Researchers at the Massachusetts Institute of Technology (MIT) have developed a system that allows robots to learn complicated tasks that would normally confuse them with too many complicated rules, such as setting a dinner table under specific conditions.
The system, called Planning with Uncertain Specifications (PUnS), gives robots the humanlike planning ability to simultaneously consider many ambiguous or contradictory requirements, in order to reach an end goal.
The system always chooses the most likely action to take based on the "belief" about some probable specifications for the task it is supposed to perform.
Said Ankit Shah of MIT's Interactive Robotics Group, “The vision is to put programming in the hands of domain experts, who can program robots through intuitive ways, rather than describing orders to an engineer to add to their code."
From MIT News
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found