An algorithm inspired by Cornell University's universal jamming gripper robot hand, shown here picking up a glass of water, can teach any industrial robot how to pick up unfamiliar, oddly-shaped objects. (Source: John Amend, Cornell University)
Cabe I never would have thought of that, either. Once again, this solution to a design problem seems obvious in hindsight, but unless one was spending a lot of time contemplating how to use different shapes to grasp objects, it's unlikely the idea would occur.
Agree....Most of the comments are based on environments where uniform parts are pre-aligned. Many times that's fine, but what if electronic components, gears, etc. could be "loose" and gripped and oriented by more sophisticated robotics? It could result in net savings. Another application is when the component shapes or orientation are irregular and poorly defined- logs, chicken wings, gemstones, or debris on the seabed.
Jack, that's a good point about the use case of slight changes in the expected location of the object to be picked up. The main advantage the researchers cited was in adapting to different shaped and oddly shaped objects and being able to pick them up without dropping them (or spilling water from them as shown in the photo).
Yes, Ann, the adaptation to different shapes is the key component of the algorithm. I see two practical applications for something like that. First, it gives the robot a much higher margin of error when moving a product. If the product is not quite in the right orientation or has moved somewhat from where it it expected, the gripper can still get it (within reason). The second application is if the product the robot is trying to grab gets redesigned. A minor modification to it physical shape may not require as drastic of changes to the processes if the robot is still able to adapt to it.
jmiller, you can see and hear about the inner workings of the gripper's ball--what makes it a jamming gripper--in the video linked to in the article. The fact that the robot has to follow the same repetitive steps is secondary here: it's the fact that it may have to adjust those repetitive steps to different shaped objects, as stated in the article. That's what the algorithm teaches it to adapt to.
This gripper--which is not the main subject of the DN article--is not designed to pick and place small chips or other tiny objects on a high-speed line. The universal jamming gripper is a very different gripper designed to quickly grasp and release, or throw, a wide variety of object shapes. According to a FAQ http://creativemachines.cornell.edu/jamming_faq_2 for an earlier IEEE article about this gripper by its inventors, not the algorithm which my article focused on, specific applications include "military robotics and improvised explosive device (IED) defeat missions; consumer and service robotics in unstructured environments like the home; and industrial and manufacturing robotics able to perform of a wider variety of gripping tasks than currently possible." According to that article, universal grippers can be used for sorting and throwing objects. One immediate use that comes to mind is end-of-line palletizing for non-fragile objects. A different (non-jamming) approach to universal grippers is shown here: http://blog.robotiq.com/bid/29474/Universal-Gripper-Tooling-for-Pre-Engineered-Robotic-Cells
In a line of ultra-futuristic projects, DARPA is developing a brain microchip that will help heal the bodies and minds of soldiers. A final product is far off, but preliminary chips are already being tested.
Focus on Fundamentals consists of 45-minute on-line classes that cover a host of technologies. You learn without leaving the comfort of your desk. All classes are taught by subject-matter experts and all are archived. So if you can't attend live, attend at your convenience.