Self-navigating AI learns to take shortcuts: study

Self-navigating AI learns to take shortcuts: study
DeepMind route. Credit: DeepMind

A computer programme modelled on the human brain learnt to navigate a virtual maze and take shortcuts, outperforming a flesh-and-blood expert, its developers said Wednesday.

While artificial intelligence (AI) programmes have recently made great strides in imitating human brain processing—everything from recognising objects to playing complicated board games—spatial navigation has remained a challenge.

It requires the recalculation of one's position, after each step taken, in relation to the starting point and destination—even when travelling a never-before-taken route.

Navigation is considered a complex behavioural task, and in animals is partly controlled by a sort of onboard GPS driven by " " in the brain's hippocampus region. These cells have been observed firing in a regular pattern as mammals explore a new environment.

In a new study published in the journal Nature, AI researchers said they had developed a "", or "brain", which they trained to navigate towards a goal in a virtual maze.

When shortcuts were introduced, by opening a previously blocked opening for example, the AI automatically took the shorter route.


Furthermore, the computer "brain" generated navigational grids strikingly similar to those observed in the brains of foraging mammals, said the team.

Interview with Caswell Barry about grid cells. Credit: DeepMind

The programme "performed at a super-human level, exceeding the ability of a professional game player," three of the study authors said in a press statement.

It "exhibited the type of flexible navigation normally associated with animals, taking novel routes and shortcuts when they became available."

Most of the researchers are attached to DeepMind, the British AI company that also created AlphaGo, the self-trained computer that beat human champions at the Chinese board game "Go" said to require intuition rather than brute processing power to prevail.

The team said their work was "an important step in understanding the fundamental computational purpose of grid cells in the ".

The discoverers of were awarded the Nobel Prize for Medicine in 2014.

Interview with Matt Botvinick about neuroscience and AI. Credit: DeepMind

Explore further

A robot computer algorithm that copies the navigation functionality of humans and animals

More information: Vector-based navigation using grid-like representations in artificial agents, Nature (2018).
Journal information: Nature

© 2018 AFP

Citation: Self-navigating AI learns to take shortcuts: study (2018, May 9) retrieved 26 October 2020 from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Feedback to editors

User comments