UW Roboticists Learn to Teach Robots from Babies

Reading time ( words)

Children acquire intention-reading skills, in part, through self-exploration that helps them learn the laws of physics and how their own actions influence objects, eventually allowing them to amass enough knowledge to learn from others and to interpret their intentions. Meltzoff thinks that one of the reasons babies learn so quickly is that they are so playful.

“Babies engage in what looks like mindless play, but this enables future learning. It’s a baby’s secret sauce for innovation,” Meltzoff said. “If they’re trying to figure out how to work a new toy, they’re actually using knowledge they gained by playing with other toys. During play they’re learning a mental model of how their actions cause changes in the world. And once you have that model you can begin to solve novel problems and start to predict someone else’s intentions.”

Rao’s team used that infant research to develop machine learning algorithms that allow a robot to explore how its own actions result in different outcomes. Then the robot uses that learned probabilistic model to infer what a human wants it to do and complete the task, and even to “ask” for help if it’s not certain it can.

The team tested its robotic model in two different scenarios: a computer simulation experiment in which a robot learns to follow a human’s gaze, and another experiment in which an actual robot learns to imitate human actions involving moving toy food objects to different areas on a tabletop.

This robot used the new UW model to imitate a human moving toy food objects around a tabletop. By learning which actions worked best with its own geometry, the robot could use different means to achieve the same goal — a key to enabling robots to learn through imitation.University of Washington

In the gaze experiment, the robot learns a model of its own head movements and assumes that the human’s head is governed by the same rules. The robot tracks the beginning and ending points of a human’s head movements as the human looks across the room and uses that information to figure out where the person is looking. The robot then uses its learned model of head movements to fixate on the same location as the human.

The team also recreated one of Meltzoff’s tests that showed infants who had experience with visual barriers and blindfolds weren’t interested in looking where a blindfolded adult was looking, because they understood the person couldn’t actually see. Once the team enabled the robot to “learn” what the consequences of being blindfolded were, it no longer followed the human’s head movement to look at the same spot.

“Babies use their own self-experience to interpret the behavior of others — and so did our robot,” said Meltzoff.

In the second experiment, the team allowed a robot to experiment with pushing or picking up different objects and moving them around a tabletop. The robot used that model to imitate a human who moved objects around or cleared everything off the tabletop. Rather than rigidly mimicking the human action each time, the robot sometimes used different means to achieve the same ends.



Suggested Items

Brittle Pals Bond for Flexible Electronics

05/13/2019 | Rice University
Mixing two brittle materials to make something flexible defies common sense, but Rice University scientists have done just that to make a novel dielectric. Dielectrics are the polarized insulators in batteries and other devices that separate positive and negative electrodes. Without them, there are no electronic devices.

Army Researchers Explore Benefits of Immersive Technology for Soldiers

01/18/2019 | ARL
The emergence of next generation virtual and augmented reality devices like the Oculus Rift and Microsoft HoloLens has increased interest in using mixed reality to simulate training, enhance command and control, and improve the effectiveness of warfighters on the battlefield.

Flights Show Promising Technologies from Industry and Academic Partnerships

02/06/2018 | NASA
The technologies ranged from proposed new space suits to cryogenic propellant research, with implications for future NASA space missions as well as other research efforts.

Copyright © 2021 I-Connect007. All rights reserved.