Viewing posts categorised under: Neocortex

Complex Dynamical Systems

3D Vision Guidance, Artificial Intelligence, Cybernetics, Machine Learning, Neocortex, Robot Vision Guidance, Robotics / 15.06.20200 comments

Universal Logic’s years as practitioners, implementing state-of-art automation, has given us deep insight into the interplay between invention and utility.  We have engaged with a spectrum of clients from technocrats to novices, on a range of industrial applications.  Through it all, one thing remains clear.  Success in deploying a complex, multi-technology solution – blending vision, AI and motion control, resides in the close interplay and analysis between these disparate engineering domains.  As magnificent as robots, sensors and algorithms are individually, it is their combination in service to an application that allows cutting edge automation to handle real-time dynamic variability. 

Our full-stack software, Neocortex, is comprised of DeepEye (AI), Autonomy (path planning and obstacle avoidance), and Spatial Vision (middleware).  It is machine agnostic.  The software provides a closed-loop, behavior-based system of sense/act/learn and represents a profound expansion of manufacturing execution systems (MES) in an area of Industry 4.0 know as IoRT (Internet of Robotics Things).  Neocortex is embodied, that is, physically in the world, controlling movement through space, and learning from that action.  This is a paradigm shift in the way to think about software.  Intelligence emerges because it has a physical form.  The software/hardware union and the environment constitute two halves of a complex dynamical system. Neocortex senses the environment and reacts, changing the environment which updates the sensing and behavior.  They are a closed loop.

Software structures easily allow for highly layered communications and decision making processes.  As exposure to new variables increases over time, a rich set of exception handling protocols develop in Neocortex.  The data base of retained and applied learning are brought to bear with every installation.  There is a direct corollary between robust behavior and the layers of decision making options the software evaluates in milliseconds before executing an action.  

The embodied character of Neocortex is reflected in Universal’s IOT profile, in that we are both a software developer and a system integrator.  This is a great strength.  Our intimate experience coupling the software and hardware, provides the real-world feedback necessary to perfect the craftmanship of Neocortex.  We also team with other integrators, who benefit from  our advice and sympathy as fellow integrators.   

Our time on the line has given us the humility to know where the state-of-art actually is.  Give us a call to discuss your application.  We are very generous with our knowledge.

Read More >>

How to Deploy Affordable Automation in Uncertain Times

Artificial Intelligence, eCommerce, Neocortex, Robotic Case Palletizing, Robotic Order Fulfillment, Robotics, Robotics Business / 05.05.20200 comments

Teaming Man & Machine for a more resilient supply chain

Let’s talk about light-duty, semi-skilled labor for a minute.  Today these jobs are mission critical for supply chains to function.  Fully-burdened at $40K a year, the employee works 7.5 hours a day.  The employer has significant onboarding costs.  Productivity fluctuates throughout the day.  When hiring, the candidate has to pass a drug test, speak English, be able to read, and pass a background check.

There are plenty of dedicated hard workers, but any employer tasked with filling these positions,  knows the truth.  Finding quality is tough, there are thousands of unfilled supply jobs, even in today’s pandemic world with masses looking for work.  Make no mistake,  ambitious and talented people taking a light-duty semi-skilled job are doing so while looking for other work.  The workforce revolving door keeps spinning, and employers are faced with rising costs to maintain productivity while promoting  stability in the employee ranks.

We all know the painful stories of employers struggling to fill, then train, then retain an employee.  One employer I know had to seriously weigh if the murder conviction was premeditated, or accidental in order to make their hiring decision! 

There is a solution.  It involves enabling  current employees to be more efficient by expanding automation in ways not possible until now.   Today robots that sense their environment with an AI “brain” to extract inference from their perception are capable of duplicating the real-time flexible decision making of semi-skilled labor.  They do so retaining the prized qualities that put labor on the supply chain in the first place, but with none of the disappointing troubles.  We call it, robot loyalty – the ultimate company man/woman.

Couple this “smart” robot with a human supervisor, and you now have one person doing work that before required many. 

Let me make a comment about the idea that robots are taking jobs.  The fact is, yes labor will be offset by increasing automation.  But the reason my post started with the lousy state of these jobs, is because they are undesirable.   By turning them over to the robot,  the employee who remains now has an interesting job, and together they drive lower costs and increased efficiency.  The skills they need to manage the machine will lead to a pay raise because the employer want to retain their advanced skills. 

