Data Science

Using Machine Learning to Optimize Warehouse Operations

Dec 14, 2015
By Brad Nemire
Discuss (0)

AI-Generated Summary
  • Zalando uses GPU-accelerated deep learning to identify the shortest route possible to products in their 1.3 million-square-foot distribution center.
  • Data Scientist Calvin Seward and his team apply the Caffe deep learning framework and Tesla K80 GPUs to train a deep neural network that accelerates a processing bottleneck.
  • The acceleration enables the company to more efficiently split work between warehouse workers.

Next Step

Powered by NVIDIA Nemotron. AI-generated content may summarize information incompletely. Verify important information. Learn more

With thousands of orders placed every hour and each order assigned to a pick list, Europe’s leading online fashion retailer Zalando is using GPU-accelerated deep learning to identify the shortest route possible to products in their 1.3 million-square-foot distribution center.

warehouse_3d-624x274
Two schematics of a rope ladder warehouse zone with picks. The blue shelves denote shelves with items to be picked, so the goal is to find the shortest possible route that allows a worker to visit all blue shelves while starting and ending at the depot.

Calvin Seward, a Data Scientist focused on warehouse logistics, shares how his team is using the Caffe deep learning framework and Tesla K80 GPUs to train their deep neural network to greatly accelerate a processing bottleneck, which in turn enabled the company to more efficiently split work between workers.
Read more on Parallel Forall >>

Discuss (0)

Tags

Data Science | Robotics | Retail / Consumer Packaged Goods | News | Machine Learning & Artificial Intelligence

About the Authors

Avatar photo
About Brad Nemire
Brad Nemire leads the Developer Communications team at NVIDIA. Prior to NVIDIA, he worked at Arm on the Developer Relations team. Brad graduated from San Diego State University and currently resides in Silicon Valley.

Comments