Self-Navigating AI Learns to Take Shortcuts: Study

Advertisement
By Agence France-Presse | Updated: 10 May 2018 18:06 IST
Highlights
  • The computer programme was modelled on the human brain
  • It learnt to navigate a virtual maze and take shortcuts
  • It outperformed a flesh-and-blood expert

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.

Advertisement

Navigation is considered a complex behavioural task, and in animals is partly controlled by a sort of onboard GPS driven by "grid cells" 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 "deep neural network", or computer "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.

Advertisement

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

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.

Advertisement

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.

Advertisement

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

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

 

Catch the latest from the Consumer Electronics Show on Gadgets 360, at our CES 2026 hub.

Further reading: Science, Self-Driving, AI, Nature Journal
Advertisement

Related Stories

Popular Mobile Brands
  1. Avatar: Fire and Ash OTT Release: When, Where to Watch the Sci-Fi Fantasy
  2. Shambhala OTT Release: When, Where to Watch the Telugu Supernatural Horror
  3. Top Deals on Gaming Laptops During Amazon Great Republic Day Sale
  1. Ustaad Bhagat Singh OTT Release: When, Where to Watch Harish Shankar's Telugu Action Drama Film
  2. Bha Bha Ba is Now Streaming: All You Need to Know About This Malayalam Comedy Thriller Film
  3. World’s Biggest Alien Search Enters Final Stage With 100 Mystery Signals
  4. NASA Pulls Out Artemis II Rocket to Launch Pad Ahead of Historic Moon Mission
  5. Shambhala OTT Release: When, Where to Watch the Telugu Supernatural Horror Film
  6. AGS 28 OTT Release: Know Where to Watch This Tamil Entertainer Starring Arjun, Abhirami
  7. Avatar: Fire and Ash OTT Release: When, Where to Watch James Cameron’s Epic Sci-Fi Fantasy
  8. OpenAI to Begin Testing Ads in ChatGPT, Says Responses Will Not Be Influenced
  9. Gurram Paapi Reddy OTT Release: When, Where to Watch This Telugu Crime Comedy Thriller
  10. Hypothetical ‘Dark Stars’ Could Rewrite Early Cosmic History, Research Suggests
Gadgets 360 is available in
Download Our Apps
Available in Hindi
© Copyright Red Pixels Ventures Limited 2026. All rights reserved.