Banner
    ‘Stray Sock Syndrome’ - A Robotic Investigation
    By Martin Gardiner | December 5th 2013 11:25 AM | Print | E-mail | Track Comments
    About Martin

    I specialise in beachcombing the scholarly journals and university websites for uncommonly intriguing academic articles by uncommonly intriguing...

    View Martin's Profile

    The ubiquitous ‘Stray Sock Syndrome’ can be a considerable headache for human sock-owners and sock-sorters. But help is afoot courtesy of the Computer Science Division at the University of California at Berkeley, US, and the Max Planck Institut Informatik, Germany. Where a team of computer scientists and robotics experts have “…considered the problem of equipping a robot with the perceptual tools for reliable sock manipulation.”
    Their robot (a Willow Garage PR2) has not only been programmed to identify ‘stray’ socks from a sample of pair-able and non-pair-able socks – but also to physically sort them into pairs – with accuracies approaching 98%.

    The stray-sock algorithm can be outlined thus:

    “To handle stray socks we start with the lowest scoring (best) pairs and work our way up until the cost exceeds the maximum cost in which the algorithm considers indicative of a proper match. In case of an odd number of socks in the set, we introduce a ‘fake sock’ which has equal similarity with all socks. The true sock matched to the fake sock is considered a stray sock.”

    The academic paper: Perception for the Manipulation of Socks, (by Ping Chuan Wang, Stephen Miller, Mario Fritz, Trevor Darrell, and Pieter Abbbeel) was presented at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2011.

    Note: Any judgements about the niftiness of demonstration above might benefit from tempering with the fact that the video is speeded-up (15 times).

    Question: What musical soundtrack might reasonably accompany the video?