New Ken Goldberg Dex-Net Video Online
Professor Ken Goldberg unveiled Dex-Net 4.0 at the EmTech Digital Conference hosted by the MIT Technology Review, demonstrating the improved dexterity in which his robot could handle and recognize complex shapes and materials.
At its current stage, the Dex-Net robotic system can pick up around 270 items per hour. Through its 3D camera and previous experience picking up similar objects, Dex-Net 4.0 can pick up items it has never seen before and assess the best point of contact through deep learning.
MIT Technology Review called this system "the most dexterous robot ever created." According to the rest of the article:
Goldberg’s system is a lot closer to matching the adroitness of a human than anything developed previously. Industrial robots with better dexterity could find application in warehouses and factories as well as hospitals and homes.
What’s especially clever about Dex-Net is how it learns to grasp. The software tries picking up objects in a virtual environment, training a deep neural network through trial and error. Even in simulation, this is a laborious task. Crucially, though, Dex-Net can generalize from an object it has seen before to a new one. The robot will even nudge an item to get a better look at it if it isn’t sure how it should be grasped. The latest version of the system includes a high-resolution 3-D sensor and two arms, each controlled by a different neural network. One arm is equipped with a conventional robot gripper and another with a suction system. The robot’s software scans an object and then looks at both neural networks to decide, on the fly, whether it makes more sense to grab or suck that particular object.
Read more about Dex-Net in articles written by Mashable, Internet of Business, and Interesting Engineering.