Robots today can perform space missions, solve a Rubik’s cube, sort hospital medication and even make pancakes. But most can’t manage the simple act of grasping a pencil and spinning it around to get a solid grip.
Intricate tasks that require dexterous in-hand manipulation — rolling, pivoting, bending, sensing friction and other things humans do effortlessly with our hands — have proved notoriously difficult for robots.
Now, a University of Washington team of computer scientists and engineers has built a robot hand that can not only perform dexterous manipulation but also learn from its own experience without needing humans to direct it.
Their latest results are detailed in a paper to be presented May 17 at the IEEE International Conference on Robotics and Automation.
“Hand manipulation is one of the hardest problems that roboticists have to solve,” said lead author Vikash Kumar, a UW doctoral student in computer science and engineering. “A lot of robots today have pretty capable arms but the hand is as simple as a suction cup or maybe a claw or a gripper.”
By contrast, the UW research team spent years custom building one of the most highly capable five-fingered robot hands in the world. Then they developed an accurate simulation model that enables a computer to analyze movements in real time. In their latest demonstration, they apply the model to the hardware and real-world tasks like rotating an elongated object.
With each attempt, the robot hand gets progressively more adept at spinning the tube, thanks to machine learning algorithms that help it model both the basic physics involved and plan which actions it should take to achieve the desired result. (This demonstration begins at 1:47 in the video.)
This autonomous learning approach developed by the UW Movement Control Laboratorycontrasts with robotics demonstrations that require people to program each individual movement of the robot’s hand in order to complete a single task.
“Usually people look at a motion and try to determine what exactly needs to happen —the pinky needs to move that way, so we’ll put some rules in and try it and if something doesn’t work, oh the middle finger moved too much and the pen tilted, so we’ll try another rule,” said senior author and lab director Emo Todorov, UW associate professor of computer science and engineering and of applied mathematics.
“It’s almost like making an animated film — it looks real but there was an army of animators tweaking it,” Todorov said. “What we are using is a universal approach that enables the robot to learn from its own movements and requires no tweaking from us.”
Building a dexterous, five-fingered robot hand poses challenges, both in design and control. The first involved building a mechanical hand with enough speed, strength responsiveness and flexibility to mimic basic behaviors of a human hand.
The UW’s dexterous robot hand — which the team built at a cost of roughly $300,000 — uses a Shadow Hand skeleton actuated with a custom pneumatic system and can move faster than a human hand. It is too expensive for routine commercial or industrial use, but it allows the researchers to push core technologies and test innovative control strategies.
“There are a lot of chaotic things going on and collisions happening when you touch an object with different fingers, which is difficult for control algorithms to deal with,” said co-authorSergey Levine, UW assistant professor of computer science and engineering who worked on the project as a postdoctoral fellow at University of California, Berkeley. “The approach we took was quite different from a traditional controls approach.”
The team first developed algorithms that allowed a computer to model highly complex five-fingered behaviors and plan movements to achieve different outcomes — like typing on a keyboard or dropping and catching a stick — in simulation.
Most recently, the research team has transferred the models to work on the actual five-fingered hand hardware, which never proves to be exactly the same as a simulated scenario. As the robot hand performs different tasks, the system collects data from various sensors and motion capture cameras and employs machine learning algorithms to continually refine and develop more realistic models.
“It’s like sitting through a lesson, going home and doing your homework to understand things better and then coming back to school a little more intelligent the next day,” said Kumar.
So far, the team has demonstrated local learning with the hardware system — which means the hand can continue to improve at a discrete task that involves manipulating the same object in roughly the same way. Next steps include beginning to demonstrate global learning — which means the hand could figure out how to manipulate an unfamiliar object or a new scenario it hasn’t encountered before.
The Latest on: Robot learns by experience
via Google News
The Latest on: Robot learns by experience
- Robot uses AI to learn to cook cracking good eggson June 3, 2020 at 9:57 am
The robot must know how and when to add ingredients and also how to make the omelette taste good, which is a subjective human experience. Getting it right involves texture, smell and appearance, ...
- Rosie CEO sees local retailers and customers embracing digital toolson June 3, 2020 at 7:43 am
Coming out of the pandemic, shoppers will continue to blend online grocery seamlessly into their lives, says Nick Nickitas ...
- Seeing Growth in Collaborative Robot Applications, Applied Manufacturing Technologies Releases the jobHopper Portable Automation Workstationon June 2, 2020 at 9:40 am
North America's largest independent full-service systems integration provider supporting manufacturers, robot companies, systems integrators, line builders, and users of robotic automation worldwide, ...
- Robotic digital signage tackles COVID-19on June 2, 2020 at 9:18 am
As the world continues to battle the coronavirus, many technology companies are finding innovative ways to combat the virus,, such as digital signage hand sanitizer dispensers or free virtual ...
- Why Sphero decided to spin off a new company and change its CEO after 10 yearson June 2, 2020 at 6:19 am
It’s a commitment to education tech that lead Sphero to make two key announcements on May 20. First, it was spinning off its public safety division into its own business called Company Six. Second, ...
- Bad Robot: Katie McGrath and JJ Abrams Pledge $10 Million to Anti-Racist Effortson June 1, 2020 at 5:41 pm
Over the next five years, mega-producers Katie McGrath, JJ Abrams, and their Bad Robot Foundation will be donating $10 million to anti-racist organizations. The production company announced the ...
- The 2022 edition of Bucharest Biennial to be curated by roboton May 30, 2020 at 5:21 pm
This year's edition of the Bucharest Biennial, entitled "Farewell to Research," will launch online on June 28 in reaction to the global pandemic. While the ninth Bucharest Biennial is migrating online ...
- 3 Marketing and Customer Experience Trends That Are Transforming Manufacturingon May 29, 2020 at 10:46 am
Most financial advisors would agree that any return that beats the market (which has seen an average annual return of 10.7% since 1871) is pretty darn good. From 1965-2017, Warren Buffett (through ...
- How Can American Retail Learn From Asia’s “New Normal”?on May 29, 2020 at 7:04 am
Just before shoppers begin flocking to their favourite malls for a little revenge buying, retailers have to pull out all the stops to regain their confidence with heightened safety measures. Here are ...
- Bitcoin Profit Review – Legit or Scam Robot?on May 25, 2020 at 1:50 am
Bitcoin Profit supposedly earns enormous profits for users from an investment of as little as 250 USD. The robot was launched in 2014 and is said to be one of the most popular in the crypto trading ...
via Bing News