Babies learn about the world by exploring how their bodies move in space, grabbing toys, pushing things off tables and by watching and imitating what adults are doing.
But when roboticists want to teach a robot how to do a task, they typically either write code or physically move a robot’s arm or body to show it how to perform an action.
Now a collaboration between University of Washington developmental psychologists and computer scientists has demonstrated that robots can “learn” much like kids — by amassing data through exploration, watching a human do something and determining how to perform that task on its own.
“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 senior author Rajesh Rao, a UW professor of computer science and engineering.
“If you want people who don’t know anything about computer programming to be able to teach a robot, the way to 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.”
The research, which combines child development research from the UW’s Institute for Learning & Brain Sciences Lab (I-LABS) with machine learning approaches, was published in a paper in November in the journal PLOS ONE.
In the paper, the UW team developed a new probabilistic model aimed at solving a fundamental challenge in robotics: building robots that can learn new skills by watching people and imitating them.
The roboticists collaborated with UW psychology professor and I-LABS co-director Andrew Meltzoff, whose seminal research has shown that children as young as 18 months can infer the goal of an adult’s actions and develop alternate ways of reaching that goal themselves.
In one example, infants saw an adult try to pull apart a barbell-shaped toy, but the adult failed to achieve that goal because the toy was stuck together and his hands slipped off the ends. The infants watched carefully and then decided to use alternate methods — they wrapped their tiny fingers all the way around the ends and yanked especially hard — duplicating what the adult intended to do.
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.
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.
The Latest on: Robots that learn
via Google News
The Latest on: Robots that learn
- Sex robots are here, but laws aren't keeping up with the ethical and privacy issues they raiseon June 27, 2020 at 11:17 am
The robots are here. Are the “sexbots” close behind? From the Drudge Report to The New York Times, sex robots are rapidly becoming a part of the national conversation about the future of sex and ...
- ‘Robot Chicken’ Returns for Season 10, Part 2 With Mutants, Magic, and Mayhemon June 27, 2020 at 9:17 am
The Robot Chicken team is back with more stop-motion animated antics, all leading up to the 200th episode arriving next month.
- How To Make Robots Behave More Like People — And Why It Matterson June 26, 2020 at 12:54 pm
Had my friend not been with me, explaining the automation to me, I very likely would have gotten into an accident — in a car designed to keep me safer. Fortunately, Tesla released its new “Traffic ...
- 20 things from Best Buy that make aging in place easieron June 25, 2020 at 10:13 am
From smart thermostats and doorbells to wireless headphones and lights, these smart devices make aging in place easier.
- Medical Robots Market Worth $20.70 Billion, Globally, by 2027 at 14.2% CAGR: Verified Market Researchon June 25, 2020 at 6:55 am
Verified Market Research recently published a report, "Medical Robots Market by Product (Instruments & Accessories, Robotic ...
- J.J. Abrams' production company Bad Robot releases 20-page employee guide on practicing anti-racismon June 23, 2020 at 12:26 pm
Director J.J. Abrams’ production company, Bad Robot, released a 20-page guide to help its employees practice anti-racism.
- Fork off: This ubiquitous machine is about to turn into a roboton June 23, 2020 at 7:00 am
Humans have a role in the future of work, but shared autonomy may be the new reality for warehouse and logistics.
- Robots that can learn? Watson professor is working on iton June 22, 2020 at 1:05 pm
AI algorithms will help service robots in everyday environments to gain knowledge and develop their own reasoning abilities.
- AI-Powered Agricultural Robots: A Revolution in Affordable Ultra-Precision, Says IDTechExon June 22, 2020 at 11:30 am
The developments in agricultural robotics, machine vision, and AI will drive a deep and far-reaching transformation of the way farming is carried out. Yes, today the fleet sizes and the total area ...
- This $75,000 Boston Dynamics robot 'dog' is for sale—take a lookon June 22, 2020 at 10:19 am
Boston Dynamics' well-known robot, Spot, is available for commercial purchase. Michael Perry, VP of business development at Boston Dynamics, says Spot has "seemingly limitless" applications for ...
via Bing News