The Fracturing of E-Commerce Robotics Strategies


Visual Inspection

Autonomous automation: Mobile robot system HelMo at Electrical Connectors

Also, Ansys delivered the Simulation World 2021 opening keynote.

Acoustic Monitoring

Assembly Line

Multi-Task Robotic Reinforcement Learning at Scale

πŸ“… Date:

✍️ Authors: Karol Hausman, Yevgen Chebotar

πŸ”– Topics: reinforcement learning, robotics, AI, machine learning

🏒 Organizations: Google

For general-purpose robots to be most useful, they would need to be able to perform a range of tasks, such as cleaning, maintenance and delivery. But training even a single task (e.g., grasping) using offline reinforcement learning (RL), a trial and error learning method where the agent uses training previously collected data, can take thousands of robot-hours, in addition to the significant engineering needed to enable autonomous operation of a large-scale robotic system. Thus, the computational costs of building general-purpose everyday robots using current robot learning methods becomes prohibitive as the number of tasks grows.

Read more at Google AI Blog

How Robotic Automation Impacts E-Commerce

πŸ“… Date:

✍️ Author: Robert McElmurry

πŸ”– Topics: E-commerce, robotics

🏒 Organizations: Fanuc

AI and machine learning technologies are enabling new applications. In fact, most of the applications in ecommerce/fulfillment require some type of machine vision. However, with the huge proliferation of SKUs, the old way of programming for a particular part or object discretely is much more difficult to figure out what item to pick next. AI and machine learning will provide more opportunities for companies to expand their capabilities and help ease the burden of dealing with high levels of product variability.

Read more at Fanuc America

A digital twin solved the risks associated with the 50m smart patching line made by Raute

πŸ“… Date:

✍️ Author: Ville Paso

πŸ”– Topics: digital twin, machine design

🏭 Vertical: Wood

🏒 Organizations: Siemens, Raute

The project consists of a digital twin and virtual commissioning of the production line to secure the project delivery for the new designed machine sections (material infeed and baseplate removal) of a patching line. Different scenarios could be created with the digital twin to optimize the design (i.e. avoidance of mechanical collisions etc.) and validate the concept before manufacturing the real machine sections.

Read more at Siemens Ingenuity

Walmart Is Pulling Plug on More Robots

πŸ“… Date:

✍️ Author: Sarah Nassauer

πŸ”– Topics: robotics, BOPIS

🏒 Organizations: Walmart, Bossa Nova Robotics, Cleveron

The retailer is phasing out the hulking automated pickup towers that were erected in more than 1,500 stores to dispense online orders. The decision reflects a growing focus on curbside pickup services that have become more popular during the Covid-19 pandemic and continues a broader retreat from some initiatives to use highly visible automation in stores.

Read more at Wall Street Journal (Paid)

How Amazon's Middle Mile team helps packages make the journey to your doorstep

πŸ“… Date:

πŸ”– Topics: E-commerce, operations research

🏒 Organizations: Fanuc

β€œTo give you an idea of the scale and complexity we’re managing, our trucking network alone presents us with over 1088 β€” or ten octovigintillion β€” possible routing solutions,” says Tim Jacobs, director of Middle Mile Research Science and Optimization. β€œThis is an especially large number, when you consider that there are 1082 atoms in the visible universe.”

And that’s just for the trucking network.

When a product is ordered on the Amazon Store, there are several ways it can make its way from a fulfillment center to the customer’s residence.

Read more at Amazon Science

Surge Demand

There aren’t many machines synonymous with a family name, but Zamboni is one of them. The US is still competitive with China in critical future industries like solar photovoltaic panel manufacturing. Reinforcement learning learns to evolve.