• Scientists create coevolved Predator and Prey bots

    Monday, February 1st, 2010

    Biggs is the East Cost Editor of TechCrunch. Biggs has written for the New York Times, InSync, USA Weekend, Popular Mechanics, Popular Science, Money and a number of other outlets on technology and wristwatches. He is the former editor-in-chief of Gizmodo.com and lives in Bay Ridge, Brooklyn. You can Tweet him here and G+ him here. Email him directly at... → Learn More

    http://c.brightcove.com/services/viewer/federated_f9/3924348001?isVid=1&publisherID=1274168784

    Some scientists at the Ecole Polytechnique Fédérale of Lausanne have built “evolving” predator and prey robots designed to, in short, learn from each other. Read that again: While we’re worried about Taylor Swift and and Lady Gaga, robots are now teaching each other how to hunt us.

    The robots use Darwinian Selection to decide how to escape each other or work together to catch another robot.

    Just a few hundred generations of selection are sufficient to allow robots to evolve collision-free movement, homing, sophisticated predator versus prey strategies, coadaptation of brains and bodies, cooperation, and even altruism. In all cases this occurred via selection in robots controlled by a simple neural network, which mutated randomly.

    Presumably they kept running these programs over and over again and eventually produced Taylor Swift and Lady Gaga, two Darwinian superrobobeasts designed to lull us into submission.

    via Eng

    Sponsored Ads

    blog comments powered by Disqus

    Sponsored Ads

    Sponsored Ads

    Upcoming Events

    E3 2012

    Los Angeles, CA

    Disrupt SF 2012

    San Francisco, CA