MTA Announces Pilot Programme for TrackInspect System

The Metropolitan Transportation Authority (MTA) has announced a new pilot programme with Google Public Sector to further develop its TrackInspect prototype system.

TrackInspect, developed in collaboration with the Rapid Innovation Team at Google Public Sector, combines sensors with advanced cloud and artificial intelligence (AI) technology to detect potential track issues ahead of time.

The TrackInspect prototypes, which are currently fitted into Google Pixel smartphone cases, have been retrofitted onto R46 subway cars operating along MTA lines, utilising a microphone to capture vibrations and sound patterns through a combination of built-in sensors.

Data is sent in real time to cloud-based systems, before AI and machine learning algorithms generate predictive insights into potential future issues, with New York City Transit (NYCT) track inspectors serving to inspect any locations highlighted by the system.

Once attended to, inspectors will be able to confirm any issues before providing accurate feedback in order to train the model.

MTA Chief Technology Officer, Raf Portnoy, said:

The TrackInspect pilot is a game-changer for the MTA, combining advanced cloud, AI, and real-time sensor technology to transform how we maintain and monitor our subway infrastructure.

It reflects our commitment to uniting technology and operations to drive innovation and safety.

In its initial pilot run, the TrackInspect prototype collected around 335 million sensor readings, one million GPS locations and 1,200 hours of audio, all of which has been utilised to create a machine learning model on the Google Cloud.

All data collected by the prototype complements information provided by the MTA’s own track geometry cars, combining to provide a clear picture of potential track issues.

TrackInspect, which first began as a proof-of-concept prototype, also uses Generative AI for natural language processing, allowing inspectors to ask questions about maintenance history, protocols, and repair standards, with clear, conversational answers.