QARTA: An ML-based System for Accurate Map Services

Maps services are ubiquitous in widely used applications including navigation systems, ride sharing, and items/food delivery. Though there are plenty of efforts to support such services through designing more efficient algorithms, we believe that efficiency is no longer a bottleneck to these 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 and the third largest food delivery company in the State of Qatar, replacing the commercial map service that was in use, and responding in real-time to hundreds of thousands of daily API calls. Experimental evaluation of QARTA shows its comparable or higher accuracy than commercial services. PVLDB Reference Format: Mashaal Musleh, Sofiane Abbar, Rade Stanojevic, Mohamed Mokbel. QARTA: An ML-based System for Accurate Map Services. PVLDB, 14(11):

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Ugur Demiryurek,et al.  PerNav: A Route Summarization Framework for Personalized Navigation , 2016, SIGMOD Conference.

[3]  Nick Koudas,et al.  Distributed Processing of k Shortest Path Queries over Dynamic Road Networks , 2020, SIGMOD Conference.

[4]  Sofiane Abbar,et al.  Robust Road Map Inference through Network Alignment of Trajectories , 2018, SDM.

[5]  Filippo Furfaro,et al.  Exploiting Integrity Constraints for Cleaning Trajectories of RFID-Monitored Objects , 2016, ACM Trans. Database Syst..

[6]  James Biagioni,et al.  Inferring Road Maps from Global Positioning System Traces , 2012 .

[7]  Haris N. Koutsopoulos,et al.  Estimation of Arterial Travel Time from Automatic Number Plate Recognition Data , 2013 .

[8]  Yanjie Li,et al.  Efficient map reconstruction and augmentation via topological methods , 2015, SIGSPATIAL/GIS.

[9]  Arthur E. Hoerl,et al.  Ridge Regression: Biased Estimation for Nonorthogonal Problems , 2000, Technometrics.

[10]  Catherine Dolbear,et al.  What's So Special about Spatial? , 2007, The Geospatial Web.

[11]  Chao Chen,et al.  TripImputor: Real-Time Imputing Taxi Trip Purpose Leveraging Multi-Sourced Urban Data , 2018, IEEE Transactions on Intelligent Transportation Systems.

[12]  Xiaofang Zhou,et al.  Trajectories know where map is wrong: an iterative framework for map-trajectory co-optimisation , 2019, World Wide Web.

[13]  Sofiane Abbar,et al.  Traffic routing in the ever-changing city of Doha , 2021, Commun. ACM.

[14]  Shiming Xiang,et al.  Automatic Road Detection and Centerline Extraction via Cascaded End-to-End Convolutional Neural Network , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Erin W. Chambers,et al.  Map-matching using shortest paths , 2018, IWISC.

[16]  Christian S. Jensen,et al.  Path Cost Distribution Estimation Using Trajectory Data , 2016, Proc. VLDB Endow..

[17]  Mohamed F. Mokbel,et al.  Machine Learning Meets Big Spatial Data , 2020, 2020 IEEE 36th International Conference on Data Engineering (ICDE).

[18]  Masashi Sugiyama,et al.  Trajectory Regression on Road Networks , 2011, AAAI.

[19]  Fangfang Zheng,et al.  Urban link travel time estimation based on sparse probe vehicle data , 2013 .

[20]  Jaana Kekäläinen,et al.  IR evaluation methods for retrieving highly relevant documents , 2000, SIGIR '00.

[21]  Christian S. Jensen,et al.  Fast stochastic routing under time-varying uncertainty , 2019, The VLDB Journal.

[22]  Rade Stanojevic,et al.  MapReuse: Recycling Routing API Queries , 2019, 2019 20th IEEE International Conference on Mobile Data Management (MDM).

[23]  Christian S. Jensen,et al.  PACE: a PAth-CEntric paradigm for stochastic path finding , 2017, The VLDB Journal.

[24]  Christian S. Jensen,et al.  Risk-aware path selection with time-varying, uncertain travel costs: a time series approach , 2018, The VLDB Journal.

[25]  Christian S. Jensen,et al.  Anytime stochastic routing with hybrid learning , 2020, Proc. VLDB Endow..

[26]  Jacek Malczewski,et al.  Quality Evaluation of Volunteered Geographic Information: The Case of OpenStreetMap , 2017 .

[27]  Christian S. Jensen,et al.  Stochastic Weight Completion for Road Networks Using Graph Convolutional Networks , 2019, 2019 IEEE 35th International Conference on Data Engineering (ICDE).

[28]  Cheng Long,et al.  Learning to Generate Maps from Trajectories , 2020, AAAI.

[29]  Xiaofang Zhou,et al.  A Survey on Map-Matching Algorithms , 2019, ADC.

[30]  Christian S. Jensen,et al.  Learning to Route with Sparse Trajectory Sets , 2018, 2018 IEEE 34th International Conference on Data Engineering (ICDE).

[31]  Heng Tao Shen,et al.  IF-Matching: Towards Accurate Map-Matching with Information Fusion , 2017, IEEE Transactions on Knowledge and Data Engineering.

[32]  Xing Xie,et al.  Reducing Uncertainty of Low-Sampling-Rate Trajectories , 2012, 2012 IEEE 28th International Conference on Data Engineering.

[33]  Zhifeng Bao,et al.  A Data-Driven Approach for GPS Trajectory Data Cleaning , 2020, DASFAA.

[34]  Lionel M. Ni,et al.  Time-Dependent Trajectory Regression on Road Networks via Multi-Task Learning , 2013, AAAI.

