Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

This 5-fingered robot hand learns to get a grip on its own

10.05.2016

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.


A University of Washington research team has custom built one of the most highly capable five-fingered robot hands in the world. They also developed an accurate simulation model that enables a computer to analyze movements in real time, and in their latest demonstration (beginning at 1:47), 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.

Credit: Vikash Kumar, University of Washington

Now, a University of Washington team of computer science and engineering researchers 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 autonomous learning approach developed by the UW Movement Control Laboratory contrasts 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-author Sergey 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 research was funded by the National Science Foundation and the National Institutes of Health.

For more information, contact Kumar at vikash@cs.washington.edu.

Media Contact

Jennifer Langston
jlangst@uw.edu
206-543-2580

 @UW

http://www.washington.edu/news/ 

Jennifer Langston | EurekAlert!

Further reports about: Robotics computer science machine learning algorithms

More articles from Power and Electrical Engineering:

nachricht Producing electricity during flight
20.09.2017 | Albert-Ludwigs-Universität Freiburg im Breisgau

nachricht Solar-to-fuel system recycles CO2 to make ethanol and ethylene
19.09.2017 | DOE/Lawrence Berkeley National Laboratory

All articles from Power and Electrical Engineering >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: Highly precise wiring in the Cerebral Cortex

Our brains house extremely complex neuronal circuits, whose detailed structures are still largely unknown. This is especially true for the so-called cerebral cortex of mammals, where among other things vision, thoughts or spatial orientation are being computed. Here the rules by which nerve cells are connected to each other are only partly understood. A team of scientists around Moritz Helmstaedter at the Frankfiurt Max Planck Institute for Brain Research and Helene Schmidt (Humboldt University in Berlin) have now discovered a surprisingly precise nerve cell connectivity pattern in the part of the cerebral cortex that is responsible for orienting the individual animal or human in space.

The researchers report online in Nature (Schmidt et al., 2017. Axonal synapse sorting in medial entorhinal cortex, DOI: 10.1038/nature24005) that synapses in...

Im Focus: Tiny lasers from a gallery of whispers

New technique promises tunable laser devices

Whispering gallery mode (WGM) resonators are used to make tiny micro-lasers, sensors, switches, routers and other devices. These tiny structures rely on a...

Im Focus: Ultrafast snapshots of relaxing electrons in solids

Using ultrafast flashes of laser and x-ray radiation, scientists at the Max Planck Institute of Quantum Optics (Garching, Germany) took snapshots of the briefest electron motion inside a solid material to date. The electron motion lasted only 750 billionths of the billionth of a second before it fainted, setting a new record of human capability to capture ultrafast processes inside solids!

When x-rays shine onto solid materials or large molecules, an electron is pushed away from its original place near the nucleus of the atom, leaving a hole...

Im Focus: Quantum Sensors Decipher Magnetic Ordering in a New Semiconducting Material

For the first time, physicists have successfully imaged spiral magnetic ordering in a multiferroic material. These materials are considered highly promising candidates for future data storage media. The researchers were able to prove their findings using unique quantum sensors that were developed at Basel University and that can analyze electromagnetic fields on the nanometer scale. The results – obtained by scientists from the University of Basel’s Department of Physics, the Swiss Nanoscience Institute, the University of Montpellier and several laboratories from University Paris-Saclay – were recently published in the journal Nature.

Multiferroics are materials that simultaneously react to electric and magnetic fields. These two properties are rarely found together, and their combined...

Im Focus: Fast, convenient & standardized: New lab innovation for automated tissue engineering & drug

MBM ScienceBridge GmbH successfully negotiated a license agreement between University Medical Center Göttingen (UMG) and the biotech company Tissue Systems Holding GmbH about commercial use of a multi-well tissue plate for automated and reliable tissue engineering & drug testing.

MBM ScienceBridge GmbH successfully negotiated a license agreement between University Medical Center Göttingen (UMG) and the biotech company Tissue Systems...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

Event News

“Lasers in Composites Symposium” in Aachen – from Science to Application

19.09.2017 | Event News

I-ESA 2018 – Call for Papers

12.09.2017 | Event News

EMBO at Basel Life, a new conference on current and emerging life science research

06.09.2017 | Event News

 
Latest News

Comet or asteroid? Hubble discovers that a unique object is a binary

21.09.2017 | Physics and Astronomy

Cnidarians remotely control bacteria

21.09.2017 | Life Sciences

Monitoring the heart's mitochondria to predict cardiac arrest?

21.09.2017 | Health and Medicine

VideoLinks
B2B-VideoLinks
More VideoLinks >>>