Grabbing the awkwardly shaped items that people pick up in their day-to-day lives is a slippery task for robots. Irregularly shaped items such as shoes, spray bottles, open boxes, even rubber duckies are easy for people to grab and pick up, but robots struggle with knowing where to apply a grip. In a significant step toward overcoming this problem, roboticists at UC Berkeley have a built a robot that can pick up and move unfamiliar, real-world objects with a 99 percent success rate.
Berkeley professor Ken Goldberg, postdoctoral researcher Jeff Mahler and the Laboratory for Automation Science and Engineering (AUTOLAB) created the robot, called DexNet 2.0. DexNet 2.0’s high grasping success rate means that this technology could soon be applied in industry, with the potential to revolutionize manufacturing and the supply chain.
DexNet 2.0 gained its highly accurate dexterity through a process called deep learning. The researchers built a vast database of three-dimensional shapes — 6.7 million data points in total — that a neural network uses to learn grasps that will pick up and move objects with irregular shapes. The neural network was then connected to a 3D sensor and a robotic arm. When an object is placed in front of DexNet 2.0, it quickly studies the shape and selects a grasp that will successfully pick up and move the object 99 percent of the time. DexNet 2.0 is also three times faster than its previous version.
DexNet 2.0 was featured as the cover story of the latest issues of MIT Technology Review, which called DexNet 2.0 “the most nimble-fingered robot yet.” The complete paper will be published in July.
Learn more: Meet the most nimble-fingered robot ever built
The Latest on: Robot dexterity
Three end-of-arm robotic companies become OnRobot
on June 20, 2018 at 9:17 am
OptoForce, founded in 2012, provides force/torque sensors that bring the sense of touch to industrial robots so that they can automate tasks that would otherwise require the dexterity of the human hand. Perception Robotics, founded in 2012 and based in ... […]
Rise of the Robots
on June 20, 2018 at 4:52 am
Beyond assembly lines, public and private research organizations have made a wide variety of humanoid robots for different purposes (Honda’s running, hopping, soccer-playing Asimo being one example), but these still have limited capabilities. Dexterity ... […]
Robots and AI creating more jobs in Asia
on June 19, 2018 at 10:44 pm
"This pattern reflects both technological and economic feasibility," the report said. "More technological sophistication is required to give a robot the dexterity to stitch cloth, for example, than to handle large metal parts." At the same time, low pay in ... […]
Think you and a robot could do surgery? Try your hand at this Pasco event
on June 18, 2018 at 2:24 pm
Want to try your hand at surgery and piloting a robot at the same time ... and high-definition cameras — means better dexterity and field of vision. Lourdes has two robotics-assisted surgery systems in use — and the new advanced Xi model is the ... […]
Epson brings ‘WorkSense’ dual-armed robot to Europe
on June 18, 2018 at 5:37 am
The N6 completes Epson’s robotics offering, providing revolutionary kinematics as a compact 6-axis industrial robot with a small footprint but incredible dexterity. Epson’s corporate vision sees high revenue growth to 2025, with a substantial portion ... […]
via Google News and Bing News