Mission-critical information technology, software and systems engineering for all modes of transportation
U.S. Department of Transportation
Cambridge, Massachusetts, USA
The U.S. Department of Transportation Volpe Center’s mission is to advance transportation innovation for the public good by anticipating emerging transportation issues and objectively addressing the nation’s most pressing and complex transportation challenges, particularly those that can be solved with an intermodal, systems perspective.
The contracted company supported the Volpe Center with mission-critical information technology, software and systems engineering for all modes of transportation, including the Federal Aviation Administration (FAA), National Highway Traffic Safety Administration (NHTSA), U.S. Department of Defense, and U.S. Department of Interior. The key technologies employed to support this work included cloud and serverless architecture, modern web frameworks, Agile/DevOps, data analytics, and machine learning. They also developed and maintained modeling and simulation systems that supported environmental policies, and they provided cybersecurity to numerous transportation-related programs for the Volpe Center and other government entities.
Developed the FAA Safety Assurance System (SAS), a web application with millions of lines of code, fully operational at all FAA field and regional offices, to improve aviation safety and oversight.
Developed the FAA Air Traffic Operations Network (OPSNET) replacement system proof-of-concept that improves measurement of FAA-reportable delays, attribution of causal factor through data analytics, and display and reporting of operation performance data.
Developed a deep-learning system to validate the performance of the MobileEye collision avoidance system to detect pedestrians in front of moving vehicles.
Modernized the NHTSA Artemis system used to identify and address potential safety defects in motor vehicles and inform recall actions. The modernized, serverless Amazon Web Services (AWS) cloud-based architecture consolidates disparate data and provides analytical capabilities enabling investigators to immediately see safety-related information.
Conducted a big-data pilot project that uses machine learning methods to estimate crash risk and reportable traffic crashes to help emergency responders, traffic management centers, and law enforcement proactively allocate resources to locations with the highest accident potential.
Developed web applications focused on analysis of geospatial data for the Federal Highway Administration and other transportation agencies using state-of-the-art Geographic Information System (GIS) and data science technologies.
Architected and developed a data lake to store and analyze traffic flow information using an open-source toolset on the AWS environment, and demonstrated cross-domain data correlation to calculate fuel burn for flights in holding patterns.
Developed a cross-platform mobile application for the National Highway Institute Bridge Inspectors compatible with iOS and Android platforms.