Robots Like Pizza Too

Date:

A Starship Technologies robot food delivers pizza at George Mason University. Credit: Bill Nino A Starship Technologies robot food delivers pizza at George Mason University. Credit: Bill Nino

It’s no secret that pizza is among the world’s favorite foods, but you would be surprised at the amount of leading edge technology being applied to the pizza value chain. Starting with the ingredients, tomatoes require significant energy from both direct and indirect sources to grow and can be harvested through flying robots. When the ingredients are combined in a food production facility artificial intelligence is used to put an end to salami squabbles. In the last mile, one of the initial use cases for self-driving cars is pizza delivery. Ultimately, novel technology often shows up first in the most obvious places, we just have to look.

Visual Inspection

AI Robotics for the Real World

Acoustic Monitoring

If you enjoyed my posts on shipping containers and industrial third-party APIs, then you’ll also enjoy this conversation with Ryan Peterson, founder and CEO of Flexport:

Assembly Line

Way beyond AlphaZero: Berkeley and Google work shows robotics may be the deepest machine learning of all

Date:

Author: @TiernanRayTech

Topics: AI, machine learning, robotics, reinforcement learning

Organizations: Google

With no well-specified rewards and state transitions that take place in a myriad of ways, training a robot via reinforcement learning represents perhaps the most complex arena for machine learning.

Read more at ZDNet

Leveraging AI and Statistical Methods to Improve Flame Spray Pyrolysis

Date:

Author: Stephen J. Mraz

Topics: AI, machine learning, materials science

Vertical: Chemical

Organizations: Argonne National Laboratory

Flame spray pyrolysis has long been used to make small particles that can be used as paint pigments. Now, researchers at Argonne National Laboratory are refining the process to make smaller, nano-sized particles of various materials that can make nano-powders for low-cobalt battery cathodes, solid state electrolytes and platinum/titanium dioxide catalysts for turning biomass into fuel.

Read more at Machine Design

Introducing Amazon SageMaker Reinforcement Learning Components for open-source Kubeflow pipelines

Date:

Authors: Alex Chung, Kyle Saltmarsh, Leonard O'Sullivan, Matthew Rose, Nicholas Therkelsen-Terry, Nicholas Thomson, Ragha Prasad, Sahika Genc,

Topics: AI, machine learning, robotics

Organizations: AWS, Max Kelsen, Universal Robots, Woodside Energy

Woodside Energy uses AWS RoboMaker with Amazon SageMaker Kubeflow operators to train, tune, and deploy reinforcement learning agents to their robots to perform manipulation tasks that are repetitive or dangerous.

Read more at AWS Blog

Using AI to Find Essential Battery Materials

Date:

Author: @mariagallucci

Topics: AI, materials science

Vertical: Mining

Organizations: KoBold Metals, IBM, IEEE

KoBold’s AI-driven approach begins with its data platform, which stores all available forms of information about a particular area, including soil samples, satellite-based hyperspectral imaging, and century-old handwritten drilling reports. The company then applies machine learning methods to make predictions about the location of compositional anomalies—that is, unusually high concentrations of ore bodies in the Earth’s subsurface.

Read more at IEEE Spectrum

Evolutionary Algorithms: How Natural Selection Beats Human Design

Date:

Author: @OzdDerya

Topics: AI, generative design

Vertical: Aerospace

Organizations: NASA

An evolutionary algorithm, which is a subset of evolutionary computation, can be defined as a “population-based metaheuristic optimization algorithm.” These nature-inspired algorithms evolve populations of experimental solutions through numerous generations by using the basic principles of evolutionary biology such as reproduction, mutation, recombination, and selection.

Read more at Interesting Engineering

Surge Demand

Condition-based maintenance (CBM) language can be tough to decipher especially when overlaying an Industry 4.0 mindset. Signal propagation timings are a core challenge of AI hardware. The Constrained Application Protocol (CoAP) helps balance network bandwidth for large amounts of IoT devices. Actuator technology progresses with inspiration from jellyfish.