Drs. Azadeh and Maknoon from TU Delft to give keynote at Disrupt 2023
July 14, 2023
The 2023 Disruptive Transportation Technologies and Services Research Symposium (Disrupt 2023) will be held on July 21, 2023, at Toronto Metropolitan University. We are pleased to welcome Dr. Azadeh and Dr. Maknoon from TU Delft as this year’s keynote speakers.
Biography
Dr. Shadi Sharif Azadeh is a faculty member at Civil Engineering and Geosciences faculty and the co-director of SUM (Sustainable Urban Multi-modal Mobility) lab at TU Delft in the department of Transport & Planning. Her areas of expertise include integration of operations research with behavioural models for transport, mobility and logistics networks (Choice Driven Optimization). More precisely, her current major projects are related to 1) combining pricing and assortment optimisation methods to model supply and demand interplay for last mile delivery and urban mobility systems and 2) developing real-time methods to be incorporated in combinatorial optimisation framework for large-scale transport problems. She is an editorial board editor at Transportation Research Part B: Methodological, editorial board member of Transportation Research Part C: Emerging Technologies and guest editor of three special issues at Transportation Science, EURO Journal of Transport and Logistics and OR Spectrum.
Dr. Yousef Maknoon is a faculty member at the Faculty of Technology, Policy, and Management (TPM) at TU Delft. He is also the director of Orbit Lab, a research group specializing in Operations Research and Behavioral Informatics in Transportation. His research takes a multidisciplinary approach, firmly rooted in operations research, to tackle emerging challenges in the transport and logistics domains. In recent years, his primary focus has been on the design and operational strategies for on-demand and instant logistics services, driving the evolution of this dynamic field.
Title
Two Paradigms Tackling the Same Problem Real-Time Decisions for On-Demand Delivery Systems, a Tailored Deep Reinforcement Learning and a Probabilistic Optimization Framework
Abstract
Driven by the digital revolution and advanced communication technologies, a profound transformation is sweeping the transportation and logistics sector. This paradigm shift is underpinned by the real-time flow of information from diverse resources and the complex dynamics of human behaviour. As a result, the benchmarks for service efficiency and customer satisfaction have been raised to new heights. Nonetheless, in this information-rich landscape, the extraction of actionable insights and their effective integration into strategic, tactical, and operational planning still demands the deployment of efficient models and algorithms. In this presentation, we explore the real-time dynamics of these multifaceted systems through a dual analytical lens. Our first approach uncovers a reinforcement learning (RL)-based strategic dual control framework, designed to dispatch, and steer fleet operations in real time. Our second approach unveils an innovative optimization framework tailored to guide both fleet activities and customer service, responding adeptly to real-time fluxes.