Transportation is a basic necessity of life. The exploration of better transportation options has never been stopped through human history. In recent years, the revolution of ride-sharing industry and the innovation of self-driving technologies produces a huge amount of transportation data every day. Such huge amount of data starts a new era of modern smart transportation. Many traditional transportation problems may find better solutions through modern machine learning and data mining methodologies. This tutorial aims to provide the participants a broad and comprehensive coverage on the foundations, recent developments and open problems on transportation AI.
Transportation is a very wide research field. In this tutorial, we focus on the topics for the mobile transportation platform, based on the real applications and demands in DiDi, the world’s largest mobile transportation platform. We organize our topics into three categories. The first one is map services, including map matching, traffic prediction, estimated time of arrival (ETA) and route planning et al., which provide precise basic information for the follow-up decision making process. Most of these problems have been investigated in the literature in pure transportation or geographic information system. However, those are unable to meet the accuracy or the efficiency requirements for the real-time mobile transportation platform. It is necessary to revisit these problems with a modern view and to explore novel solutions adapting to more strict demands. The second category is the decision making, which builds up the core ride-sharing platform. The similar problems have been extensively investigated in research fields other than transportation. However, they have been redefined with new challenges in mobile transportation systems. The last category is the user experience, such as travel safety assessment, which is the unique demand for the mobile transportation platform.
Zheng WANG, DiDi AI Labs, Didi Chuxing
Zhiwei (Tony) QIN, DiDi AI Labs, DiDi Labs, Didi Chuxing
Jieping YE, DiDi AI Labs, Didi Chuxing & University of Michigan, Ann Arbor
Tracy LI, Research Outreach, Didi Chuxing
Yan LIU, University of South California
Chenxi WANG, Research Outreach, Didi Chuxing
Dr. Zheng Wang is a researcher in DiDi AI Labs and the architecture of the intelligent map service for DiDi. He received his Ph.D. degree from Tsinghua University in 2011 and worked as a research fellow in Arizona State University in 2011-2014, then as a research faculty in the University of Michigan at Ann Arbor in 2014-2016. He has received several awards, including best research paper award runner-up in KDD and best paper award in IEEE International Conference in Social Computing (SocialCom). He served as the PC member of leading conferences, such as ICML, NIPS, SDM and IJCAI, and gave tutorial in ICDM. He is now leading the R&D team, working on designing and developing novel machine learning systems and services for DiDi map and DiDi capacity prediction platform. He designed the novel machine learning and deep learning solutions of DiDi ETA and route planning services, which serve over 20 billion requests per day.
Dr. Zhiwei (Tony) Qin leads the reinforcement learning research at DiDi AI Labs, working on core problems in ride-sharing marketplace optimization. He received his Ph.D. in Operations Research from Columbia University and B.Sc. in Computer Science and Statistics from the University of British Columbia, Vancouver. Tony is broadly interested in research topics at the intersection of optimization and machine learning, and most recently in reinforcement learning and its applications in operational optimization, digital marketing, traffic signals control, and education. He has published in top-tier conferences and journals in machine learning and optimization, including ICML, KDD, IEEE ICDM, WWW, JMLR, and MPC. He has served as Senior PC/PC of NeurIPS, AAAI, IJCAI, KDD, JMLR, TPAMI, and other operations research journals.