HOME  |  NEWS  |  BLOGS  |  MESSAGES  |  FEATURES  |  VIDEOS  |  WEBINARS  |  INDUSTRIES  |  FOCUS ON FUNDAMENTALS
  |  REGISTER  |  LOGIN  |  HELP
Blogs
Blog
Robots Learn to Pick Up Oddly-Shaped Objects
5/29/2012

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)
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)

Return to Article

View Comments: Oldest First|Newest First|Threaded View
Page 1/3  >  >>
naperlou
User Rank
Blogger
Like humans do
naperlou   5/29/2012 9:39:16 AM
NO RATINGS
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.

GlennA
User Rank
Gold
Manipulators
GlennA   5/29/2012 10:01:07 AM
NO RATINGS
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.

Ann R. Thryft
User Rank
Blogger
Re: Like humans do
Ann R. Thryft   5/29/2012 11:48:57 AM
NO RATINGS
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.

Ann R. Thryft
User Rank
Blogger
Re: Manipulators
Ann R. Thryft   5/29/2012 11:50:15 AM
NO RATINGS
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.

GlennA
User Rank
Gold
Re: Manipulators
GlennA   5/29/2012 12:37:33 PM
NO RATINGS
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.

Rob Spiegel
User Rank
Blogger
Re: Manipulators
Rob Spiegel   5/29/2012 1:17:30 PM
NO RATINGS
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. 

Ann R. Thryft
User Rank
Blogger
Re: Manipulators
Ann R. Thryft   5/29/2012 3:15:57 PM
NO RATINGS
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.

GlennA
User Rank
Gold
A Solution looking for a Problem
GlennA   5/29/2012 4:12:07 PM
NO RATINGS
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.

jmiller
User Rank
Platinum
Re: Manipulators
jmiller   5/29/2012 8:06:29 PM
NO RATINGS
I like the ability of the robot to adapt and learn according to it's memory or history.  no matter what the robot or technology in the robot I just love to hear about how the SW is learning.

jmiller
User Rank
Platinum
Re: Manipulators
jmiller   5/29/2012 8:07:58 PM
NO RATINGS
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.

Page 1/3  >  >>
Partner Zone
More Blogs
MIT’s Senseable City Lab recently announced the program’s next big project: “Local Warming.” The concept involves saving on energy by heating the occupants within a room, not the room itself.
The fun factor continues to draw developers to Linux. This open-source system continues to succeed in the market and in the hearts and minds of developers. Design News will delve into this territory with next week's Continuing Education Class titled, “Introduction to Linux Device Drivers.”
The new draw-it-on-a-napkin is the CAD program. As CAD programs become more ubiquitous and easier to use, they have replaced 2D sketching for early concepting.
A University of Chicago graduate has invented a compact elliptical trainer that lets people work out at their desk while they work.
New developments in sensors span a wide range of applications in all areas of manufacturing and plant automation.
Design News Webinar Series
7/23/2014 11:00 a.m. California / 2:00 p.m. New York
7/17/2014 11:00 a.m. California / 2:00 p.m. New York
6/25/2014 11:00 a.m. California / 2:00 p.m. New York
5/13/2014 10:00 a.m. California / 1:00 p.m. New York / 6:00 p.m. London
Quick Poll
The Continuing Education Center offers engineers an entirely new way to get the education they need to formulate next-generation solutions.
Aug 4 - 8, Introduction to Linux Device Drivers
SEMESTERS: 1  |  2  |  3  |  4  |  5  |  6


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.
Next Class: August 12 - 14
Sponsored by igus
Learn More   |   Login   |   Archived Classes
Twitter Feed
Design News Twitter Feed
Like Us on Facebook

Sponsored Content

Technology Marketplace

Copyright © 2014 UBM Canon, A UBM company, All rights reserved. Privacy Policy | Terms of Service