Human-Like Vision for Pick-and-Place Robotics

Achieving full SKU coverage and fewer mispicks, and completely emptying a bin of random objects, are success factors that may be hard to achieve if an automation system is based on stereo depth sensors that are low-end or slow. Sharma provides several before-and-after examples, as well as the structured light path for improving the rates of success for detecting, picking, and placing most objects in manufacturing and logistics. Inspired by the mantra "See more. Do more," he covers colored, reflective, shiny, small, and large parts to demonstrate how AI and detection algorithms and a robotic piece-picking system can use human-like vision to finally achieve the goal of universal picking and placing. Additionally, Sharma will discuss positioning 3D sensors at the right angle maximize your field of view.

About the presenter
Raman Sharma is responsible for sales and marketing for at Zivid in the Americas. He is passionate about technology and building businesses from the ground up. Zivid is his third start-up in his 20-year career. Sharma holds bachelor's and master's degrees in electrical and computer engineering from Carnegie Mellon University and an MBA from the Kellogg School of Management at Northwestern University.