Meet newly minted Dr. Riju Livanya, Spring 2021 Ph.D. in Transportation Systems Engineering from the University of California, Irvine. Prior to his Ph.D., Dr. Livanya completed his bachelor’s degree in Civil Engineering from the prestigious Indian Institute of Technology - Bombay.

Livanya grew up in Bareilly, Uttar Pradesh, and shares that moving from a small city to a large metropolis for his undergraduate studies was transformational for him. Living in Mumbai gave Livanya an appreciation for the massive scale at which human activities and movement can take place.  That, coupled with his traditional and rigorous technical undergraduate studies gave him an interest in transportation and the confidence to apply to graduate schools in the United States.   “Witnessing the extraordinary scale of human movement in Mumbai gave me an appreciation for the complexity of the fields of transportation planning and engineering,” he explains.  “I love the interdisciplinary nature of this field. New technologies (connected and autonomous vehicles, for example) and mobility paradigms have the potential to fundamentally alter the way we move, the way we live, the way we plan our neighborhoods and structure our cities. This is the most exciting time to be in transportation!”

Livanya feels fortunate to have worked on projects relating to transportation planning, paratransit, transportation modeling, traffic simulation, and machine learning while at UC Irvine, working alongside world-renowned faculty researchers. His dissertation, “Disaggregate Control of Vehicles using In-Vehicle Advisories and Peer-to-Peer Negotiations”, focuses on the development of a lane-based cooperative driving framework in which vehicles can enter into Peer-to-Peer negotiations with surrounding vehicles, and trade their position in time and space in exchange for monetary or other benefits (see abstract below). This proposed framework of routing vehicles on a lane to lane basis can only be realized in the field if the mediating agency (for example, a TMC, or a mobility service) has accurate information about traffic conditions, he notes. So, as part of his dissertation research, Livanya developed machine learning techniques to estimate traffic states solely using information collected from sensor-equipped probe vehicles, without the need for any other data such as those obtained from traditional embedded loop detectors.

Livanya was selected twice as a Pedagogical Fellow, a university-wide award, and has conducted several workshops to train incoming graduate students on pedagogical techniques, and mentored them for the entire academic year. “I have thoroughly enjoyed my time at school,” he shares. “I continue. to be inspired by all the smart peers and wonderful professors who have created an ideal environment to freely pursue my research interests.” Livanya was also the recipient of the United States Department of Transportation Pacific Southwest Region University Transportation Center (PSR UTC) Graduate Fellowship, which funded his dissertation research in its final stages.

Livanya is now a lecturer at UC Irvine, and is looking for opportunities in the fields of mobility services, travel demand modeling, and data science in transportation. Recognizing the fascinating interdisciplinary nature of transportation, Livanya advises incoming students to be sure to not only become experts in their specific area of focus in transportation but also to seek and gain knowledge outside of their specific sub-field. For example, engineers should understand the broader economic and sociopolitical (or even cultural) context within which hard-core engineering problems are invariably situated. Students interested in policy should maintain a clear understanding of technology/data analytics and other quantitative techniques that can help prepare them for effective decision-making in their careers.

Dr. Riju Lavanya

Spring 2021 Ph.D. in Transportation Systems Engineering from the University of California, Irvine

Disaggregate Control of Vehicles using In-Vehicle Advisories and Peer-to-Peer Negotiations

Abstract

Traffic advisories to travelers are based upon traffic state information at the link level. This is due to existing infrastructure which sometimes can only provide link-level information. However, the primary justification for providing link-level data is the reluctance of Traffic Management Agencies to consider more detailed traffic state data for operational and safety reasons. However, with the advances in automotive technology, sensing equipment, and the Internet of Things (IoT), we can do better. Research shows that faster and more accurate travel paths can be obtained by using lane data rather than link data. Our contention is that for vehicles to be able to change lanes to improve their travel times, operationally, they would need to enter into Peer-to-Peer negotiations with surrounding vehicles, where they can trade their position in time and space in exchange for monetary benefits. Our work is an exploration of this idea.

I begin with a simple in-vehicle advisory control policy, partially inspired by the Kinetic theory of traffic. I then move towards an individual-level Peer-to-Peer negotiated lane change framework by first investigating its efficacy by means of microsimulation studies. I then propose an agent-based optimization framework for this system, which minimizes both travel time and the envy induced among drivers when they are assigned paths that are inferior to their peers. Numerical results from running our optimization on an illustrative off-ramp network show that the proposed model converges to both envy-free and system optimum traffic states, even at a net-zero budget, meaning this system can be used by transportation agencies without exacting tolls or giving subsidies.

The proposed framework of routing vehicles on a lane-to-lane basis can only be realized in the field if the mediating agency (TMC, or a mobility service) has accurate information about traffic conditions. I propose multiple algorithms, including a LSTM (Long Short Term Memory) neural network architecture-based framework to estimate traffic states solely using information collected from sensor-equipped probe vehicles, without the need for any other data such as those obtained from traditional embedded loop detectors.

About the Author:

Dr Nikitha Kolapalli is a health economist/clinical pharmacist pursuing her master's in Healthcare Decision Analysis from the USC School of Pharmacy. She works as a staff writer and editor for the METRANS student team. She is deeply passionate about maximizing accessible, equitable, and affordable healthcare.