Affiliation: Assistant Professor, USC CEE
Presentation Time: 8:50 am - 9:30 am MT
Title: Harnessing Autonomous Vehicles for Smarter Traffic Management
Abstract: Autonomous vehicles (AVs) offer new opportunities to improve traffic flow, enhance system-wide coordination, and maximize societal benefits through their increased controllability and adaptability. However, their effective integration into transportation systems requires a comprehensive understanding of AV-human interactions and the development of strategic control mechanisms to prevent potential negative consequences, such as the exploitation of AVs’ cooperative behaviors by selfish drivers.
This talk examines a series of representative transportation scenarios—weaving ramps, vehicle routing in networks, and toll lane usage—to explore how AVs can be leveraged to improve traffic efficiency and overall system performance. The presentation introduces innovative models that capture the complex interplay between human-driven and autonomous vehicles and demonstrates control strategies that optimize AVs' potential while mitigating the risks of adverse exploitation. The discussion highlights the importance of well-designed AV deployment and control policies to ensure that autonomous mobility serves broader societal interests.
Bio: Ruolin Li is a Gabilan Assistant Professor in the Department of Civil and Environmental Engineering at the University of Southern California. Her research focuses on the active control and management of autonomous vehicles in mixed-autonomy environments, leveraging game theory, multi-agent systems, and optimization to enhance the societal benefits of intelligent transportation systems. She explores how AVs can be strategically integrated to foster more adaptive and cooperative mobility networks.
Prior to joining USC, Ruolin was a postdoctoral scholar in the Department of Aeronautics and Astronautics at Stanford University. She earned her Ph.D. and M.S. degrees in Mechanical Engineering from UC Berkeley in 2023 and 2018, respectively. She is recognized as a Rising Star in Civil and Environmental Engineering by MIT and a Rising Star in Mechanical Engineering by Stanford.
Slides: (link to PDF)
Affiliation: Associate Professor, UCSB ECE
Presentation Time: 10:00 am - 10:40 am MT
Title: Routing and Pricing for Multi-modal Delivery Systems
Abstract: Multi-modal delivery systems are a promising solution to the challenges posed by the increasing demand of e- commerce. In this talk, we aim to quantify this potential by developing a mathematical model for a multi-modal delivery system composed of trucks, drones, autonomous vehicles, etc. We first propose an optimization formulation that can be efficiently solved in order to design socially-optimal routing and allocation policies. We incorporate both societal cost in terms of road congestion and parcel delivery latency in our formulation. Our model is able to quantify the effect drones have on mitigating road congestion, and can solve for the path routing needed to minimize the chosen objective. Next, we address the challenge of efficiently allocating transportation resources while price matching users with their desired delivery modes. More precisely, we consider that orders are demanded by a heterogeneous population of users with varying trade-offs between price and latency. We show that one can set prices explicitly to induce a desired network flow. Finally, we demonstrate several case studies that corroborate the theoretical and algorithmic results of the talk.
Bio: Dr. Ramtin Pedarsani is an associate professor in the ECE department at UCSB. He obtained his Ph.D. in Electrical Engineering and Computer Sciences from UC Berkeley in 2015. He received his M.Sc. degree at EPFL in 2011 and his B.Sc. degree at the University of Tehran in 2009. His research interests include machine learning, optimization, information theory, game theory, and intelligent transportation systems. He is the recipient of the Communications/Information Theory Society joint paper award in 2020 and the best paper award in the IEEE International Conference on Communications (ICC) in 2014.
Slides: (link to PDF) (link to PPT)
Affiliation: Assistant Professor, UMN Aerospace
Presentation Time: 11:20 am - noon MT
Title: Actively Learning Correlated Equilibria for Coordinating Noncooperative Agents
Abstract: In noncooperative multiagent systems—such as users competing for bandwidth in shared communication or transportation networks—agents independently optimize their own private objectives that may be interdependent and conflicting. This decentralized behavior typically leads to Nash equilibria, which may be stable but often fail to ensure fairness or system-level efficiency. Correlated equilibria offer a powerful alternative by enabling win-win outcomes through shared recommendations from a central coordinator, effectively serving as a mechanism for coordinated decision-making. However, computing such equilibria requires knowledge of agents’ objective functions, which are often unknown due to limited access to agent-level information. We propose an active learning framework that learns correlated equilibria from agents’ reported correlated regrets, which quantify the suboptimality of a coordination strategy. Leveraging Bayesian optimization, our method efficiently learns effective strategies using a limited number of correlated regret evaluations. To further enhance learning efficiency, we introduce a model reduction technique that identifies a representative set of strategies by maximizing their worst-case pairwise differences. We demonstrate the proposed approach in a network flow coordination problem where users compete for shared bandwidth.
