- Computer Science - Jul 21 Imaging software predicts how you look with different hair styles, colors, appearances
- Medicine - Jul 21 Hearing what the community has to say about e-health
- Physics - Jul 20 New Yale- developed device lengthens the life of quantum information
- Life Sciences - Jul 19 UW professor is digitizing every fish species in the world
- Mathematics - Jul 18 Computational Design Tool Transforms Flat Materials Into 3-D Shapes
- Physics - Jul 18 A Playful Approach to Quantum Computing
- Life Sciences - Jul 13 Exploring networks efficiently
- Life Sciences - Jul 11 Giving animals a voice - computer software that could tell us what they are thinking
- Computer Science - Jul 11 How to stay anonymous online
- Computer Science - Jul 11 Ethical Questions Must Be Asked About Use of Police Robot
- Computer Science - Jul 8 Solar Superstorms? invited to show at SIGGRAPH 2016
- Medicine - Jul 8 Phone calls can forecast dengue fever outbreaks
- Computer Science - Jul 8 Democratizing databases
- Computer Science - Jul 5 Major energy savings when computers learn to share »
- Computer Science - Jul 4 Technologist No. 9: High- Tech for everyone - The Sports Revolution
- Earth Sciences - Jul 1 Fingerprinting rare earth elements from the air
Robots learn to pick up oddly shaped objects
When Cornell engineers developed a new type of robot hand that could pick up oddly shaped objects it presented a challenge: It was easy for a human operator to choose the best place to take hold of an object, but an autonomous robot, like the ones we may someday have helping around the home or office, would need a new kind of programming. So they have developed a procedure -- an algorithm -- that allows a robot to learn grasping skills from experience and apply them in new situations.
Although inspired by the "universal jamming gripper" created in the lab of Hod Lipson, associate professor of mechanical engineering and computer science, the new method is "hardware agnostic," the researchers said, and will work with any type of robot gripper.
The work by Lipson and Ashutosh Saxena, assistant professor of computer science, a specialist in "machine learning," will be presented May 16 at the International Conference on Robotics and Automation in St. Paul, Minn. Co-authors of their paper are graduate students Yun Jiang and John Amend.
Lipson’s gripper consists of a flexible bag filled with a granular material. As the bag settles on an object it deforms to fit, then air is sucked out of the bag, causing the granules to pull together and tighten the grip. Previous grasping algorithms have been based on 3-D models of the object and the robot’s gripping mechanism. A robot’s computer brain creates an image of how its hand will look when attached to, say, a cup handle or pencil, and computes the motions needed to arrive in that position. But modeling how a deformable bag shapes around irregular objects is too hard to compute, so the researchers adopted a learning approach.
In a 3-D image of the object, the robot examines a series of rectangles that match the size of the gripper and tests each one on a variety of features. The robot is trained on images of many different objects until it has built a library of features common to good grasping rectangles. Presented with a new object, it chooses the rectangle with the highest score based on the rules it has discovered. For example, if a rectangle is divided into three strips and the center strip is higher than the other two, that might be a good place to grab.
The robot also considers the overall size and shape of the object to choose a stable grasping point. You don’t want to pick up a heavy, irregular object by one end; but arbitrarily choosing the center may not work either. The "center" of a computer mouse is halfway along the cord.
To test the method the researchers fitted an industrial robot arm with the jamming gripper and a Microsoft Kinect 3-D camera. In trying to pick up 23 objects, including tools, toys and dishes, the robot succeeded an average of 90 percent to 100 percent of the time, depending on the type of object. In most cases, the robot was able to successfully grasp new objects that had not been in the training set. Deformable objects like a shoe or a purse were harder, with the robot averaging only 67 percent success.
They ran the same tests with a simple "pick it up at the center" directive, scoring only 30 percent to 50 percent, except on flat objects, where both approaches tied at 89 percent.
The algorithm also was tested with the standard parallel jaws most modern robots use, with about the same results, except that the jaws were 100 percent successful in picking up soft, deformable objects. A future robot may need interchangeable hands for different jobs. An extension of their work, the researchers said, might be to include a gripper selection feature.
Last job offers
- Computer Science/Telecom - 20.7
Forschungsdozentin / Forschungsdozent mit Schwerpunkt IT Security
- Microtechnics - 15.7
- Computer Science/Telecom - 14.7
Wissensch. Assistent/in Programmierung
- Computer Science/Telecom - 5.7
Doktoranden / Doktorandin im Fachbereich Data Intelligence (70%)
- Physics/Materials Science - 28.6
Material Scientist - Post-Doctoral position for 2 years
- Physics/Materials Science - 21.6
Faculty Position in Photonics
- Life Sciences - 22.7
Asst./Assoc. Professor of Bioinformatics for Human Diseases
- Computer Science/Telecom - 13.7
Professor of Emerging Dependable Computing Technologies
- Computer Science/Telecom - 19.7
§ 98 Professur
- Computer Science/Telecom - 27.8
Professur für Praktische Informatik, mit Schwerpunkt Computational Life Science
- Computer Science/Telecom - 21.7
The Faculty of Engineering at the University of Duisburg-Essen, Department of Computer Science and Applied...
- Medicine/Pharmacology - 21.7
Professorship in Perioperative Medical Informatics an Technology
- Computer Science/Telecom - 16.7
Transitional Assistant Professor in Computer Science (2 posts)
- Computer Science/Telecom - 15.7
Lecturer (Assistant Professor) / Senior Lecturer / Reader (Associate Professor) in Machine Learning
- Microtechnics - 12.2
- Microtechnics - 16.12