ITS Berkeley

Estimating Hybrid Choice Models with Biogeme

Bierlaire, Michel
Ben-Akiva, Moshe
Joan Walker
2026

The literature on discrete choice models with latent variables is vast (Walker, 2001, Ashok et al., 2002, Greene and Hensher, 2003, Ben-Akiva, Walker, Bernardino, Gopinath, Morikawa and Polydoropoulou, 2002, Ben-Akiva et al., 2002, to cite just a few early references). This document presents a practical introduction to the specification and estimation of hybrid choice models using Biogeme. It introduces the main concepts and notation underlying these models, discusses the associated normalization issues, and illustrates their implementation through a sequence of progressively richer...

Air Traffic Control Using Large Language Models: Prompt Engineering, Architecture, and Evaluation

Ghazanfari, Mahyar
Casanova, Matthias
Kam, Jordan
Zongo, Alex
Wei, Peng
Darrell, Torsten
Alexandre Bayen
2026

Air traffic control (ATC) communication is a safety-critical dialogue that remains largely human-driven even as other parts of air traffic management have been semi-automated. In this article, we experimentally evaluate whether large language models (LLMs) can generate operationally realistic ATC transmissions. An experimental general-aviation flight flying over the San Francisco "Bay Tour" route is hand-transcribed and used as ground truth (P0). Through a pilot-in-the-loop process we design five prompt structures (P1-P5) of increasing constraint and embed them in a stateful multi-turn...

Degradation-Model-Agnostic Energy Throughput Control for EV Range Preservation and Battery Lifetime Extension via Cell-Level Inverters

Jiang, Shida
Tao, Shengyu
Shi, Junzhe
Scott Moura
2026

A conventional electric vehicle (EV) powertrain relies on a centralized high-voltage DC–AC inverter, thereby limiting cell-level control and potentially reducing overall driving range and battery lifetime. This paper studies an H-bridge-based cell-level inverter topology that performs power conversion at the cell level, enabling independent control of individual cells and expanding the design space for battery management. Leveraging these additional degrees of freedom, we propose a degradation-model-agnostic energy-throughput control strategy that preserves usable energy and EV range while...

Unequal Risk: Longitudinal Observation of Socioeconomic Disparities and Pedestrian Mortality Patterns in Cali, Colombia

Villaveces, Andres
Fox, Lani
Daniel Rodriguez
Bangdiwala, Shrikant I.
Ortega, Delia
Serre, Marc
2026

Household locations of pedestrian injuries and fatalities are disproportionately concentrated in lower socioeconomic neighborhoods, reflecting deep-rooted disparities in urban infrastructure, pedestrian exposure, and traffic safety. This study analyzes the relationship between socioeconomic levels and pedestrian incidents in Cali, Colombia, focusing on both the residential locations of injured individuals and the physical locations of fatalities. By separately examining injury residences and fatality locations, we begin to investigate how socioeconomic disparities influence both who is...

Reinforcement Learning-based Traffic Control with Multiple Interacting Connected and Autonomous Vehicles

Wang, Yusheng
Maria Laura Delle Monache
2026

This paper develops a centralized reinforcement learning (RL)–based controller for Connected and Automated Vehicles (CAVs) operating in mixed autonomy settings designed to lower overall traffic fuel consumption. The traffic dynamics are formulated as a coupled PDE–ODE system, with the PDE governing macroscopic density evolution of the traffic and the ODEs characterizing the motion of CAVs that act as moving actuators. We integrate finite volume numerical schemes with the RL controller as the control input. Numerical experiments demonstrate that the proposed RL controller achieves a lower...

Disruptions as Catalysts for Change: Exploring Multi-year Temporal Dynamics of Mobility Styles

Ho, Phoebe
Bouzaghrane, Mahamed Amine
Guirado, Carlos
Joan Walker
2026

Disruptive events, ranging from extreme weather events to global pandemics, inevitably reshape the way people live, travel, and interact with their environments. Understanding both temporary shifts and longer-term behavioral adaptations in response to disruptions is critical for planning resilient transportation systems that can adapt to evolving mobility patterns. This study leverages longitudinal Point of Interest (POI) data from 15,720 unique panelists in the United States between February 2020 and May 2022 to uncover the multi-year temporal dynamics of individual activity-travel...

Shared Mobility Policies for California

Susan Shaheen
Cohen, Adam
2018

In recent years, economic, environmental, and social forces have quickly given rise to the “sharing economy,” a collective of entrepreneurs and consumers leveraging technology to share resources, save money, and generate capital. Shared mobility—the shared use of a vehicle, bicycle, or other low-speed travel mode—is an innovative transportation strategy that enables users to have short-term access to a transportation mode on an as-needed basis. Business-to-consumer services, such as Zipcar and car2go, and peer-to-peer carsharing and shared ride services, such as Getaround, Turo, Lyft, and...

A Systematic Review of Fast Food Access Studies

Fleischhacker, SE
Evenson, KR
Daniel Rodriguez
Ammerman, AS
2011

The frequent consumption of energy-dense fast food is associated with increased body mass index. This systematic review aims to examine the methodology and current evidence on fast food access and its associations with outcomes. Six databases were searched using terms relating to fast food. Only peer-reviewed studies published in English during a 10-year period, with data collection and analysis regarding fast food access were included. Forty articles met the aforementioned criteria. Nearly half of the studies (n = 16) used their own set of features to define fast food....

A Research Roadmap for Transportation and Public Health

Sandt, LS
West, A
Johnson, S
Brookshire, K
Evenson, K
Blackburn, L
Peach, K
Tartala, M
Ricklin, A
Shah, S
Daniel Rodriguez
Coburn, J
2019

States and localities are beginning to recognize and act on the connection between health and transportation. A growing number of entities have produced a number of resources, guidance documents, and strategic plans on the topic.

The TRB National Cooperative Highway Research Program's NCHRP Research Report 932: A Research Roadmap for Transportation and Public Health builds upon this body of work to provide a plan for funding research over the next decade that can lead to greater consideration of health issues in transportation contexts.

A Method for Estimating the Associations of Neighborhood Type with Availability of Sit-down Restaurants and Supermarkets

Peng, K
Daniel Rodriguez
Hirsch, JA
Gordon-Larsen, P
2020

Although neighborhood-level access to food differs by sociodemographic factors, almost all research on neighborhoods and food access has used a single construct of neighborhood context, such as income or race. Neighborhoods possess many interrelated built environment and sociodemographic characteristics, a condition that obscures relationships between neighborhood factors and food access. Methods: To account for the effects of many interrelated aspects of neighborhoods in food access, we developed a generally applicable method that used multiple measures (e.g., population density, mix of...