A robot hand that can perform extremely dexterous manoeuvres and learn from its own experiences has been developed by University of Washington researchers.
Intricate tasks that require dexterous in-hand manipulation such as rolling, pivoting, bending, sensing friction and other actions that humans carry out effortlessly have proved notoriously difficult for robots.
The new robot hand has been designed to be as dexterous as possible and its ability to learn from its own experiences allows it to carry out actions without human input.
"Hand manipulation is one of the hardest problems that roboticists have to solve," said Vikash Kumar, leader of the research project. "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."
The Washington team spent years custom building what they claim is one of the most highly capable five-fingered robot hands in the world.
A computer simulation model was then developed that enables a computer to analyse movements in real time.
In their latest demonstration, they applied 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 Professor Emo Todorov, who also worked on the project.
"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."
The construction of the robot hand itself poses numerous challenges in balancing finessed design and control with enough speed, strength, responsiveness and flexibility to mimic the basic behaviours of a human hand.
The device, which cost approximately $300,000 (£207,000) to construct, uses a shadow hand skeleton actuated with a custom pneumatic system. It can move faster than a human hand.
Although still too expensive for routine commercial or industrial use, it allows the researchers to test the core technologies.
Attempts to create robots that can move more like humans are ongoing. University of Michigan researchers recently demonstrated an unsupported two-legged robot that is capable of walking down steep slopes and traversing uneven ground using a 3D walking algorithm that can be applied to other robots.