Researchers from MIT have created a robot hand that can handle your fine breakables.
Daniela Rus of MIT’s Distributed Robotics Lab demonstrated the 3-D-printed robotic hand which was made out of silicone rubber. The three-fingered bot can handle items as delicate as an egg and as thin as a compact disc. But the soft silicone isn’t the only aspect of the robot that allows it to deal with fragile items. Sensors in the fingers estimate the size and shape of an object so that it can identify a particular object from a set.
“Robots are often limited in what they can do because of how hard it is to interact with objects of different sizes and materials,” Rus says. “Grasping is an important step in being able to do useful tasks; with this work we set out to develop both the soft hands and the supporting control and planning systems that make dynamic grasping possible.”
The hand is an example of Rus’ ongoing work on what she calls “soft robots,” which are bots made of non-traditional materials such as paper, silicone and fiber. The softness, say researchers, helps robots deal with irregularly shaped objects.
“A robot with rigid hands will have much more trouble with tasks like picking up an object,” says Rus’ colleague and graduate student Bianca Homberg. “This is because it has to have a good model of the object and spend a lot of time thinking about precisely how it will perform the grasp.”
The challenge is that the flexibility of a soft robot hand makes it tough to know exactly where an item is or if it has been successfully picked up. When Rus’ silicone hand picks up an item, data is collected from the bend sensors in the robots fingers. That data is then compared to data the robot has already stored on past objects, to try to find a match. Rus hopes to integrate more sensors into future versions of the robot.
“If we want robots in human-centered environments, they need to be more adaptive and able to interact with objects whose shape and placement are not precisely known,” Rus says. “Our dream is to develop a robot that, like a human, can approach an unknown object, big or small, determine its approximate shape and size, and figure out how to interface with it in one seamless motion.”