Researchers are tapping into the oversized brains of London cab drivers to create the next generation of artificial-intelligence (AI) guided route mapping.
Dr Pablo Fernandez Velasco, from the University of York, said unlike a satnav, which calculated every possible route to the destination, researchers found that London taxi drivers rationally planned each route by prioritising the most challenging areas first and filling in the rest of the route around these tricky points.
Dr Velasco said previous studies had shown the brain of a London taxi driver, famous for their knowledge of more than 26,000 streets across the city, had a larger posterior hippocampus region than the average person, with their brains changing in volume as a result of their cab driving experience.
He said current computational models to understand human planning systems were challenging to apply to the “real world”, so researchers measured the thinking time of London taxi drivers while they planned travel journeys to various destinations in the capital city.
“London is incredibly complex, so planning a journey in a car ‘off the top of your head’ and at speed is a remarkable achievement.
“If taxi drivers were planning routes sequentially, as most people do, street-by-street, we would expect their response times to change significantly depending on how far they are along the route.
“Instead, they look at the entire network of streets, prioritising the most important junctions on the route first, using theoretical metrics to determine what is important.”
Dr Velasco said this was a highly efficient way of planning.
“It is the first time that we are able to study it in action.”
He said researchers showed that taxi drivers used their cognitive resources in a much more efficient way than current technology, and argued that learning about expert human planners could help with AI development in a number of ways.
Fellow researcher Dan McNamee, from the Champalimaud Foundation, said the development of future AI navigation technologies could benefit from the flexible planning strategies of humans, particularly when there were a lot of environmental features and dynamics that had to be taken into account.
“Another way to enhance these technologies would be to integrate the information about human experts into AI algorithms designed to collaborate with humans,” Dr McNamee said.
“This is a very important point, because if we want to optimize how an AI algorithm interacts with a human, the algorithm has to ‘know’ how the human thinks.”
Read the full study: Expert navigators deploy rational complexity–based decision precaching for large-scale real-world planning.
