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
- The Age of Thinking Machineson November 18, 2019 at 11:55 pm
Every day millions of machines are fed with data, they learn new things, become better and smarter. They expand their ability to store knowledge, transfer it and exchange it with other machines. We ...
- Top 10 reasons Roborock is better than iRobot Roombaon November 18, 2019 at 6:21 pm
iRobot even recommends that you run the vacuum at different times of day to help it better learn your ... Two out of the three robot vacuums that Roborock launched this year include mopping ...
- How To Get Your Résumé Past The Artificial Intelligence Gatekeeperson November 18, 2019 at 6:34 am
It’s no longer a secret that getting past the robot résumé readers to a human – let alone land an interview – can seem like trying to get in to see the Wizard of Oz. As the résumés of highly qualified ...
- Miko 2, one of the best kids robots, lauched in North America- 9to5Googleon November 16, 2019 at 4:36 pm
If you didn’t know, Miko is all about offering an interactive and engaging way for kids to learn with technology, and the Miko 2 is their best kids robot yet with interactive voice-controlled features ...
- Stuffed toys, Robotics, Coding, and Bedtime Stories, the Mochi Robot for kids has it allon November 16, 2019 at 8:30 am
What if this new method was playful and intuitive enough to help children learn the basics of coding without being attached to a phone or a tablet? What if it had an aspect of storytelling that made ...
- DENSO Robots Featured at New Cranbrook Institute of Science Exhibiton November 15, 2019 at 5:33 am
Starting Nov. 19 through July 3, 2020, exhibit visitors can interact with and learn from robots previously used in space ... it also serves as an entry point for students and families to experience ...
- Scientists believe programming AI for self-preservation could be the key to giving robots feelingson November 11, 2019 at 2:44 pm
‘A computer simulation of a hurricane won’t get us wet,’ they argue, pointing the idea there may be a fundamental divide between human experience and robot experience. Whether real or simulated ...
- Welcome to robot university (only robots need apply)on November 7, 2019 at 3:26 am
“We propose RoboNet, an open database for sharing robotic experience,” they say. So any robot can learn from the experience of another. To kick-start the database, the team has already recorded some ...
- Abusing a robot won’t hurt it, but it could make you a crueller personon November 6, 2019 at 2:11 pm
Paro can learn new names, respond to greetings ... After all, we may pity or despise a character in a book, movie, or video game without believing they actually experience anything. That said, a link ...
- Armchair Quarterback Virtual Reality Experience Puts Fans on the Fieldon November 5, 2019 at 4:38 pm
"The Armchair Quarterback VR experience will absolutely do that for them." College football fans can attend one of the three remaining Nissan Heisman House Tour events in November 2019 for their ...
via Bing News