Vehicle Inertial Tracking via Mobile Crowdsensing: Experience and Enhancement

Nowadays, GPS and other global navigation satellite systems (GNSSs) have been widely developed, enabling accurate and convenient outdoor location-based services for vehicles. However, there is still a range of areas in an urban city that cannot be covered by satellites, e.g., large-scale tunnels, underground parking lots, and multilevel flyovers. Current vehicle inertial tracking methods always rely on dead-reckoning, but their performances are seriously affected by intrinsic fluctuations and external disturbances. Based on our experiments with thousands of smartphones, we summarize three threats for vehicle inertial tracking, i.e., arbitrary and unknown placements of smartphones during driving, volatile and inconstant noises on low-quality inertial sensors in commodity smartphones, and a diversity of smartphones and vehicles via crowdsensing. In this article, we explore a novel smartphone-based inertial learning framework to infer a vehicle’s location in real time. It contains a coordinate transformation algorithm to yield vehicle’s movements from smartphone’s inertial readings, an inertial sequence learning model to train and infer the trajectory instead of double integrations, and a customized model refinement mechanism to improve the tracking accuracy for individual drivers. Extensive experiments on the DiDi ride-hailing platform in two large cities have proved the effectiveness of our solution. In addition, our approach has been deployed on DiDi real-world mobile applications in 7.59 million devices and conducted 4.26 billion location inferences every day.