So what happens to the offset labor?  Here’s the truth: We have an opportunity in this country to finally begin bringing manufacturing back to the United States, closer to the consumer.  The economics that drove it overseas,  have run headlong into the fragility of the long supply chain. If we actually made most of what we need right here at home, our ability to support our customers would have made our current circumstance more timely and manageable.  Apple’s chain was broken within days of the outbreak.  Imagine if they made their phones here.  I, for one, would love to buy a television stamped “Made in America”.  We invented the technology and not a single TV is made here anymore.  It’s time to change that.  And robots are the way.

At Universal we’ve been selling the “brains” for robots (or any actuated machine) for over ten years. Our product is used to simulate the semi-skilled work by giving the robot the ability to handle high variability at high speed.  And I can tell you with absolute certainty,  that making America great again, means we need to shorten our supply chains, and bring the production home.  And the way we do it is by driving worker efficiency through the roof.

Okay, so with all the uncertainty in the market,  outlaying capital for equipment right now is simply not possible.  I understand that.  But, I can tell you Amazon is gaining market share because they have been building a harden supply chain for years ,that is now showing its strength.  Waiting will erode your market share even more.  We can help you, and here’s how.

Rather than fund the purchase as a capital expense, with significant cash outlays before realizing the value,  Universal offers off-book leasing.  This technique allows you to order the solution and not pay a dime before implementation.  Then you pay monthly, as an operating expense, out of the labor savings.  You are saving money the day the system goes live, hardening your supply chain, and driving up worker efficiency. 

Call or email us to discuss your automation/labor saving needs.  Together, we will win the day! 

Read More >>

If I Only Had a Brain

3D Vision Guidance, Artificial Intelligence, Cybernetics, Machine Learning, Neocortex, Robot Vision Guidance, Robotics / 25.02.20200 comments

If your robots could text you, it’s first message would read: “If I only Had a Brain”

Neocortex Leads the industry with a software “Brain” that gives robots human-like flexibility at high speed.

As Ray Bolger rightly exclaimed in the Wizard of Oz in 1939 “I could think of things I’d never Thunk before, And then I’d sit down and think some more.”  Welcome to Industry 4.0 and the world of smart robots. Over the last few years, advances in the coupling of AI, 3D vision, and robot control, have spawned the expansion of machines replacing or working closely with laborers, manifesting all the benefits of automation to new horizons.

Universal spent a decade advancing it’s robot software brain, Neocortex.  Today the technology is integrated across the supply chain from handling retail products to manufacturing, allowing our customers to reap the benefits of lower operating cost, improved reliability,  and mitigation of risk.  The product is achieved 6 Sigma reliability with picking speeds up to 1800 cycles per hour, tripling typical manual output.

Upgrade or Retrofit your current robots to Smart Robots and achieve both increased adaptability and productivity out of your Robots!

Read a fascinating article Dumb Robots vs. Smart Robots  “If we want machines to think, we need to teach them to see” Fei-Fei Le, Chief Scientist Google, AI/Machine Learning.

From Bloomberg News: Make Dumb Industrial Robots Smart

Read More >>

Fulfilling the Vision of AI-Driven Automation

3D Vision Guidance, Artificial Intelligence, Machine Learning, Neocortex, Neocortex G2R Cell, Random Bin Picking, Robotic Order Fulfillment, Robotics / 30.11.20172 comments

Sarah Mellish of Yaskawa Motoman Robotics explains the role of artificial intelligence for robotic order fulfillment:

“Technical innovations in artificial intelligence and robotics have unlocked massive potential for retailers to automate the handling of diverse Stock Keeping Units (SKUs) in the order fulfillment process with human-like flexibility at high speed….”

View Yaskawa Motoman blog here.

Read More >>

Neocortex AI links cyber and physical systems for Industry 4.0

Artificial Intelligence, eCommerce, Machine Learning, Neocortex, Neocortex G2R Cell, Robotic Order Fulfillment, Robotics / 26.10.2017

Neocortex artificial intelligence links cyber/digital systems and physical systems of the Industry 4.0 revolution – where software algorithms control machines that are integrated with each other and users.

Neocortex uses a closed loop system, known as cybernetics, to control robots.  This embedded system uses sensor data coupled with physical movement, further integrating the Internet of Things.

In the supply chain, the above smart system provides a highly flexible robot cell that operates at maximum speed – matching the utility of semi-skilled labor.  The Neocortex-based robotic cell (Neocortex G2R Cell) continues to get smarter with time – adjusting to parts, processes, containers, and orders. Thus, its value increases over time and with use (just like an employee), leading to a SaaS (software as a service) delivery model.

