New program to help robots 'see' better

WASHINGTON: MIT scientists have developed a new algorithm that could enable household robots to better identify objects in cluttered environments. 

Researchers believe that the robots should take advantage of their mobility and their relatively static environments to make object recognition easier by imaging objects from multiple perspectives before making judgements about their identity. Matching up the objects depicted in the different images, however, poses computational challenges. 

Researchers at the Massachusetts Institute of Technology (MIT) show that a system using an off-the-shelf algorithm to aggregate different perspectives can recognize four times as many objects as one that uses a single perspective, while reducing mis-identifications. 

Researchers believe that the robots should take advantage of their mobility and their relatively static environments to make object recognition easier by imaging objects from multiple perspectives before making judgements about their identity.