Rail Implementations

UtterBerry is operating within the rail network, streamlining processes surrounding the maintenance and upkeep of rail-side assets. This has saved many hours of engineering work, cutting costs for rail companies and reducing rail closures for customers.

People Counting

Train Maintenance

The UtterBerry Smart Sensor System can also be used to accurately count the number of passengers within specific areas of a station; waiting on the platform or on a train itself.

The data gathered can be used to decrease congestion within stations, a problem that occurs too often in underground tube stations. Reducing congestion improves passenger experience and prevents delays from occurring.

Faults in Train machinery can result in many hours of delay. While engineers investigate and repair the problem, many passengers will be left waiting for long periods of time whilst replacement trains arrive.

Active vehicles with an installed UtterBerry System will benefit from improved problem warning systems, which are able to identify exactly what has caused a fault on the train. With this information, engineers will be able to get the train back to a working state in less time than ever before.


The UtterBerry Smart Sensor System also has the ability to detect displacement changes in earthworks surrounding any transport route.

Warnings will be issued by the system if a significant change were to take place so the problem can be remedied sooner. The system’s patented AI and Machine Learning can offer users predictions for future changes in earthworks displacement, allowing rail companies to prepare in advance.


Existing Projects

UtterBerry has worked on underground sites including Paddington, Farringdon, Barbican, Moorgate, Liverpool Street, Whitechapel and Canary Wharf. 

Sensors embedded in the Rail Network monitor the location, speed and trajectory of each train to understand the effect they have on underground tunnels. Once enough data is collected, predictions can be made by the onboard Artificial Intelligence and Machine Learning, alerting relevant personnel of potential dangers to tunnel structure in advance.