to the community. These motivate our design of CrowdNavi, a complementary service to existing navigation systems, seeking to combat the last mile puzzle. CrowdNavi collects the crowdsourced driving information to identify the local driving patterns, and recommend the best local routes to reach the destinations. In this paper, we present the architectural design of CrowdNavi and the algorithms for different modules, including identifying the last segment from the drivers trajectories, scoring the landmark and locating best routes with user preferences. We have implemented the CrowdNavi app on Android OS, and have examined its performance under various circumstances. The experimental results demonstrate its superiority in navigating drivers in the last segment.