[35]  Christian S. Jensen,et al.  Context-aware, preference-based vehicle routing , 2020, The VLDB Journal.

[36]  Sofiane Abbar,et al.  Road Network Fusion for Incremental Map Updates , 2018, LBS.

[37]  Philip S. Yu,et al.  Time Series Data Cleaning: From Anomaly Detection to Anomaly Repairing , 2017, Proc. VLDB Endow..

[38]  Leonidas J. Guibas,et al.  City-Scale Map Creation and Updating using GPS Collections , 2016, KDD.

[39]  David J. DeWitt,et al.  RoadTracer: Automatic Extraction of Road Networks from Aerial Images , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[41]  Leonidas J. Guibas,et al.  Knowledge-based trajectory completion from sparse GPS samples , 2016, SIGSPATIAL/GIS.

[42]  Shashi Shekhar,et al.  Time-Aggregated Graphs for Modeling Spatio-temporal Networks , 2006, J. Data Semant..

[43]  Xiaofang Zhou,et al.  Fast Query Decomposition for Batch Shortest Path Processing in Road Networks , 2020, 2020 IEEE 36th International Conference on Data Engineering (ICDE).

[44]  Cyrus Shahabi,et al.  Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting , 2017, ICLR.

[45]  Pengpeng Zhao,et al.  LC-RNN: A Deep Learning Model for Traffic Speed Prediction , 2018, IJCAI.

[46]  Leonidas J. Guibas,et al.  Large-scale joint map matching of GPS traces , 2013, SIGSPATIAL/GIS.

[47]  Shuigeng Zhou,et al.  Shortest Path and Distance Queries on Road Networks: An Experimental Evaluation , 2012, Proc. VLDB Endow..

[48]  P. Abbeel,et al.  Path and travel time inference from GPS probe vehicle data , 2009 .

[49]  Sofiane Abbar,et al.  W-edge: weighing the edges of the road network , 2018, SIGSPATIAL/GIS.

[50]  Chun Liu,et al.  Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imagery , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  Rade Stanojevic,et al.  STAD: Spatio-Temporal Adjustment of Traffic-Oblivious Travel-Time Estimation , 2020, 2020 21st IEEE International Conference on Mobile Data Management (MDM).

[52]  Shashi Shekhar,et al.  Spatial big data for eco-routing services: computational challenges and accomplishments , 2015, SIGSPACIAL.

[53]  Sofiane Abbar,et al.  RoadRunner: improving the precision of road network inference from GPS trajectories , 2018, SIGSPATIAL/GIS.

[54]  Niloy Ganguly,et al.  Link Travel Time Prediction from Large Scale Endpoint Data , 2017, SIGSPATIAL/GIS.

[55]  Muhammad Aamir Cheema,et al.  Continuously monitoring alternative shortest paths on road networks , 2020, Proc. VLDB Endow..

[56]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[57]  Stefan Edelkamp,et al.  Route Planning and Map Inference with Global Positioning Traces , 2003, Computer Science in Perspective.

[58]  Hua Lu,et al.  Managing Evolving Uncertainty in Trajectory Databases , 2014, IEEE Transactions on Knowledge and Data Engineering.

[59]  Dieter Pfoser,et al.  On Map-Matching Vehicle Tracking Data , 2005, VLDB.

[60]  Hanan Samet,et al.  SPDO: High-throughput road distance computations on Spark using Distance Oracles , 2016, 2016 IEEE 32nd International Conference on Data Engineering (ICDE).

[61]  Lu Qin,et al.  Efficient shortest path index maintenance on dynamic road networks with theoretical guarantees , 2020, Proc. VLDB Endow..

[62]  Farnoush Banaei Kashani,et al.  A case for time-dependent shortest path computation in spatial networks , 2010, GIS '10.

[63]  Shanshan Zhang,et al.  A trajectory restoration algorithm for low-sampling-rate floating car data and complex urban road networks , 2020, Int. J. Geogr. Inf. Sci..

[64]  Marta C. González,et al.  Understanding congested travel in urban areas , 2016, Nature Communications.

[65]  John Krumm,et al.  From GPS traces to a routable road map , 2009, GIS.

[66]  Christian S. Jensen,et al.  Using Incomplete Information for Complete Weight Annotation of Road Networks , 2013, IEEE Transactions on Knowledge and Data Engineering.

[67]  Yong Wang,et al.  Querying Shortest Paths on Time Dependent Road Networks , 2019, Proc. VLDB Endow..

[68]  Bin Yang,et al.  Context-Aware Path Ranking in Road Networks , 2020, IEEE Transactions on Knowledge and Data Engineering.

[69]  Venkatesh Ganti,et al.  Data Cleaning , 2009, Encyclopedia of Database Systems.

[70]  Benjamin Coifman,et al.  Estimating travel times and vehicle trajectories on freeways using dual loop detectors , 2002 .

[71]  Yin Wang,et al.  Map matching: comparison of approaches using sparse and noisy data , 2013, SIGSPATIAL/GIS.

[72]  Bin Yang,et al.  A Road Segment Attribute Completion System , 2020, 2020 21st IEEE International Conference on Mobile Data Management (MDM).

[73]  Jed A. Long,et al.  Kinematic interpolation of movement data , 2016, Int. J. Geogr. Inf. Sci..

[74]  Christian S. Jensen,et al.  EcoSky: Reducing vehicular environmental impact through eco-routing , 2015, 2015 IEEE 31st International Conference on Data Engineering.

[75]  Cyrus Shahabi,et al.  DeepTRANS , 2020, Proc. VLDB Endow..