The studies in Ai Research Group are motivated by the challenge that all transportation agencies are currently facing and will continue to face: The conflict among the increasing demands on transportation systems, the continually aging transportation infrastructures, and the stringent labor and financial resources. Such a challenge bears an urgent, yet a long-lasting need for an intelligent way to construct a reliable and cost-effective transportation infrastructure system. The research in Ai Group is motivated by the challenge that all transportation agencies are currently facing and will continue to face: The conflict among the increasing demands on transportation systems, the continually aging transportation infrastructures, and the stringent labor and financial resources. Such a challenge bears an urgent, yet a long-lasting need for an intelligent way to construct a reliable and cost-effective transportation infrastructure system.
Sensing-Based Transportation Asset Management
Transportation assets are the most critical element in transportation systems to provide critical functional support for road users. Public agencies need to make optimized decisions to maintain the functionality of their transportation assets while minimizing cost. These optimized decisions can and will be relying on a comprehensive synthesis using sensing-based systems. Therefore, Ai Group envisions its effort in this direction on developing fundamental computer vision and sensing signal processing algorithms to construct a system that can intelligently evaluate, monitor, and diagnose transportation asset conditions.
- Ai, C. (PI). “Improving Pedestrian Facility Inventory Data in Massachusetts using Mobile Light Detection and Ranging (LiDAR).” Massachusetts Department of Transportation. 2018-1019.
Sensing-Based Transportation Safety Awareness
Ai Group sees great opportunities in the research areas of transportation safety awareness by employing sensing technologies. Sensing technologies have inherent advantages to answer some of the fundamental questions in this research area, e.g. how to accurately and objectively acquire and evaluate safety measures, how to proactively aware (“predict”) the potential safety issues, etc. However, naturally, many research issues in transportation safety may not be instantly resolved by simply applying sensing technologies. For example, it may remain challenging to quantify and estimate human perception and psychological behavior. Therefore, Ai Group envisions the research in this direction focuses on these challenging issues, by integrating the traditional safety analysis methods, e.g., driving simulation, survey, etc., and the sensing-based methods, e.g., eye tracking, vehicle trajectory analysis, etc.
- Ai, C. (PI), with Knodler, M. “Collecting Model Inventory Road Element (MIRE) Fundamental Data Elements (FDEs) for Intersections in Massachusetts.” Massachusetts Department of Transportation. 2018-2019.
- Ai, C. (PI), with Knodler, M. “Quantifying the Impacts of Situational Visual Clutter on Driving Performance Using Video Analysis and Eye Tracking.” U.S. Department of Transportation through the Safety Research using Simulation (SAFER-Sim) University Transportation Center. 2019-2020.
Sensing-Based Pavement Preservation and Maintenance
To construct and maintain the most invested infrastructure in the whole transportation infrastructure system, studies on pavement condition evaluation and preservation have been actively conducted during the past decades. Until recently, the emerging 3-D scanning laser technology has revolutionized both the industry’s and public transportation agencies’ practices, especially in the area of pavement data acquisition. However, while the overwhelmingly large amount of data provides unprecedented details for the pavement, it has become increasingly challenging to accurately and efficiently extract useful information supporting maintenance decisions. Therefore, Ai Group envisions the research in this direction focuses on bridging the gap between the “raw data” acquired on the pavement and the “derived knowledge” of the pavement condition, through harnessing exciting collaborations in the areas of image processing and signal processing, structure analysis, pavement deterioration modeling, pavement management system, etc.