Dubai’s Roads and Transport Authority (RTA) is exploring the use of artificial intelligence (AI) to plot more efficient bus routes based on how they are used throughout the day.
Machine learning (ML) algorithms could eventually inform updates to 150 routes used by 2,158 buses across Dubai, the RTA said.
The authority trialled the system on ten public bus routes over thirty days, using Nol Card (Dubai’s public transport smart card) data to understand patterns such as which bus stops were busy all day, which were primarily used during peak hours and those that were rarely used.
The one-month trial cut wasted time on bus routes by 13.3 percent, the RTA reports.
Ahmed Mahboub, Executive Director of Smart Services, Corporate Technology Support Services Sector, RTA, commented: “By using machine learning algorithms in analysing the captured data, departments can build up systems and take decisions with reference to abolishing certain stops, or proposing an express service that skips those stops, while ensuring customer needs are always addressed. Such a process will contribute to improving this vital service.”
The technology could also reduce fuel consumption and carbon emissions and save time for staff, he added.
The RTA said the approach is in line with the United Arab Emirate government’s Artificial Intelligence Strategy as well as its own internal goals. It could also be of interest to cities and public transport operators more widely as they consider how to plan for the future amid the COVID-19 pandemic, which has upended the patterns which mobility systems have been based around.