INFORMS Open Forum

Gentle Reminder: TSL Society Webinar (Nov 18, 2021)

  • 1.  Gentle Reminder: TSL Society Webinar (Nov 18, 2021)

    Posted 19 days ago
    Dear Colleagues,

    This is a gentle reminder for the TSL Society Webinar on the 18th of November 2021 (for most of the World).

    Title: Dynamic fleet management of on-demand ridesharing systems with mixed-autonomy: A deep reinforcement learning framework

    Time: 8 am ET November 18, 2021

    Registration: Welcome! You are invited to join a webinar: TSL presents - Dynamic fleet management of on-demand ridesharing systems with mixed-autonomy: A deep reinforcement learning framework. After registering, you will receive a confirmation email about joining the webinar.

    Abstract: With the continuous development of urbanization, the past decades have witnessed the rapid growth of the ridesharing systems as a new business mode. Autonomous vehicles (AVs) are expected to be introduced into ridesharing systems for its advantages in central coordination. We aim to optimize the real-time operation of a ridesharing platform transiting from traditional ridesharing networks to fully automated mobility-on-demand systems, where conventional vehicles (CVs) and AVs coexist. The operator can directly control all the AVs and thus make centralized AV dispatching decisions. Human drivers focusing on their own monetary return, however, tend to gather at hot spots and lead to unbalanced supply and demand. Incorporating distinct characteristics of AVs and CVs, we propose a two-sided multi-agent reinforcement learning based framework to dynamically coordinate mixed fleets in ridesharing systems. Specifically, we model the operator and driver decision making procedure as Markov decision processes (MDP), where the operator and drivers interact with the environment at the same time. The operator makes centralized decisions on AV fleet dispatching and driver commission rates, while drivers make relocation decisions in a decentralized manner. The proposed model is validated using a case study in New York City using real taxi trip dataset. Results demonstrate that our algorithm significantly improve system performance. In particular, we also show that charging dynamic commission fee makes both the platform and the drivers better off, especially in scenarios with higher demand volume.

    Speaker bio: Dr. Liu Yang is jointly appointed as an Assistant professor in the Department of Civil and Environmental Engineering and the Department of Industrial Systems Engineering and Management at National University of Singapore. She received her B.S. from Tsinghua University, MPhil from Hong Kong University of Science and Technology, and Ph.D. from Northwestern University. Previously, Dr. Liu worked as a consultant at Cambridge Systematics and provided modeling expertise to public agencies such as the Chicago Department of Transportation. Dr. Liu's research focuses on the areas of urban mobility management, travel demand and congestion management, and data-driven transportation system modeling and analysis. Her work has been published in the major journals in the transportation area, including Transportation Research Part A, Part B, Part C, and Part E. Currently, she serves as a member on the editorial advisory board of Transportation Research Part C and an associate editor in Socio-Economic Planning Sciences. She is a co-chair of WTC Shared Logistics and Transportation Systems Committee, a member of Transportation Research Board Standing Committee on Emerging and Innovative Public Transport and Technologies (AP020) and Transportation Network Modeling (AEP40), a member of the Chinese Overseas Transportation Association (COTA) Board of Directors, and a member of WCTRS Special Interest Group Transport Theory and Modelling. Her research is currently supported by Singapore Ministry of Education and ST Engineering.

    Best regards,

    Yong Wu
    Senior Lecturer
    Griffith University
    Southport QLD