Robotic grippers typically used today in industrial applications tend to be rigid and can only work in structured environments without any intuitive capability. This scenario soon may change with the development of a soft yet exceptionally strong soft-gripper robot by researchers at MIT and Harvard University that can pick up items as much as 100 times its weight.
The robot—a collaboration between MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) and Harvard’s John A. Paulson School of Engineering and Applied Sciences—is an origami-inspired cone-shaped structure that collapses in on objects, similarly to how a Venus flytrap plant traps its prey.
|A new soft, origami-inspired robotic gripper from researchers at Harvard University and MIT can lift a wide range of objects, from apples and soup cans to wine glasses and drones. (Image source: Jason Dorfman/MIT Computer Science and Artificial Intelligence Laboratory)|
Current rubber robotic grippers exist that are soft and flexible, allowing them to pick up items such as grapes, boxes, and even empty water bottles. However, they are typically limited to picking up objects without much weight.
The new gripper is less limited, with the ability to grasp and pick up a large array of objects, including soup cans, hammers, wine glasses, drones, and something as small and delicate as a single piece of broccoli, said MIT Professor Daniela Rus, director of CSAIL.
“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,” she said. “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. 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.”
Indeed, the new robotic gripper sets a different bar for what these type of machines can do, and researchers at MIT and CSAIL are at the forefront of this type of research. In fact, Rus said she one day hopes to create “a robot that can automatically pack groceries for you,” she said.
The Power of Origami
Researchers used a different form for the shape of the robot than has been previously used in gripper designs, inspired by what’s called an “origami magic ball,” a design in the Japanese paper-folding art. This shape—which is cone-shaped, hollow, and vacuum-powered—allows the device to envelop an entire object and successfully pick it up, researchers said.
There are three parts to the robotic gripper—the origami-based skeleton structure, the airtight skin to encase the structure, and the connector. To create these parts, researchers used a mechanical rubber mold and a special heat-shrinking plastic that self-folds at high temperatures.
To test the strength of the gripper on different objects, researchers paired it with a standard robot. They found that the gripper could grasp and lift objects 70 percent of its diameter, which allowed it to pick up and hold a variety of soft foods without causing damage. It could also pick up bottles weighing over four pounds.
Shuguang Li, a joint postdoc at CSAIL and Harvard’s John A. Paulson School of Engineering and Applied Sciences, said its performance would make it attractive to shipping companies such as Amazon that need this type of automation in their warehouses to pick up “delicate or irregular-shaped objects.” This currently can’t be done with finger-based and suction-cup grippers, he said.
“Suction cups can’t pick up anything with holes--and they’d need something much stronger than a soft-finger-based gripper,” Li said.
Currently, the origami-inspired gripper works best with cylindrical objects like bottles or cans, which also means it could be well-suited for use in production lines in factories. However, it does have its limitations; for instance, it would be challenging for the gripper to pick up something flat, like a sandwich or a book, researchers said.
The team plans to continue its work to solve some problems the gripper currently has with angle and orientation by adding computer vision, which they said would let the gripper “see” as well as make it possible to grasp specific parts of objects, researchers said.
Elizabeth Montalbano is a freelance writer who has written about technology and culture for more than 20 years. She has lived and worked as a professional journalist in Phoenix, San Francisco and New York City. In her free time she enjoys surfing, traveling, music, yoga and cooking. She currently resides in a village on the southwest coast of Portugal.
The nation's largest embedded systems conference is back with a new education program tailored to the needs of today's embedded systems professionals, connecting you to hundreds of software developers, hardware engineers, start-up visionaries, and industry pros across the space. Be inspired through hands-on training and education across five conference tracks. Plus, take part in technical tutorials delivered by top embedded systems professionals. Click here to register today!