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
- Sharp takes wraps off new RoBoHoN, with apps aimed at getting families and firms used to 'life with robots' on February 18, 2019 at 3:10 am
The new lineup — two walking models and one that remains seated — focuses more on family users with small children, who can experience ... movements for the robot, such as having it say hello and then ... […]
- Google open-sources PlaNet, an AI agent that learns about the world from images on February 15, 2019 at 11:10 am
But in order to accurately forecast actions in unfamiliar surroundings, those agents have to formulate rules from experience ... a simulated robot lying on the ground that had to learn to stand ... […]
- Artificial Self-consciousness: Does My Robot Know that it Knows? on February 15, 2019 at 4:22 am
Rahner calls it transcendental experience ... awareness that Rahner talks about. Say my robot—let’s call it Robbie—and I play chess. I taught Robbie the basic moves of chess. Robbie also learns from i... […]
- Robots are becoming classroom tutors. But will they make the grade? on February 12, 2019 at 3:06 am
“The robot slowly learns which … behaviors result in high valence and ... Reading socially: Transforming the in-home reading experience with a learning-companion robot. Science Robotics. Published onl... […]
- The Robot Revolution: An (Automated) Wake-Up Call For Marketers on February 6, 2019 at 6:00 am
robots ... need to learn a lot more about the factors that will attract or dissuade customers from seeking a machine’s advice – and actually following it. Certainly, there are consumer variables such ... […]
- Machine Learning Powered Wearable Soft Robot for Patients with Limited Hand Mobility on February 6, 2019 at 4:55 am
Here’s a video from Seoul National University’s Soft Robotics Research Center about the latest development: Study in Science Robotics: Eyes are faster than hands: A soft wearable robot learns user ... ... […]
- AS Watson on health tech, robots and in-store experience on February 5, 2019 at 12:48 am
Essential Retail speaks with Malina Ngai, group chief operating officer at AS Watson, to learn more about the use of technology ... Customers want to try new technologies and the robot format adds to ... […]
- Robot created to imagine itself on January 30, 2019 at 1:03 pm
Humans can imagine themselves in future scenarios or learn by reflecting on their past experience, but robots have not previously simulated themselves in the way which humans do, according to the stud... […]
- Robots learn tasks from people with framework developed by Stanford researchers on October 26, 2018 at 12:11 am
Robots typically learn by interacting with and exploring their environment ... “Humans are by no means optimal at this,” Mandlekar said, “but this experience is still integral for the robots.” These t... […]
- New iRobot® Roomba® i7+ Robot Vacuum Learns a Home's Floor Plan and Empties Itself on September 6, 2018 at 4:06 am
Experience the interactive Multichannel News Release here ... giving customers total control to choose which rooms are cleaned and when. The robot learns every room – remembering up to 10 different fl... […]
via Bing News