This 3D Printed Robot Can Pick Up Even Your Most Fragile Mess
Including stuffed animals
Robotic hands aren’t typically known for being delicate or spontaneous. They’re more likely to be part of an assembly line, or specifically designed to do one task perfectly, over and over. But those days may be waning. A new robotic hand printed out of silicone by MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) can pick up just about any object, no matter how delicate or strangely sized. The results were released today, and really, it can pick up any small object:
The variety is incredibly important. “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,” Daniela Rus, CSAIL’s director said in a statement. “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.”
Sometimes, that means that the robot needs to be able to pick up things lying in awkward positions. CD’s may be nearly obsolete, but the fact that the robot can pick up a CD lying flat on a table is still pretty impressive.
The silicone fingers are equipped with sensors that analyze the object they are touching and compare it to other items in it’s database. Then, they apply force accordingly and are able to pick up plastic bottles, individual pieces of paper, and even eggs without crushing them. Take a look at this guy delicately picking up a stuffed animal:
CSAIL isn’t the only group looking into this. Researchers at Carnegie Mellon University also announced this week the development of delicate, highly-sensitive robot hands equipped with optical sensors that actually let the hand see the object that it is picking up, increasing the robot’s dexterity. Both the CMU and MIT research was presented at the International Conference on Intelligent Robots and Systems, going on this week in Germany.
Watch the entire MIT demonstration video here: