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
- Using large language models to code new tasks for robotson November 28, 2023 at 7:28 am
You've likely heard that "experience is the best teacher"—but what if learning in the real world is prohibitively expensive? This is the plight of roboticists training their machines on manipulation ...
- An approach that allows robots to learn in changing environments from human feedback and explorationon November 28, 2023 at 4:50 am
To best assist humans in real-world settings, robots should be able to continuously acquire useful new skills in dynamic and rapidly changing environments. Currently, however, most robots can only ...
- Games Where You Build Robotson November 27, 2023 at 2:34 pm
This isn't a game that holds players’ hands and requires time and practice to learn ... learning experience for children who are interested in robotics. With engaging but challenging activities, ...
- Humanoid robots are here, but they’re a little awkward. Do we really need them?on November 26, 2023 at 10:30 pm
Building a robot that’s both human-like and useful is a decades-old engineering dream inspired by popular science fiction.
- The best robot vacuums of 2023, tested by editorson November 26, 2023 at 8:03 am
We tested nine great robot vacuums that can keep your house cleaner by picking up dirt, dust and pet hair on a daily basis.
- Roomba, Bissell, Shark: So Many Robot Vacuums Are on Sale for Cyber Monday — Up to 83% Offon November 26, 2023 at 3:30 am
Ahead of Cyber Monday, there are great deals on robot vacuums that will save you time and energy. Score major discounts, up to 83 percent off, on vacuums from beloved brands like iRobot, Shark, and ...
- Roomba Robot Vacuums Are Up to 42% Off During Amazon’s Black Friday Saleon November 22, 2023 at 3:31 am
Learn more. People / Rachel Marek If a time-saving cleaning gadget is on your holiday shopping wish list, you’re in luck. Amazon just dropped Black Friday deals on popular Roomba robot vacuums. Right ...
- Save Over 40% on Robot Vacuums With Amazon’s Black Friday Dealson November 17, 2023 at 3:19 pm
Us Weekly has affiliate partnerships so we may receive compensation for some links to products and services. Are you in the market for a new vacuum? Then allow Us to introduce you to a robot vacuum.
- Robot chef can learn recipes from YouTubeon November 14, 2023 at 4:00 pm
Researchers at Cambridge University have trained a robot chef that learns how to recreate recipes by watching cooking videos. The robot uses a machine learning method known as “imitation learning” to ...
via Bing News