Advertisement
UK markets close in 5 hours 2 minutes
  • FTSE 100

    7,838.46
    -38.59 (-0.49%)
     
  • FTSE 250

    19,289.78
    -160.89 (-0.83%)
     
  • AIM

    741.37
    -3.92 (-0.53%)
     
  • GBP/EUR

    1.1682
    -0.0001 (-0.01%)
     
  • GBP/USD

    1.2443
    +0.0004 (+0.04%)
     
  • Bitcoin GBP

    52,149.16
    +2,614.25 (+5.28%)
     
  • CMC Crypto 200

    1,332.81
    +20.19 (+1.56%)
     
  • S&P 500

    5,011.12
    -11.09 (-0.22%)
     
  • DOW

    37,775.38
    +22.07 (+0.06%)
     
  • CRUDE OIL

    82.30
    -0.43 (-0.52%)
     
  • GOLD FUTURES

    2,396.10
    -1.90 (-0.08%)
     
  • NIKKEI 225

    37,068.35
    -1,011.35 (-2.66%)
     
  • HANG SENG

    16,224.14
    -161.73 (-0.99%)
     
  • DAX

    17,722.74
    -114.66 (-0.64%)
     
  • CAC 40

    8,002.06
    -21.20 (-0.26%)
     

CMU and Facebook AI Research use machine learning to teach robots to navigate by recognizing objects

Carnegie Mellon today showed off new research into the world of robotic navigation. With help from the team at Facebook AI Research (FAIR), the university has designed a semantic navigation that helps robots navigate around by recognizing familiar objects.

The SemExp system, which beat out Samsung to take first place in a recent Habitat ObjectNav Challenge, utilizes machine learning to train the system to recognize objects. That goes beyond simple superficial traits, however. In the example given by CMU, the robot is able to distinguish an end table from a kitchen table, and thus extrapolate in which room it’s located. That should be more straightforward, however, with a fridge, which is both pretty distinct and is largely restricted to a singe room.

"Common sense says that if you're looking for a refrigerator, you'd better go to the kitchen,” Machine Learning PhD student Devendra S. Chaplot said in a release. “Classical robotic navigation systems, by contrast, explore a space by building a map showing obstacles. The robot eventually gets to where it needs to go, but the route can be circuitous.”

CMU notes that this isn’t the first attempt to apply semantic navigation to robotics, but previous efforts have relied too heavily on having to memorize where objects were in specific areas, rather than tying an object to where it was likely to be.