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)
Ann, this might mark me out as a bit wierd, but I think about this a lot. Whenever I put the silverware away I thnk to myself, how would I program a robot to do this?
What really strikes me about this, and some other situations I have seen, is that people are programming robots to do things using a fairly simple vision system along with memory (a database) and an algorithm. This contrasts with robotics approaches that use all kinds of complex sensors. In many cases they are trying to automate something we do with our simple sensors naturally. Interesting.
naperlou, not everyone thinks about how a robot would do things they themselves are doing. But that does sound like how engineers think. Thanks for the observation about the lack of sensors here--I think that's a good point, and it's interesting to know this isn't the only research team taking that approach.
Picking up an object is only part of the problem. The picture shows a gripper spilling a glass of water. After the object is grasped, some purpose must be accomplished. If the water were wine and needed to go from a pitcher into a glass, it would be inportant not to spill it onto the floor or table, and that the robot's 'fingers' not get into the wine. While this is an interesting line of research, I can't see it replacing purpose-built grippers yet.
Glenn, thanks for that observation about the photo. I should have pointed out in the caption that this universal gripper, without the algorithm, can pick up objects but that this shows how it does so in a non-optimal manner, forming a "before" picture.
Ann R Thryft; Yes, optimal vs. non-optimal is the clarification. For some applications the optimal gripper is vacuum cup(s). The human hand is a very versatile end effector. Duplicating it is not easy. There could be applications where this gripper would be optimal, but I don't think the water glass is one of them.
Right now this looks like a technology development seeking a solution. As the robots develop, solutions will appear. I've seen this notion of robots learning how to do things by trial and error. That's impressive.
The point here is that, with a less expensive universal gripper, such as Cornell's, plus the algorithm the team invented, a robotic assembly line can quickly adapt to optimally picking up all kinds of new objects with different sizes and shapes that it's never encountered before. The alternative, which we've heard a lot about in DN articles and comments, is lengthy and expensive programming in 4D, presumably with highly specialized grippers. This would be a big benefit in assembly lines, especially those of EMS, which are continually changing products.
I have had a bit of experience with assembly lines. I can't think of any application for this gripper. Printed circuit board assembly needs very fast small part placement with vision compensation, or fast very fine placement of large parts with many leads, using vision compensation. I have only seen vacuum nozzles used. I can't see this gripper being used in a high-speed vision application. In automotive speed, accuracy, and payload are important. I don't think this gripper has any of these 3. Even where I have seen off-line programming using 3-D modeling, an actual human had to step through the program to touch-up positions and movements. Robots, aka Flexible Automation, vs. 'hard automation', was the answer to changing products. The gripper or 'end effector' is always customized to the application. The part must be both 'picked' and 'placed'.
To belabor the point: I don't think this gripper could pick up a 1mm x 2mm chip, take a vision shot, and then place it into a solder screened location, and do it again 1/10 second later. I also doubt that it could pick up a 50 lb bag of flour and place it to a pallet.
The gripper and the algorithm are interesting research, without a current practical application.
I agree I don''t know that I see an application for an adaptable gripper. But I do believe the ability of robots to pick up parts and hold them in place perhaps to be welded by another robot would be an application where this would be helpful. But on the typical assembly line the job is going to be repetitive and follow the same steps again and again without having to adapt.
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.
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.
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).
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.
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.
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
I really liked the article. I don't know if I completely understand the inner workings of the pressure adaping inside of the big blue ball, but the statistics of success for picking up parts is pretty cool.
This technology seems to allow for a certain amount of forgiveness in the pick location for larger objects. It would be great to have a cell that can easily adjust to different parts as they come down the assembly line. This would allow for touchup free product changes. That would be great.
One of the biggest walls in embedded software development is the integration of low-level drivers with higher-level middleware and application code, but silicon vendors are stepping up to bring it down.
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.