Amazon’s Robotic Warehouses as a Many Robot System
Every day, Amazon is able to quickly pick, pack, and ship millions of items to customers from a network of fulfilment centres all over the globe. Each Amazon warehouse holds millions of items of inventory, most customer orders represent a unique combination of several items, and many orders need to be shipped within a couple hours of being placed to meet delivery promises. This would not be possible without leveraging cutting-edge advances in technology. This talk will describe the mobile robotic fleet that powers an Amazon warehouse and delivers inventory shelves to associates, including how we approach the interrelated problems of assigning tasks and planning paths for thousands of robots in dynamic warehouse environments. I will also discuss the Amazon Robotics Challenge in manipulation and grasping, as well as a couple of big open problems in robotic warehousing.
Jeremy L Wyatt is Senior Manager Applied Science at Amazon, Robotics AI. His team focuses on using robotics, machine learning, and artificial intelligence to improve processes in Amazon’s fulfilment centres. Jeremy joined Amazon after being Professor of Robotics and Artificial Intelligence at the University of Birmingham. He has published more than 100 scientific articles on robot manipulation, robot task planning, machine learning, machine vision and probabilistic AI.
Organisation - Imperial College London
Contact Name -
I agree to the website Terms & Conditions - No