Multi-Objective Transportation System Optimization Using BISTRO

Jessica Lazarus & Alexandre Bayen

PhD student and Professor of UC Berkeley

Alexandre Bayen is the Liao-Cho Professor of Engineering at UC Berkeley. He is a Professor of Electrical Engineering and Computer Science, and Civil and Environmental Engineering. He is currently the Director of the Institute of Transportation Studies (ITS). He is also a Faculty Scientist in Mechanical Engineering, at the Lawrence Berkeley National Laboratory (LBNL).

This talk is given by Alex's PhD student Jessica Lazarus. Jessica's doctoral research focuses on multi-objective mechanism design for transportation policy. In particular, she is interested in the optimization of pricing policies to achieve economic, social, and environmental sustainability objectives. Jessica was one of the lead researchers in the development of BISTRO (Berkeley Integrated TRansportation Optimization).

Talk abstract: The Berkeley Integrated System for TRansportation Optimization (BISTRO) is an open-sourced transportation planning and decision support system that uses an agent-based simulation and optimization framework to develop and evaluate transportation system interventions. We will examine the key opportunities and challenges in using activity-based travel models with agent-based simulation to optimize transportation policies across multiple conflicting objectives. In particular, we will discuss case studies using BISTRO for the optimization of pricing, transit operations, and vehicle fleet mix with respect to multiple objectives representing systemwide congestion-, social-, and revenue-based policy goals.

Policy Informatics: Knowledge discovery in synthetic worlds

Stephen Eubank

Professor of University of Virginia

Stephen Eubank received his B.A. in physics from Swarthmore College in 1979 and his Ph.D. in theoretical physics from the University of Texas at Austin in 1986. While a staff member at Los Alamos from 1997-2005. Dr. Eubank played a leading role in developing the traffic microsimulation component of the Transportation Analysis and Simulation System (TRANSIMS); he led the Epidemiology Simulation (EpiSims) project; and he was the team leader for the Urban Infrastructure Suite (UIS), of which both TRANSIMS and EpiSims are parts. UIS is a collection of interoperable simulations of interacting infrastructures, each of which simulates the behavior of every individual in a large urban region. In his current position as Deputy Director of the Network Simulation Sciences and Computing Laboratory at the Biocomplexity Institute at University of Virginia, he is pursuing interests in developing advanced technology for the study of large socio-technical systems and understanding the dynamics and structure of social networks.

Talk abstract: Policy informatics provides decision-makers evidence-based policy analytics for real-world situations. This presentation will examine the constraints this problem space imposes on modeling methods. Based on experiences in this area, we suggest the use of synthetic information systems constructed by simulating causal dynamics of socio-technical interactions. This generative approach is suitable for addressing hypothetical policies and can untangle the complex feedback loops among different scales in the system. KDD methods are involved in both the construction and analysis of the synthetic worlds.

Lessons from the Field: AI for Mission-Critical Infrastructure

Jim Gao

CEO & Co-founder of Phaidra, previous Team Lead of DeepMind Energy

Jim Gao is an entrepreneur with a background in AI and mechanical engineering. He led interdisciplinary teams at DeepMind and Google to develop and commercialize artificial intelligence (AI) products. This includes: 40% energy savings in cooling Google's data centers, 20% revenue increase in Google's wind farms, autonomous industrial systems, and future announcements. He left DeepMind to co-found Phaidra, a startup that helps industrial companies develop in-house AI solutions.

Talk abstract: Applying AI to real-world physical systems can be challenging. This is especially true in the industrial sector, where the opportunities for AI and the cost of failure are very high. This talk shares lessons learned on how to apply AI to large industrial systems for maximum safety and impact.

Planning and Modeling Urban Systems with Novel Data Sources

Marta Gonzalez

Professor of UC Berkeley

Marta C. Gonzalez is Associate Professor of City and Regional Planning at the University of California, Berkeley, and a Physics Research faculty in the Energy Technology Area (ETA) at the Lawrence Berkeley National Laboratory (Berkeley Lab). Her research team develops computer models to analyze digital traces of information mediated by devices. They process this information to manage the demand in urban infrastructures in relation to energy and mobility.

Talk abstract: Computational Urban Sciences refer to the use of information and communication technology and data in the context of cities and urban environments.  I present methods to identify patterns of occupancy in building energy consumption and the utilization of urban space. Our mobile phone-based occupancy estimates are integrated with a state-of-the-art urban building energy model to understand their impact on energy use predictions.  Second, I present a new urban planning paradigm where within minutes, inhabitants can access their basic living needs by bike or by foot. I show insights of the interplay between the distributions of facilities and population that maximize accessibility over the existing road networks. 

Building An Intelligent Ridesharing Marketplace

Jieping Ye

Head of DiDi AI Labs, Associate Professor of University of Michigan, Ann Arbor.

Jieping Ye is Head of DiDi AI Labs, a VP of Didi Chuxing and a DiDi Fellow. He is also a Professor at the University of Michigan, Ann Arbor. His research interests include data mining and machine learning with applications in transportation and biomedicine. He has served as a Senior Program Committee/Area Chair/Program Committee Vice Chair of many conferences including NIPS, ICML, KDD, IJCAI, AAAI, ICDM, and SDM. He serves as an Associate Editor of Data Mining and Knowledge Discovery and IEEE Transactions on Knowledge and Data Engineering. He won the NSF CAREER Award in 2010. His papers have been selected for the outstanding student paper at ICML in 2004, the KDD best research paper runner up in 2013, and the KDD best student paper award in 2014.

Talk abstract: Didi Chuxing is the world’s leading mobile transportation platform that offers a full range of app-based transportation options for 550 million users. Every day, DiDi’s platform receives over 100TB new data, processes more than 40 billion routing requests, and acquires over 15 billion location points. AI has been used in numerous components of DiDi’s platform to improve travel safety, experience and efficiency. This talk systematically presents the challenges and opportunities in the core area of modern transportation systems, and highlights some of our recent works on order dispatching and fleet management via deep reinforcement learning.

Some Experience on Learning for Decision-Making in Real-World Scenarios

Yang Yu

Professor of Nanjing University

Yang Yu is a Professor of Artificial Intelligence School, Nanjing University. Yang Yu is an associate professor of computer science in Nanjing University, China. He joined the LAMDA Group as a faculty since he got his Ph.D. degree in 2011. His research area is in machine learning and reinforcement learning, particularly focusing on real-world reinforcement learning. He was recognized as an AI’s 10 to Watch by IEEE Intelligent Systems in 2018, invited to have an Early Career Spotlight talk in IJCAI’18, and received the Early Career Award of PAKDD in 2018.

Talk abstract: Reinforcement learning is one of the main approaches to learning for decision-making, and has shown super-human ability in playing games. While we are eager to implement such ability in real-world tasks, there are still great challenges to move RL from games to the real-world. In this talk, we will introduce some of our experience and understandings in landing RL, focusing on decision factors, data bias, and simulator learning.