Austrian researchers are working to advance the development of artificial intelligence (AI) and equip robots with common sense.
Graz University of Technology researcher Gerald Steinbauer has developed a deduction mechanism that enables robots to detect errors and repair their belief system accordingly. "We've used so-called situation calculus to model deductions in a logic language that can describe the actions carried out by a given agent and their effects," Steinbauer says.
The method involves continuously creating automatic diagnoses by observing where the beliefs of the robot no longer align with the prevailing situation.
The researchers found situation calculus can be used both for monitoring and diagnostic purposes as well as for autonomous decisions made by the robot. If the robot knows what the effect of a given action is, it can learn to deduce what needs to be done next.
"We tried to align what the robot had planned and what has really happened, by putting it down in formal language," Steinbauer says.
During testing, a robot was entrusted with simple delivery tasks for several days in a row, and it proved to be immune to irritation even when tricks were played on it; the researchers utilized common-sense databases in order to feed the models.
From Phys.org
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found