From green blobs to hydrogel fish to boa constrictors, scientists have taken inspiration from some interesting sources in pursuit of robotic arms that can lift heavy items, but do so with a delicate touch. The latest solution from MIT resembles a Venus flytrap in the way it snatches up objects many times its own weight, and its creators hope it can open up some exciting possibilities for robotic assistants that can handle all kinds of objects.

Though the end product behaves in a similar way to a Venus fly trap, the MIT team's new robotic gripper is actually inspired by the Origami Magic Ball, an intricately folded paper sphere with a light weight and plenty of pliability.

As such, the so-called Magic Ball gripper consists of a skeleton made from a cone-shaped origami structure that is connected to a vacuum device and wrapped in an airtight skin, which is made from either a rubber balloon or thin fabric sheet. As the inverted cone is placed over an object, the vacuum causes the skin to contract and fold up, snaffling its target in its grasp.

The team hooked the gripper up to a standard robotic arm and put it to work with a range of objects including soft foods, bottles, soup cans, hammers and even broccoli. The team found it could pickup these different shapes and sizes, and lift items as much as 100 times its own weight and with up to 70 percent of its diameter.

"Previous approaches to the packing problem could only handle very limited classes of objects – objects that are very light or objects that conform to shapes such as boxes and cylinders, but with the Magic Ball gripper system we've shown that we can do pick-and-place tasks for a large variety of items ranging from wine bottles to broccoli, grapes and eggs," says MIT professor Daniela Rus, director of MIT's Computer Science and Artificial Intelligence Laboratory. "In other words, objects that are heavy and objects that are light. Objects that are delicate, or sturdy, or that have regular or free form shapes."

What the Magic Ball gripper is not so good at, as you might expect given its shape, is grasping flat objects like a book or a sandwich. And like other soft grippers of a similar form it struggles to grab onto things at different angles. The scientists hope to address this by equipping it with computer vision so it can see its target and grab onto specific parts.

"One of my moonshots is to create a robot that can automatically pack groceries for you," says Rus.

A paper describing the technology has been published online, and you can see the robot do its thing in the video below.

Source: MIT

View gallery - 2 images