The map-reading AI that navigates better than you

By on 26 October, 2016

 underground-map-navigate-london-spatial

Artificial intelligence researchers from the UK have developed an AI with the ability to learn the best way to navigate a complex transportation system such as the London Underground. The method uses a system of trial and error, in a way similar to living brains, to process complicated data with the power of a computer.

The machine ‘learns’ by being shown examples of problems that have already been solved, and is then presented with an unsolved example. It was able to use this ‘training’ to understand the structure of the London Underground transport system and successfully plan the shortest route between stops, as well as plan moves in a complex block puzzle, performing better than previous AI tested in similar situations.

To get stories like this delivered to your mailbox every week, subscribe to our weekly newsletter. 

The hybrid learning machine that combines the best features of neural networks and computers is described in a study published in the journal Nature last week.

Conventional computers can process complex forms of data, but require manual programming to perform these tasks. To overcome this, artificial neural networks have been developed to mimic brain-like learning that can identify patterns in data, but they lack the memory architectures needed for symbolic processing of structured data.

Alex Graves, Greg Wayne, Demis Hassabis and colleagues developed a so-called ‘differentiable neural computer’ (DNC), which comprises a neural network that can learn by example or through trial and error, and an external memory structure similar to random-access memory in a conventional computer. Thus, it can learn like a neural network but process complicated data like a computer.

The study shows the DNC can successfully understand graph structures like family trees or transport networks; for example, planning the best route on the London Underground without prior knowledge of this transport system or solving moving block puzzles with goals described in a symbolic language.

The findings could go onto have significant repercussion for applications as diverse as urban planning, intelligent transport systems and mobile navigation.

 

You may also like to read:



Newsletter

Sign up now to stay up to date about all the news from Spatial Source. You will get a newsletter every week with the latest news.

Interview: Tori Murrant, GIS analyst
Having stumbled across the geospatial sector at university, ...
Testing SouthPAN and commercial GNSS services
UNSW surveying students were challenged to put a range of So...
Here’s what’s in our latest issue!
Learn about the metaverse, mapmaking, 3D scanning, RINEX, hy...
Modern Methods of Construction Roadshow
The events will show how the latest software, tools and tech...
Real-time LiDAR mapping system
The Brumby LiDAR rapidly produces point clouds by removing t...