Traffic monitoring in safety critical environments Daniel Work University of Illinois at Urbana-Champaign This talk will describe new approaches to monitor traffic in safety critical environments ranging from temporary events to city-scale disasters. While the field of traffic monitoring has advanced rapidly over the last several years due to falling sensing, communication, and computational costs, several holes remain which have high impact to roadway safety. This talk explores three such problems and their potential solutions. The first part of the talk will explore the challenges of sensing traffic conditions caused by temporary events such as sporting events and highway work zones. Due to the unique features of these congestion triggers, real-time data streams are needed to improve knowledge of the traffic state, which is in turn necessary for safety services ranging from back-of-queue warnings to event emergency response. The talk will present two sensing systems in development at Illinois that address these needs for temporary sensing. The second part of the talk links the traffic state estimation problem with the traffic incident detection problem, resulting in a unified framework to solve both problems simultaneously. The joint problem is posed as a hybrid state estimation problem, where a continuous variable denotes the traffic state and a discrete model variable identifies the location and severity of an incident. The hybrid state is estimated using a multiple model particle smoother to accommodate the nonlinearity and switching dynamics of the traffic incident model, and is validated in simulation and with field data. The results show the joint framework can improve both incident detection capabilities and post incident traffic state estimation. The final part of the talk considers a solution to the emerging problem quantifying the resilience of the city-scale traffic network to extreme events such as natural disasters using GPS data from taxis. The method works by computing the historical distribution of pace between various regions of a city and measuring the pace deviations during an unusual event. This method is applied to a dataset of nearly 700 million taxi trips in New York City, which is available for download at http://publish.illinois.edu/dbwork/open-data/. The analysis indicates that Hurricane Sandy impacted traffic conditions for more than five days and caused a peak delay of two minutes per mile. Practically, it identifies that the evacuation caused only minor disruptions, but significant delays were encountered during the post-disaster reentry process.