We build vessel collision warning systems for vulnerable bridges.
Roebling Labs continuously assigns threat levels to each vessel by combining real-time transponder (AIS) tracking, trajectory forecasting, and AASHTO impact analysis.
The Francis Scott Key Bridge collapse - with a life-loss of six and cost to society of $5 billion - triggered an NTSB investigation that identified 68 potentially vulnerable bridges across the U.S.A. These bridges were built before 1996 over navigation channels serving ocean-going vessels and had not yet received modern risk assessments. Currently, 46 bridges remain on the NTSB's vulnerable list as risk assessments are completed.
Figure 1: Francis Scott Key Bridge collapsed after contact with containership Dali on 28 March 2024. (Source: NTSB)
The twenty owner agencies responsible for the NTSB-named vulnerable bridges received letters on 10 December 2025 with safety recommendations enclosed.
NTSB Safety Recommendation H-25-030: "Incorporate motorist warning systems capable of activating when a threat is identified and immediately warn and stop motorists from entering the bridge."
Standards for installing traffic gates are well established at movable bridges, for example. This NTSB recommendation calls for traffic gates to be retrofitted to existing, vulnerable long-span bridges.
However, no automated vessel collision warning systems were available to alert bridge owners when to operate the traffic gates.
Roebling Labs builds vessel collision warning systems for vulnerable bridges.
We alert bridge owners when to operate their traffic gates by continuously assigning threat levels to each vessel. We combine real-time transponder (AIS) data with trajectory forecasting and AASHTO impact analysis.
Our system receives AIS signals broadcast from each vessel that include identity, size, speed, position, and heading. The U.S. Coast Guard has required AIS transponders since 2002 for self-propelled vessels over 65 feet long, towing vessels over 26 feet long, and all passenger vessels. This mandate covers the types of vessels that pose collision risk to bridges, with the exception of loose barges and acts of war or terrorism.
Optional computer vision enhancement provides redundancy, protection from spoofing, and incident logging.
We continuously rank each vessel within 30 nautical miles by probability and consequence of collision.
Figure 2: Risk Matrix for Assessing Vessel Threat
Contact scott@roeblinglabs.com to schedule a demonstration.
Field deployment of our hardware + software solution coming soon.
Roebling Labs builds vessel collision warning systems for vulnerable bridges.
Bentley Systems, the makers of Microstation CADD software, funded our development program.
We are a resident company at The Engine, the "Tough Tech" incubator built by MIT.
Office and Mailing Address:
Roebling Labs LLC
The Engine
750 Main Street
Cambridge MA, 02139
Scott Snelling, PE is CEO. He has 20+ years of bridge engineering experience having led complex projects across the U.S. and abroad.
Scott began his career at WSP and U.S. Army Corps of Engineers. He has degrees from Columbia University in the City of New York (M.S. Structural Eng.), Rose-Hulman Institute of Technology (B.S. Mechanical Eng.), and Boston University (M.B.A.).
LinkedIn: Scott Snelling
Josh Burnett is Chief Technical Officer (CTO). He has 20+ years experience working at the intersection of electronics, hardware and software for life-safety-critical medical devices and laboratory instrumentation.
Josh has degrees from Carnegie Mellon University (B.S. Mechanical Engineering with Data Storage Systems minor) and Boston University (M.S. Mechanical Engineering with focus on Robotics and Controls).
LinkedIn: Josh Burnett
Shaun Meredith is a computer vision expert, former Navy submarine officer, and MIT graduate. He is the Founder and CTO of Omnic.ai.
LinkedIn: Shaun Meredith
Email scott@roeblinglabs.com to protect your bridge users today.
Pilot program available. Pay only after successful validation at your site.
Follow our journey from prototype to life-safety system.