Algorithm That Improves A Robot's Grasping Skills
Now get ready for a robot whose experience on earlier situations shall guide it on what to do in new situations. Cornell Researchers have come up with a new algorithm which, in their own words, lets the robot acquire skills from its past experience.
#-Link-Snipped-#
source: publications.csail.mit.edu
Lipson’s gripper comprises a flexible bag loaded with granular material. Employing the new algorithm, the robot gets a 3D image of the object to analyze a series of rectangles that complement the size of the gripper and examines every rectangle individually for several features. When the robot encounters a new object, it selects the rectangle having the highest score as per the rules found. The shape and size of the object plays a key role for the robot to get a stable grasping point.
The test involved connecting a Microsoft Kinect 3D camera and a jamming gripper to the robot arm. Attempting to pick up 23 objects, the robot's success rate over 90%.
#-Link-Snipped-#
source: publications.csail.mit.edu
Hod Lipson, associate professor of mechanical engineering and computer science, along with Ashutosh Saxena, assistant professor of computer science and a specialist in machine learning, developed the "hardware agnostic", and they claim that it'll function on any kind of robot gripper. They took inspiration from the "universal jamming gripper", and their paper is slated for presentation at the International Conference on Robotics and Automation in St Paul, Minnesota, coming 16th May. Yun Jiang and John Amend have co-authored this paper.
Lipson’s gripper comprises a flexible bag loaded with granular material. Employing the new algorithm, the robot gets a 3D image of the object to analyze a series of rectangles that complement the size of the gripper and examines every rectangle individually for several features. When the robot encounters a new object, it selects the rectangle having the highest score as per the rules found. The shape and size of the object plays a key role for the robot to get a stable grasping point.
The test involved connecting a Microsoft Kinect 3D camera and a jamming gripper to the robot arm. Attempting to pick up 23 objects, the robot's success rate over 90%.
Replies
You are reading an archived discussion.
Related Posts
For those of us who love their pets, here's a good news. Fujitsu is showcasing a new service at the Fujitsu Forum 2012 that monitors your pet dog's activity levels...
Seraku Android Mirror will remind you of the Samsung Smart Window that we saw during CES 2012. Getting from the window in to the mirror, Seraku Corp. Japan have now...
Be done with your computer games, and hop on to the intelligent gaming platform, is what the Technopark IT firm Schogini Systems asking you to do. If you are one...
Of the many bright ideas that aim to revive our drooping space attempts, one Systems and Electrical engineer's idea stands out. His aim is to develop the StarshipEnterprise till 2032. ...
Dassault Systems (3DS) today announced the launch of SolidWorks Education Edition 2012-2013. The global leader in 3D design software also announced the availability of comprehensive SolidWorks curriculum library, comprising of...