Speakers

The real-time city is real! As layers of networks and digital information blanket urban space, new approaches to studying the built environment are emerging. The way we describe and understand cities is being radically transformed — as are the tools we use to design them. The Senseable City Laboratory’s mission—a… read more 

This project develops a generalized model to operate an integrated public transit, transportation network company (TNC), and FMLM service considering uncertain rider demand and network dynamics. It optimally matches riders to shuttle vehicles, and route vehicles in real time. In addition, it is a general platform to evaluate user costs… read more 

Pecan Street works with advanced energy systems including smart inverters, energy storage, controlled electric vehicle charging, HVAC demand response and V2G system testing, as well as residential electrical system issues that are not being addressed by these technologies. Speaker: Scott Hinson Scott Hinson is a Chief Technology Officer at Pecan… read more 

Reinforcement learning (RL) has gained popularity in the research community as a model-free and adaptive control paradigm for the built environment, especially for building energy control. RL has the potential to enable inexpensive plug-and-play building controllers that can be implemented without necessitating potentially expensive control models (unlike model predictive control),… read more 

We use natural language processing technique to construct sentiment index from social media; we link the sentiment index with extreme weather conditions and COVID-19 shocks to quantify their negative impacts on people’s expressed sentiment; we explore the heterogeneity across countries and different population groups, and the underlying mechanisms. Speaker: Siqi… read more 

In this talk, I will share a new error estimation method for identifying systematic errors for sensors deployed in a traffic network. This approach integrates statistics and transportation domain knowledge, specifically the spatial interdependence of traffic flows, to enable identification of the health conditions of road sensors as well as… read more 

The Austin AI Housing Analysis is a Year 2 Good Systems Project that aims to build a predictive AI system that can test past and future regulatory scenarios and help inform affordable residential development policies in Austin. This talk will cover preliminary research to date into how affordable housing in… read more 

It is very easy to fall into the trap of putting sensors around town to collect data, without developing a data strategy. It is important to think through what data is being collected, how it will be stored, and what problems it will help us solve. “Smart solutions” should be… read more 

Optimizing ambulance allocation and routing is one of the most efficient ways for the EMS to save more lives at virtually no cost. However, current EMS software were developed under models that assume normal demands. They are unable to adapt to disasters such as the COVID-19 pandemic, where traffic patterns… read more 

The collaborative autonomous driving approach depends on the collaboration between intelligent roads and intelligent vehicles. This approach is not only safer but also more economical compared to the traditional on-vehicle-only autonomous driving approach. In this talk, we introduce our real-world deployment experiences of collaborative autonomous driving, and delve into the… read more