STAR Lab

Overview

The STAR Lab looks at many aspects of transportation engineering. Our research leverages the increasing amount of transportation big data to understand underlying patterns and behavioral changes in the transportation world. In addition, with the fast paced developments in Maching Learning and Artificial Intelligence, the lab research also focuses on AI applications in transportation engineering.

Traffic sensing and edge computing



With continual technological advances and government initiatives, implementations of smart cities are arising and the surrounding concepts are solidifying. A key component of smart cities is real-time traffic management based on a wealth of sensor data. Data streams from all corners and all sources (e.g., video cameras, traffic counters, etc.) must be collected and then merged to supply model inputs to guide and support analysis and decision-making at many different scales. The wealth of data available to describe traffic and mobility is constantly increasing in dimension (both spatial and temporal) and growing more complex; long gone are the days of simple tube counters and paper-based travel surveys.

This ever-growing data deluge requires increasing orders of magnitude of network bandwidth, disk space and computation power to communicate, store and process. Data centers are often depleted and outdated and cloud solutions might be expensive. An emerging alternative is edge computing. Instead of sending all data back to the “brain” for storage and analysis, edge devices process all or part of the data locally before communicating with the center/cloud. This reduces the amount of data to be transmitted, stored and analyzed at the “brain”, while preserving a promising level of information.

In this line of research, the STAR Lab strives to detect users in a transportation system, their interactions, and to monitor infrastructure conditions. Specifically, we detect vehicles in surveillance and unmanned aerial vehicle (UAV) videos, understand paths of pedestrian & bicyclists in on-board and surveillance videos, and monitor parking events and road surface conditions.

Vehicle

Pedestrian & Cyclists

Parking

Road surface condition

Near-miss events

Transportation data science and analytics



Modeling of traffic dynamics and evolution is difficult due to complex spatial and temporal aspects of traffic across a network. For example, consider how downstream congestion from a bottleneck can spillback on a freeway for miles in some cases. When one further considers how traffic crashes and special events (among many other factors) can lead to irregularities in demand, it is clear to see how complicated traffic modeling at a network scale can become. Recently, the STAR Lab took a variety of research projects studying traffic modeling on large transportation networks that are rooted in the application of multiple sources of traffic sensing data.

A critical first step in this research is to store and maintain these various data streams. The STAR Lab thus developed and maintains an online platform, called the Digital Roadway Interactive Visualization and Evaluation Network (DRIVE Net), for exactly this purpose. This platform facilitates large-scale online data storage, sharing, visualization, modeling, and analysis.

A second step in this effort involves using this platform to collect and analyze data for a given area of analysis. Over the years, the STAR Lab developed numerous state-of-the-art machine learning and statistical-based algorithms to model and forecast traffic states for freeway networks (such as that in the Seattle area).

A third step involves sharing our knowledge and experience with the community. Recently, we built an online platform called AI Net, where we have created workspaces for transportation network model evaluation and related data sharing. On the platform, we provide datasets and implement models and demonstrate their applications such as network-level speed prediction. Visitors of the platform are also welcome to upload their own models for training online and compare to our models and other benchmarks.

Data storage and sharing platforms

Machine Learning for traffic prediction

Smart infrastructure and Urban mobility



Smart infrastructure

Urban mobility

Traffic Operations and Safety



Operations

Safety