Collaborative learning for robots | MIT News

“If constraints on power, communication, or computation mean that the robots can’t pool their data at one location, how can they collectively build a model? … At the Uncertainty in Artificial Intelligence conference in July, researchers from MIT’s Laboratory for Information and Decision Systems will answer that question. They present an algorithm in which distributed agents — such as robots exploring a building — collect data and analyze it independently. Pairs of agents, such as robots passing each other in the hall, then exchange analyses.”

Source: newsoffice.mit.edu

Conference website:

http://auai.org/uai2014/

Paper presented (PDF):

http://auai.org/uai2014/proceedings/individuals/182.pdf

Laboratory for Information and Decision Systems

http://lids.mit.edu

Found on Zero Moment

http://www.popsci.com/blog-network/zero-moment

See on Scoop.it – Cultibotics

John Payne

John Payne