Dex-Net 4.0 in TechCrunch
Dex-Net 4.0, the robot learning how to grip through neural networks from Ken Goldberg's lab, was featured in the latest TechCrunch article on the latest robots, who are evolving our understanding of robotic agility. Agility, and grasping in particular, has been an extraordinarily difficult task for robots so far. Ken Goldberg's team uses new decision making processes for the robot to quickly determine how to interact with objects.
From the website:
Berkeley’s Ken Goldberg explains:
“We can try to infer some intuition but the two networks are inscrutable in that we can’t extract understandable ‘policies,’ ” he wrote. “We empirically find that smooth planar surfaces away from edges generally score well on the suction model and pairs of antipodal points generally score well for the gripper.”
Now that reliability and versatility are high, the next step is speed; Goldberg said that the team is “working on an exciting new approach” to reduce computation time for the network, to be documented, no doubt, in a future paper."
Read more about this innovative robotic invention here!