AASS Seminar - Trying to Fix Traffic: contributions from AI

The research centre AASS arranges a seminar with Ana Bazzan, Univ. Federal do Rio Grande do Sul, Brazil.

Abstract

According to the INRIX Global Traffic Scorecard, in 2016, an average driver in Los Angeles has spent 100 hours (approximately 4 days) in traffic jams. The economic impact of this is huge. Besides, also issues related to environment is non-negligible. Many naive solutions tend to ignore the fundamental rule of traffic: building new roads just makes people drive more, i.e., more supply creates more demand. Given the continuous growth of the world urban population and the increasing needs related to mobility of people and goods, the demand is likely to grown anyway. Lucky, there are not only bad news here: people do adapt to congestion. Therefore, it is important to understand how this adaptive process occurs, and how to seize the opportunity to develop or enhance agent-based tools as well as reinforcement learning methods in order to contribute to the effort of fixing traffic as much as possible. Among many others, one example here is the design of protocols and mechanisms underlying new traffic-related apps.

Bio

Ana Bazzan received her PhD in 1997 from the University of Karlsruhe (now KIT), Germany. She is a full professor at UFRGS in Porto Alegre, Brazil. Her activities include: fellow of the Alexander von Humboldt Foundation; current or past associate editor of journals (Autonomous Agents and Multiagent Systems, Advances in Complex Systems, among others); member of the IFAAMAS board. Her main research interests are: multiagent systems, machine learning, complex systems, agent-based simulation.