QARTA: An ML-based System for Accurate Map Services

Download PDF

Abstract

Maps services (e.g., routing and store finding) are ubiquitous in widely used applications including navigation systems, ride sharing, and items/food delivery. There are plenty of efforts dedicated to supporting such services through designing more efficient algorithms, e.g., efficient shortest path and range queries. We believe that efficiency is no longer a bottleneck to these map services. Instead, it is the accuracy of the underlying road network and query result. This paper presents QARTA; an open-source full-fledged system for highly accurate and scalable map services. QARTA employs machine learning techniques to construct its own highly accurate map, not only in terms of map topology but more importantly, in terms of edge weights. QARTA also employs machine learning techniques to calibrate its query answers based on contextual information, including transportation modality, location, and time of day/week. QARTA is currently deployed in all Taxis in the State of Qatar and in the third-largest food delivery company in the country, replacing the commercial map service that was in use, and receiving hundreds of thousands of daily API calls with a real-time response time. Experimental evaluation of QARTA in such a real deployment environment shows that QARTA has comparable or higher accuracy than commercial services.