A five-fingered robot hand that can not only perform dexterous manipulation but also learn from its own experience without needing humans to direct it has been developed by researchers, including one of Indian-origin.
Robots today can perform space missions, solve a Rubik’s cube, sort hospital medication and even make pancakes. But most cannot manage the simple act of grasping a pencil and spinning it around to get a solid grip, researchers said.
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, they said.
Now, scientists from University of Washington (UW) have built a robot hand that can not only perform dexterous manipulation but also learn from its own experience without needing humans to direct it.
“Hand manipulation is one of the hardest problems that roboticists have to solve. 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,” said Vikash Kumar from UW.
Researchers 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 analyse movements in real time.
In their latest demonstration, they apply the model to the hardware and real-world tasks like rotating an elongated object, researchers said.
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, they said.
This autonomous learning approach contrasts with robotics demonstrations that require people to programme each individual movement of the robot’s hand in order to complete a single task, researchers said.
The dexterous robot hand uses a Shadow Hand skeleton actuated with a custom pneumatic system and can move faster than a human hand, they said.
It is too expensive for routine commercial or industrial use, but it allows researchers to push core technologies and test innovative control strategies.
Researchers first developed algorithms that allowed a computer to model highly complex five-fingered behaviours and plan movements to achieve different outcomes – like typing on a keyboard or dropping and catching a stick – in simulation.
Most recently, they transferred the models to work on the actual five-fingered hand hardware, which never proves to be exactly the same as a simulated scenario, researchers said.
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, they said.
