Communications of the ACM
Robotic Assistants May Adapt to Humans in the Factory
MIT grad students Ron Wilcox, left, and Matthew Gombolay coordinate human-robotic interaction.
Credit: William Litant/MIT
Massachusetts Institute of Technology (MIT) researchers have developed an algorithm that enables a robot to quickly learn an individual's preference for a certain task and adapt accordingly to help complete the task.
The researchers are using the algorithm to train robots and humans to work together. "Using this algorithm, we can significantly improve the robot’s understanding of what the person’s next likely actions are," says MIT professor Julie Shah.
During testing, the researchers examined spar assembly, a process for building the basic structural element of an aircraft's wing. The researchers tested the algorithm on FRIDA, a flexible robot with two arms capable of a wide range of motion that can be manipulated to either fasten bolts or paint sealant into holes, according to Shah.
The researchers first developed a computational model in the form of a decision tree, with each branch representing a choice that a mechanic may make. They then used the decision tree to train a robot to observe an individual's chain of preference. Shah says that once the robot learned a person’s preferred order of tasks, it quickly adapted, either by applying sealant or fastening a bolt according to a person’s particular style of work.
From MIT News
View Full Article
Abstracts Copyright © 2012 Information Inc. 
, Bethesda, Maryland, USA
No entries found