Alexander Stoytchev is a professor of electrical and computer engineering at Iowa State University in Ames who is combining developmental psychology and neuroscience with artificial intelligence and robotic engineering. He and a team of grad students have developed a program that allows robots to learn, the first essential step if artificial intelligence is to become a reality. As Stoytchev explains:
A truly useful personal robot [must have] the ability to learn on its own from interactions with the physical and social environment. It should not rely on a human programmer once it is purchased. It must be trainable.Here is what they were able to do (from SciAm.com):
In one set of experiments, the robot was presented with 36 different objects, including hockey pucks and Tupperware. It could perform five different actions with each one—grasping, pushing, tapping, shaking and dropping—and had to identify and classify them based only on the sounds they made. After just one action the robot had a 72 percent success rate, but its accuracy soared with each successive action, reaching 99.2 percent after all five. The robot had learned to use a perceptual model to recognize and classify objects—and it could rely on this model to estimate how similar two objects were with only the sounds they made to guide it.
Another set of experiments showed the robot could learn to tell whether or not something was a container. The team presented the machine, topped with a 3-D camera, with objects of different shapes. By dropping a small block on each one and then pushing it, the robot learned to classify objects either as containers—those that moved together with the block ["co-moved"] more often when pushed—or as noncontainers. The robot could then use this knowledge to judge whether unfamiliar objects could hold things; in other words, it had learned, roughly, how to discern the unique characteristics of a container. Read more...
Here are some additional SciAm.com articles discussing recent advances in robotics:
No comments:
Post a Comment