The robotic gripper uses the full envelope technique to grasp a tennis ball. Photo by MIT News/CSAIL
BOSTON, Sept. 30 (UPI) -- The word "robot" recalls metal and rigidity, swift and calculated motions -- not necessarily ideal for more delicate tasks, like handling eggs.
But researchers at MIT have designed a robot with a softer touch, capable of handling and identifying everyday objects, fragile or not.
The new robot -- designed, built and tested by engineers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) -- is outfitted with a hand made of three silicone rubber fingers, both soft and dextrous. The gripper has two techniques for grasping objects, the pinch and the full envelope.
More delicate objects can be fully enveloped by the silicone gripper for extra-protective handling, while a more rigid or oddly shaped object, like a compact disc, can be gripped with more precise finger point pressure.
The gripper is outfitted with sensors that measure the shape of an object and relay the information to robot's central processing unit. With just three data points, the robot can identify the object by comparing it to past gripping experiences.
"As a human, if you're blindfolded and you pick something up, you can feel it and still understand what it is," Robert Katzschmann, a PhD candidate and researcher at CSAIL, said in a press release. "We want to develop a similar skill in robots -- essentially, giving them 'sight' without them actually being able to see."
While the robot's functionality is powered by traditional technology (rigid pumping pistons), researchers at the MIT lab are continuing to experiment with robots built out of non-traditional materials like paper and synthetic fibers -- so-called soft robots.
"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," explained Daniela Rus, the director of CSAIL's Distributed Robotics Lab. "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."