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
- What will dating apps look like in 2050 and will we fall in love with robots?on August 14, 2022 at 1:50 am
The development of technology and the metaverse raises a lot of questions like what will relationships between people look like in the future? Will the concept of love change? Will humans fall in love ...
- Uncanny Valley Theory: Robots With Human Characteristics Being Embracedon August 13, 2022 at 11:00 am
While machines that seem too human can be unnerving, studies indicate that mechanical-looking robots with human-like behavior can be empathetic.
- AI Helps Microrobots Learn to Swim and Navigateon August 12, 2022 at 8:42 am
A team of researchers from Santa Clara University, New Jersey Institute of Technology, and the University of Hong Kong have successfully used deep reinforcement learning to teach microrobots how to ...
- Meet BRILLO, the bartending robot that can make small talkon August 12, 2022 at 6:42 am
Researchers in Italy are developing a bartending robot called BRILLO that uses machine-learning technology to carry on a "focused conversation" with customers.
- Machines Are Learning Common Senseon August 11, 2022 at 11:04 am
Researchers with DARPA’s Machine Common Sense (MCS) program recently demonstrated a series of improvements to robotic system performance over the course of multiple experiments.
- Knightscope Robot Roadshow Coming to Millville, New Jerseyon August 11, 2022 at 7:36 am
Knightscope Robot Roadshow Coming to Millville, New Jersey (Photo: Business Wire) The Robot Roadshow has made 50 landings in 19 states and Washington, D.C. to date. Knightscope’s crime-fighting robots ...
- Could robots help with Covid-19 isolation?on August 10, 2022 at 4:30 pm
As Covid outbreaks continue to impact aged care homes across the country, using robots to help keep isolated residents company could be an attractive solution. Researchers from the University of ...
- This Robot Dog Has an AI Brain and Taught Itself to Walk in Just an Houron August 8, 2022 at 7:00 am
A further ten minutes of harassment with a stick taught it how to withstand and recover from being pushed around by its handlers.
- Allowing social robots to learn relations between users' routines and their moodon August 3, 2022 at 6:40 am
Social robots, robots that can interact with humans and assist them in their daily lives, are gradually being introduced in numerous real-world settings. These robots could be particularly valuable ...
- Majority of customers have a positive experience with customer services robotson August 3, 2022 at 12:45 am
The majority of customers have a positive experience when dealing with service robots, according to new research from Durham University Business School. The study found that interacting with robots ...
via Bing News