Robots Can be Taught Like Human Babies: The Evolution of AI
Scary as it may sound, we may be teaching robots in the same way we teach human babies in the future. Scientists have demonstrated that robots can "learn" like kids, amassing data through exploration, watching a human perform a task, and figuring out how best to carry out that task.
"You can look at this as a first step in building robots that can learn from humans in the same way that infants learn from humans," said Rajesh Rao, one of the researchers, in a news release. "If you want people who don't know anything about computer programming to be able to teach a robot, the way you do it is through demonstration-showing the robot how to clean your dishes, fold your clothes, or do household chores. But to achieve that goal, you need the robot to be able to understand those actions and perform them on their own."
In this latest study, the researchers developed a new probabilistic model aimed at solving the challenge of building robots that can learn new skills by watching people and imitating them.
Children learn through self-exploration that helps them learn the laws of physics and how their actions influence objects. Over time, they build up enough knowledge to learn from others.
In this case, the scientists used this knowledge of babies to develop machine learning algorithms that allow a robot to explore how its own actions result in different outcome. Then, the robot uses the learned probabilistic model to infer what a human wants it to do and complete the task. It will even "ask" for help if it's not certain it can.
Initial experiments involved learning how to infer goals and imitate simple behaviors. However, the researchers plan to explore how such a model can also help robots learn more complicated tasks over time.
The findings are published in the journal PLOS One.
For more great science stories and general news, please visit our sister site, Headlines and Global News (HNGN).