Event Info
Friday, February 28 | 12:00 p.m. ET
Description
The safe and efficient operations of AAM rely on digital avionics, AI-driven 4D trajectory-based flight planning, and real-time flight operation management. Existing AAM simulation platforms have significant research gaps, as they primarily focus on corridor network analysis, tactical conflict management, and airspace capacity analysis while lacking the capability to develop and evaluate diverse operational management strategies, integrate deep learning for real-time flight optimization, and assess system-wide performance. To address these deficiencies, we developed AAMSim, an AnyLogic-based simulation platform that facilitates customizable AAM network configuration through the integration of external configuration files defining vertiport locations and layouts, passenger demand features, and electric Vertical Take-Off and Landing aircraft (eVTOL) fleet parameters. Its Application Programming Interfaces (APIs) facilitate seamless communication with AI-driven optimization algorithms, Providers of Services for UAM (PSU), and eVTOL avionics, enabling real-time simulation, validation of operational strategies, and transmission of optimized decisions for execution. A case study conducted in the Greater Tampa Bay area simulated a 30-vertiport AAM network, evaluating the impact of three vertiport layouts, an eVTOL rebalancing algorithm, and an early take-off strategy on passenger reneging rates, passenger waiting time, eVTOL utilization rate, and other key performance metrics. The results from five simulation scenarios modeling 4,615 passengers over four hours demonstrated that combining these strategies significantly enhanced operational performance, decreasing passenger reneging rate from 47.3% to 26.93% without compromising overall efficiency. These findings indicate that AAMSim effectively fills the current research gap and provides a versatile decision-support tool for AAM operators, PSUs, regulators, and policymakers, ultimately advancing safer, more efficient, and sustainable AAM systems.
About the Presenter
Bai Li, PhD
Dr. Bai Li is a postdoctoral researcher in the Department of Civil and Environmental Engineering at the University of South Florida and a member of the Smart Urban Mobility Laboratory (SUM-Lab). He earned his Ph.D. in Civil Engineering (Transportation) from Shanghai Jiao Tong University. Dr. Li’s research focuses on the simulation and optimization of Advanced Air Mobility (AAM) system operations, as well as the development of embedded hardware and software for intelligent transportation systems. He also specializes in mathematical programming, algorithm development, simulation tools, and machine learning/deep learning methods to enhance the efficiency, resilience, and sustainability of multimodal transportation systems.
He has published over 20 papers in leading transportation journals and has been invited to present his work at prestigious international conferences. Additionally, he serves as a reviewer for esteemed journals such as Transportation Research Part D: Transport and Environment and IEEE Internet of Things Journal. Dr. Li is the recipient of the 2024 Transportation Research Board (TRB) Best Paper Award in Intelligent Transportation Systems, an honor conferred by the National Academies of Sciences’ Transportation Research Board in recognition of his innovative research contributions.