Bio: Assistant Professor Yue Yu's research focuses on developing efficient and scalable algorithms for controlling autonomous systems in aerospace engineering. His work centers on numerical optimization and control theory, extending to various domains such as game theory, machine learning, and network systems. Recent research projects include real-time trajectory optimization and game-theoretic coordination in multiagent systems, with an emphasis on applications in advanced air mobility and spacecraft control.
Slides: (link to PDF)
Affiliation: Assistant Professor, UIUC ISE
Presentation Time: 1:40 pm - 2:20 pm MT
Title: Guarantees for Advisory Autonomy via Incentive Design and Lyapunov Analysis
Abstract: In transportation systems, if we had complete control authority, sufficient bandwidth for communication, and full automation, we could achieve great societal benefits, such as decreasing congestion and reducing emissions. However, transportation systems today do not have all these capabilities, and will likely not have them in the near future. In our work, we focus on the development of technologies for advisory autonomy: using the existing infrastructure to communicate and incentivize human agents to more closely align with the desirable actions we would have chosen if we had full autonomy. In this talk, I will address the gaps between advisory autonomy and full autonomy, with a focus on the participation and engagement of human drivers. Decision making processes of individuals are complex, and, even when they are engaged in programs to improve congestion and emissions, they may be imperfect in implementing the recommended actions. In the first half of my talk, I will discuss the difficulties that complicated dynamics and coupling between agents poses for practically implementing incentive design; in the second half of my talk, I will discuss how Lyapunov methods inspired from sampled-data systems can provide guarantees even when humans imperfectly implement advisory actions.
Bio: Roy Dong is an Assistant Professor in the Industrial & Enterprise Systems Engineering department at the University of Illinois at Urbana-Champaign. He received a BS Honors in Computer Engineering and a BS Honors in Economics from Michigan State University in 2010. He received a PhD in Electrical Engineering and Computer Sciences at the University of California, Berkeley in 2017, where he was funded in part by the NSF Graduate Research Fellowship. Prior to his current position, he was a postdoctoral researcher in the Berkeley Energy & Climate Institute, a visiting lecturer in the Industrial Engineering and Operations Research department at UC Berkeley, and a Research Assistant Professor in the Electrical and Computer Engineering department at the University of Illinois at Urbana-Champaign. His research uses tools from control theory, economics, statistics, and optimization to understand the closed-loop effects of machine learning, with applications in cyber-physical systems such as the smart grid, modern transportation networks, and autonomous vehicles.
Slides: (link to PDF)
Affiliation: Assistant Professor, UW AeroAstro
Presentation Time: 2:20 pm - 3:00 pm MT
Title: Towards Trusted Human-centric Autonomy for Autonomous Vehicles
Abstract: Autonomous robots are becoming increasingly prevalent in everyday life, from navigating our roads and sidewalks to assisting in households and warehouses. Yet building robots that can safely and fluently interact with humans in a trusted manner remains an elusive task. Humans are remarkably adept at avoiding collisions seamlessly, even in crowded settings. In this talk, we will discuss how to utilize human interaction data to learn models that describe these interactions and explore techniques to enhance the safety and fluency of robot planning and control. First, I will discuss recent work that combines data-driven techniques with control-theoretic models to learn interpretable models of safe human-robot vehicle interactions. Second, I will discuss recent work on modeling and inferring multi-agent responsibility for avoiding collision to gain insight into multi-agent vehicle interactions. Third, I will share some recent work on deep generative modeling for robot planning that is capable of incorporating learned interaction insights to produce safe and efficient robot behaviors.
Bio: Karen Leung is an Assistant Professor and the Vagners & Christianson Endowed Faculty Fellow in Aeronautics & Astronautics at the University of Washington. She directs the Control and Trustworthy Robotics Lab (CTRL), which focuses on developing safe, intelligent, and trustworthy autonomous systems that can operate seamlessly with, alongside, and around humans. Before joining UW, Karen was a research scientist at NVIDIA, working in the Autonomous Vehicle Research Group, where she holds a partial appointment as a faculty scientist. Karen received her M.S. and Ph.D. in Aeronautics and Astronautics from Stanford University and a combined B.S./B.E. in Mathematics and Aerospace Engineering from the University of Sydney, Australia. She is a recipient of the UW + Amazon Science Hub Faculty Research Award, the William F. Ballhaus Prize for Best Ph.D. Thesis Award, and an Outstanding Undergraduate Research Mentor Award.
Slides: (To be posted)