How to teach your robot well

Washington, Mar 9 (ANI): In a new study, scientists have identified the types of questions a robot can ask during a learning interaction that are most likely to characterize a smooth and productive relationship with humans.

These questions, designed by researchers from Georgia Tech's Center for Robotics and Intelligent Machines (RIM), are about certain features of tasks, more so than labels of task components or real-time demonstrations of the task itself.

The researchers identified these questions not by studying robots, but by studying the everyday people who one day will be their masters.

"People are not so good at teaching robots because they don't understand the robots' learning mechanism," Maya Cakmak, the lead author, said.

"It's like when you try to train a dog, and it's difficult because dogs do not learn like humans do. We wanted to find out the best kinds of questions a robot could ask to make the human-robot relationship as 'human' as it can be," she said.

Cakmak's study attempted to discover the role "active learning" concepts play in human-robot interaction.

In a nutshell, active learning refers to giving machine learners more control over the information they receive. Simon, a humanoid robot created in the lab of Andrea Thomaz, co-author of the study, is well acquainted with active learning; Thomaz and Cakmak are programming him to learn new tasks by asking questions.

She designed two separate experiments - first, she asked human volunteers to assume the role of an inquisitive robot attempting to learn a simple task by asking questions of a human instructor.

Having identified the three main question types (feature, label and demonstration), Cakmak tagged each of the participants' questions as one of the three. The overwhelming majority (about 82 percent) of questions were feature queries, showing a clear cognitive preference in human learning for this query type.

Next, Cakmak recruited humans to teach Simon new tasks by answering the robot's questions and then rating those questions on how "smart" they thought they were. Feature queries once again were the preferred interrogatory, with 72 percent of participants calling them the smartest questions.

"These findings are important because they help give us the ability to teach robots the kinds of questions that humans would ask.

"This in turn will help manufacturers produce the kinds of robots that are most likely to integrate quickly into a household or other environment and better serve the needs we'll have for them," Cakmak said.

The findings of the study have been presented at the 7th ACM/IEEE Conference on Human-Robot Interaction (HRI). (ANI)