Method allows robot to learn and apply grasping skills

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’, according to the researchers, and will work with any type of robot gripper.

The work was done by Lipson and Ashutosh Saxena, assistant professor of computer science and a specialist in machine learning. It will be presented on 16 May at the International Conference on Robotics and Automation in St Paul, Minnesota. Co-authors of their paper are graduate students Yun Jiang and John Amend.

Lipson’s gripper is said to consist of a flexible bag filled with a granular material. With the new algorithm, the robot uses a 3D image of the object to examine a series of rectangles that match the size of the gripper and tests each one on a variety of features.

According to a statement, the robot is trained on images of many different objects until it has built up 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. The robot also considers the overall size and shape of the object to choose a stable grasping point.

To test the method, researchers fitted an industrial robot arm with the jamming gripper and a Microsoft Kinect 3D camera.

In trying to pick up 23 objects, including tools, toys and dishes, the robot succeeded, on average, 90–100 per cent of the time.

In most cases, the robot was able to successfully grasp new objects that had not been in the training set.

They ran the same tests with a simple ‘pick it up at the centre’ directive, scoring only 30–50 per cent, except on flat objects, where both approaches tied at 89 per cent.

The algorithm was also tested with the standard parallel jaws that most modern robots use, achieving roughly the same results.

Click here to see the gripper in action.