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
- St. Clair College is getting 2 new Temi robots. Here's how they help students with learning challengeson May 25, 2022 at 3:01 pm
St. Clair College is bringing on more of the specialized robots that make education and socialization possible for students with developmental disabilities and learning challenges.
- St. Clair College buys robots that remove barriers for students with developmental disabilitieson May 25, 2022 at 2:36 pm
St. Clair College has used a $20,000 donation to buy two more robots that help remove academic and social barriers for students with developmental disabilities. Atura Power made the donation to help ...
- Dyson Is Testing Out Robots To Do Your House Chores For Youon May 25, 2022 at 1:18 pm
Dyson may be best known for vacuum cleaners, but the British company has big plans for home robotics -- and a big budget to make them happen ...
- Dyson’s unveils robot claws that could retire your dishwasher by 2030on May 25, 2022 at 11:34 am
Dyson has revealed its next advancements in household robots, which are capable of washing and drying dishes, cleaning furniture and tidying up after | Trusted Reviews ...
- Dyson working on home robotson May 25, 2022 at 10:09 am
Dyson is moving beyond vacuum cleaners and hand driers and will try to develop robots capable of helping with household chores. The company has announced plans to create a major robotics centre at its ...
- Sick of picking up toys? Dyson’s future robots want to do it for youon May 25, 2022 at 9:31 am
Dyson today shared its ambitious plans to sell robots that can do your The company best known for vacuums is in the midst of a massive hiring push as it looks to make consumer robots that roam homes ...
- Dyson launches a hiring spree for hundreds of engineers to build robots capable of doing household choreson May 25, 2022 at 3:21 am
Dyson is developing technology to put its at-home assistant robots into people's homes by the end of this decade.
- Is the Litter-Robot 4 worth $650?on May 25, 2022 at 2:00 am
So I jumped at the opportunity to try out the Litter-Robot 4 and its promise that I wouldn't have to follow my cat to the bathroom and promptly clean up his business. The Litter-Robot 4 senses when ...
- Dyson eyes robots that can do your household choreson May 25, 2022 at 1:45 am
Dyson has shown off a series of prototype robots it’s developing, and announced plans to hire hundreds of engineers over the next five years in order to build robots capable of household chores. The ...
- Researchers create digital humans that learn complex movementson May 24, 2022 at 9:07 am
Researchers at Meta's Artificial Intelligence Research Lab (Facebook) in the U.S. and at the University of Twente's Neuromechanical Modelling and Engineering Lab in the Netherlands (led by Prof.dr.ir ...
via Bing News