Black cab drivers could help improve AI computers

The way that Black Cab drivers plot routes across London could lead to innovations in AI computing, according to a study by York University.

Unlike a satnav, which calculates every possible route until it gets to the destination, academics at the University of York, in collaboration with University College London and the Champalimaud Foundation, found that London taxi drivers rationally plan each route by prioritising the most challenging areas first and filling in the rest of the route around these tricky points.

Current computational models to understand human planning systems are challenging to apply to the ‘real world’ or at large scale, and so researchers measured the thinking time of London taxi drivers while they planned travel journeys to various destinations in the capital city.

Previous studies have shown the uniqueness of the London taxi driver’s brain; they have a larger posterior hippocampus region than the average person, with their brain changing in volume as a result of their cab driving experience.

Dr Pablo Fernandez Velasco, British Academy Postdoctoral Fellow at the University of York, said: “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. This is a highly efficient way of planning, and it is the first time that we are able to study it in action.”

Researchers showed that taxi drivers use their cognitive resources in a much more efficient way than current technology, and argue that learning about expert human planners can help with AI development in a number of ways.

The research was supported by the British Academy, the EPSRC UK, and Ordnance Survey and published in the journal PNAS.

SUPPORT THIS WEBSITE

This website has been running now for over a decade, and while advertising revenue contributes to funding the website, it doesn't cover the costs. That is why I have set up a facility with DonorBox where you can contribute to the costs of the website and time invested in writing and research for the news articles.

It's very similar to the way The Guardian and many smaller websites are now seeking to generate an income in the face of rising costs and declining advertising.

Whether it's a one-off donation or a regular giver, every additional support goes a long way to covering the running costs of this website, and keeping you regularly topped up doses of Londony news and facts.

If you like what you read on here, then please support the website here.

Thank you

13 Comments on “Black cab drivers could help improve AI computers

  1. Not anymore most black cab drivers go straight into busy road to straich the fair I m Uber driver I have been in this industry well before Uber got to the uk I always use back street I mean shortest route possible to get to destination .

    • Higo, I think you’ve got it the wrong way round, you see WE use a brain nav YOU use a sat-nav. Plus if you have drove in London like I have for 36yrs then you’d know that most of the integral side roads have been closed for cyclists!

    • I think you will find that with all the LTNs and bicycle lanes and pedestrianised london roads that the black cabs have nowhere else to go but to sit in the queues of traffic that our fantastic mayor of london has caused .

    • The notion that London black cab drivers routinely try to artificially extend journeys to bump up fares has been thoroughly debunked many times. It may happen in isolated cases, but most of the time the fare structure means they’re better off turning jobs around faster anyway.

  2. “Solve the hard problems first then breeze through the easy ones” Whilst it’s an easy strategy to follow in many disciplines, the key is knowing which bits are the hard ones. That’s where skill & experience come into their own. Not sure how they’re going to teach that to computers. (Please don’t claim “AI”)

    • If you tracked millions of journeys alongside relevant data such as day/date/time, holidays, school terms, public events, weather and roadworks, and fed it all into a machine learning model, you could certainly train it to do that. The challenge is acquiring enough data in the first place.

  3. how would uber driver know london licensed taxi driver stick to main roads , we go shortest way possible, and we dont need sat nav

  4. An interesting idea and long overdue. I am sceptical of the “studies” into Black Cab drivers’ brains, having spent far too long in the back seat. Or perhaps the finite number of brain cells are reapportioned. More research needed

    The problem with The Knowledge is that it isn’t very dynamic. How many times has the so-skilled cab driver not been aware of some gov’t or royal event closing streets? It was an almost daily occurrence when I was busy in central London. Obviously the taxi association could have invested in layered tech to make the black cabs better for all involved, but instead they simply upped fares relentlessly to the point they created that huge gap for Uber

    • In London taxi fares are set by TfL, not any “taxi association”. Taxi drivers are self-employed and own or lease their vehicles, meters and other equipment, so neither would any “association” be in a position to invest in “layered tech” whatever it is you mean by that!
      Any new tech would be a matter for drivers to acquire commercially, though anything relating to metering would need to be approved by the PCO (TfL).

  5. Nitpick, since I went to one of them.
    York University and the University of York are not the same institution. Oddly enough, the one in Canada is actually older.

  6. If the AI will be trained on data based on taxi drivers’ decisions, will they ask permission and pay the drivers for the valuable data or just steal it like Google did when they scanned copyright books?

Leave a Reply

Your email address will not be published. Required fields are marked *

*