Neocortex SaaS also spans cloud-computing servers.

This broadens the scope and significance of patterns discovered and monitored across the cyber-physical barrier, leading to valuable breakthroughs in advanced analytics of big data: supply chain effectiveness, group learning of robots, introduction of SKUs, quality or vendor problems, damage trends, and customer order satisfaction. This both lowers costs and increases sales.

Watch a great overview of Industry 4.0 implications here.

Read More >>

Warehouse & Logistics Robotics WW Revenue Projected to Grow 64% CAGR

Artificial Intelligence, eCommerce, Machine Learning, Neocortex, Neocortex G2R Cell, Robotics, Robotics Business / 30.05.2017

Research and Markets projects that the global warehouse and logistics robot market revenue will grow from $1.9B in 2016 to $22.4B in 2021, and units from 40,000 to 620,000. Research Analyst Manoj Sahi states, “new robotics technologies that could yield a return on investment (ROI) in less time than it took a few years ago.” Two key areas the report points out are the growth of mobile robot platforms and industrial robot manipulators.

Read More >>

Neocortex® G2R Cells are Easy to Both Deploy & Re-Deploy

3D Vision Guidance, Artificial Intelligence, Machine Learning, Neocortex, Neocortex G2R Cell, Random Bin Picking, Robot Vision Guidance, Robotics, Robotics Business / 06.03.2017

A Neocortex® G2R (Goods to Robot) Cell is easy to deploy, like a collaborative robot. Yet it is uses an industrial Yaskawa Motoman robot with up to twice the capacity and 150% the speed of a collaborative robot (up to 800 items per hour).

How easy to deploy is the Neocortex G2R Cell? The average time for a Cell to be up and running at a customer site is one day.  See our fun time-lapse video here.  After it is up and running, our team then optimizes the robot and trains your operators. This contrasts with integrating an industrial robot system that may take weeks before being ready to run.  The Cell’s deployment efficiency is comparable a collaborative robot’s average setup time, which is about half a day.

Read More >>

What’s Hot in Robotics?

Artificial Intelligence, Machine Learning, Neocortex, Robotics, Robotics Business / 18.06.2015

Frank Tobe’s article in Robohub regarding what’s hot in robotics reads like a who’s who of companies providing state-of-the-art applications in robotics. He breaks down the trends into four buckets, one of which I’d like to address – Advances in Visual Perception.

Here’s what he says:

“Vision-enhanced robotic systems are becoming the top reason for upgrading and deploying vision-enabled robots and a core reason for the steady upward growth of the robotics industry…. Artificial intelligence and various AI learning systems have been improving regarding visual perception, and many new companies (such as Universal Robotics and their Neocortex system) are now either offering vision systems that can supplement existing fixed systems or offering mobile manipulators that can find and determine how best to pick and handle all sorts of objects from plastic-wrapped toys to boxes, cases and skids of materials.”

Frank’s points are correct. Let’s unpack the reasons for this burgeoning market opportunity.

Read More >>

Robotic Throughput vs Flexibility

3D Vision Guidance, Artificial Intelligence, Machine Learning, Neocortex, Robot Vision Guidance, Robotics / 19.09.2014

Robotic material handling occurs in unstructured environments. In addition, the objects to be moved or manipulated by the robot often have never been seen before, vary constantly, and are in random locations. In the past, there was a tradeoff between throughput and flexibility.

Enjoy this short video blog as I explain on the whiteboard the current status of robotic solutions in the depalletizing application workspace, using throughput and flexibility as the main variables. It represents state of the art, industrial grade solutions for vision-guided robots, advanced vision-guided robots, and machine learning-guided robots.

Enjoy!

Robotic Depalletizing Throughput vs Flexibility Video Blog

Read More >>

Supply Chain Analytics

Artificial Intelligence, Cybernetics, eCommerce, Machine Learning, Neocortex, Robotic Order Fulfillment, Robotics, Robotics Business / 29.08.2014

Clint Reiser points out in the linked article that a new revolution in supply chain analytics is occurring. There is new level of data detail, it’s coming at us faster, providing bigger patterns and better insights.

The detail isn’t just point-of-sale information, customer buying patterns, or fleet telematics. From Universal’s perspective, the combining of machine learning and machine vision into robust automated solutions for material handling processes previously thought as random is a unique source of this data.

Read More >>