Scientists building ‘neurotic’ robots to help them make smarter, more human decisions
A group of researchers is exploring the possibility of programming robot brains to be more “neurotic” in order to help them make more human-like decisions. Discovery News reported on one team’s findings which were presented this week at the IEEE International Conference on Robotics and Automation in Hong Kong.
Jeff Krichmar, a professor of cognitive science at the University of California, Irvine, told Discovery, “We’re trying to make the robot brain more like human brain. The brain has incredibly flexibility and adaptability. If you look at any artificial system, it’s far more brittle than biology.”
Modern robots can solve math problems, play chess and even read and respond to some human emotions. However, when they try to perform other basic human tasks like walking, running, carrying on a conversation or recognizing basic objects in their environment, their abilities fall short.
Krichmar and his team are experimenting with robotic awareness and trying to teach mechanical brains to behave more like human and animal brains by programming traits that mimic obsessive-compulsive disorder or a fear of open spaces.
For instance, the team studied the actions of neurotransmitter chemicals serotonin and dopamine in mice as the animals solved a maze or reacted to an unfamiliar environment. Neurotransmitters are the chemicals that combine to constitute awareness and to contribute to our senses of pleasure and well-being.
The scientists then mimicked the actions of the brain chemicals by translating them into equations in the robots’ cognitive software.
“Were mimicking the action of the chemicals with equations,” explained Krichmar. “We are doing mathematical models of brain or cognitive system, then putting that in software and it becomes the controller for the robot.”
“If you put a rodent in a room that is open and unfamiliar, it will hug the walls,” he said. “It will hide until it becomes comfortable, then it will move across the room. It will wait until if feels comfortable. We did that with a robot and made it so it was so anxious it would never cross the room.”
Teaching a robot to feel fear or anxiousness could contribute to its ability to adapt to changing conditions and instill in it a sense of self-preservation. A search-and-rescue robot, for example, could analyze weather conditions before attempting a mission.
Krichmar and his team have already developed a robot named “Carl’s Junior” that looks like a colorfully striped turtle. The robot responds to verbal commands and other external signals. The robot is used as a therapeutic tool for children on the autism spectrum who are less comfortable interacting with humans than they are with inanimate — but responsive — objects.
Other teams at the conference are presenting robots that can learn like babies learn. Krichmar told Discover that he’s excited about where the field is headed.
“You will see robots with these capabilities actually doing things in the home or for search and rescue,” he said. “The time is right and its moving.”
[image of contemplative robot via Shutterstock.com]