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.
Learn more: This five-fingered robot hand learns to get a grip on its own
The Latest on: Robot learns by experience
[google_news title=”” keyword=”robot learns by experience” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Robot learns by experience
- 'Like a second family': Wilsonville High School team builds robots, friendshipon April 26, 2024 at 7:06 pm
A Wilsonville High School team is teaching kids how to build a robot from the ground up — with its members learning coding, confidence and comradery.
- AI robot graduation speaker is not A-OK for some students at D'Youvilleon April 26, 2024 at 11:46 am
D'Youville has invited Sophia, a humanoid automaton produced by Hong Kong-based Hanson Robotics, to address its graduates at the May 11 ceremony at LECOM Harborcenter. And that is a problem for scores ...
- AI robot 'Sophia' announced as D'Youville University's spring 2024 commencement speakeron April 25, 2024 at 7:03 am
The social humanoid robot was created by Hanson Robotics ... providing a safe environment for people to learn through experience." ...
- Whisker Litter-Robot 4 review: This $700 self-cleaning litter box outperformed every other box we testedon April 24, 2024 at 2:01 pm
The Whisker Litter-Robot 4 is a reliable self-cleaning litter box. We weighed its pros and cons against eight other automatic boxes before naming it the best.
- THE WILD ROBOT Shares Stunning Trailer, Cast Includes Nyong’o, Pascal, and Hamillon April 24, 2024 at 1:11 am
We love watching you learn and develop bonds ... it will be a marvelous experience. A release shares of The Wild Robot‘s cast: The Wild Robot stars Academy Award® winner Lupita Nyong’o ...
- The week's best robot vacuum deals: Catch the Roomba j7 at 50% offon April 19, 2024 at 2:00 am
Only three things are certain in life: Death, taxes, and a few days each month when you need to vacuum but just don't have time. Whether you detest the chore or hope to make your home upkeep a bit ...
- Senior teacher endorses robots assisting in schoolon April 17, 2024 at 10:28 pm
Senior teacher at Alpha Infant School Sabrina Raymond-Hunter has endorsed the ‘ICHEETAH’ robot, a smart educational AI-powered tool that will advance the way young children learn and interact with ...
- This $700 Robot Vacuum and Mop Leaves Floors ‘Spotless,’ and It’s on Sale for $160 Right Now at Amazonon April 17, 2024 at 4:30 am
The Manvins Robot Vacuum and Mop automatically vacuums and mops your floors, saving you time and energy. It sucks up pet hair, dirt, and dust with ease and is small enough to clean under furniture and ...
- Mentee Robotics de-cloaks to launch new AI-driven humanoid roboton April 17, 2024 at 4:00 am
Mentee Robotics has emerged on the scene with a new AI-driven humanoid robot, planned for production release in early 2025.
- Meet The New AI-Robot Billionaireon April 15, 2024 at 3:30 am
Armed with more than $750 million in funding, Brett Adcock vows that Figure will become one of the most important businesses in the world. First, he has a lot of work to do.
via Bing News