by Gary Mintchell | Apr 3, 2024 | Automation, Robots, Software, Technology
Vision software for guiding robots news goes along with the burst of robot news. In this case, AI meets vision software.
AI software company Micropsi Industries today announced MIRAI 2, the latest generation of its AI-vision software for robotic automation. MIRAI 2 comes with five new features that enhance manufacturers’ ability to reliably solve automation tasks with variance in position, shape, color, lighting or background.
What sets the MIRAI 2 AI-Vision Software apart from traditional vision solutions is the ability to operate with real factory data without the need for CAD data, controlled light, visual-feature predefinition or extensive knowledge of computer vision.
Gary Jackson, CEO of Micropsi Industries, noted, “Recognizing the complexities of implementing advanced AI in robotic systems, we’ve assembled expert teams that combine our in-house talent with select system integration partners to ensure that our customers’ projects are supported successfully, no matter how complex the requirements.”
MIRAI is an advanced AI-vision software system that enables robots to dynamically respond to varying conditions within their factory environment, including variance in position, shape, color, lighting and background. What sets MIRAI apart from traditional vision solutions is the ability to operate with real factory data without the need for CAD data, controlled light, visual-feature predefinition or extensive knowledge of computer vision.
The five new features that will be available to MIRAI 2 users are:
Robot skill-sharing: This new feature allows users to share skills between multiple robots, at the same site or elsewhere. If conditions are identical (lighting, background, etc.), very little or no additional training is required in additional installations. MIRAI can also handle small differences in conditions by recording data from multiple installations into a single, robust skill.
Semi-automatic data recording: Semi-automatic training allows users to record episodes (of data) for skills without having to hand-guide the robot, reducing the workload on users and increasing the quality of the recorded data. MIRAI can now automatically record all the relevant data—users only need to prepare the training situations and corresponding robot target poses.
No F/T sensor: Training and running skills is now possible without ever connecting a Force/Torque sensor. This reduces cost, simplifies tool geometry and cabling setup, and overall makes skill applications more robust and easier to train.
Abnormal condition detection: MIRAI can now be configured to stop skills when unexpected conditions are encountered, allowing users to handle these exceptions in their robot program or alert a human operator.
Industrial PC: The MIRAI software can now be run on a selection of industrial-grade hardware for higher dependability in rough factory conditions.
by Gary Mintchell | Apr 2, 2024 | Automation, Process Control, Productivity, Software, Sustainability
Fero Labs has developed software to help certain types of process manufacturing plants improve quality output economically when given a random mix of feedstock. I wrote about the company last August—A Better Way to Control Process Quality.
They sent a new press release, and I must admit that I understood almost nothing in it:
Fero Labs, the only Profitable Sustainability Platform for industrial optimization, announced the release of their ground-breaking feature ‘ExplainIt for Live Predictions’ which expands a factory’s production knowledge in real-time. This advanced feature for cross-functional teams increases trust in AI predictions by disclosing real-time text explanations about abnormal factors influencing their live production.
There were way too many marketing-type phrases in there. Worst of all was the concept of “trust in AI predictions.” So, I asked the very patient publicist. She suggested that I talk with Berk Birand, Fero Labs Co-founder and CEO. And, I did. He was most helpful.
We caught up from my last article about their ability to use the huge data sets manufacturers have accumulated over the past decade using advanced statistical methods and “white box machine learning (ML)” to help engineers optimize their plants. Make them more profitable and reduce waste (sustainability). Therefore the “Profitable Sustainability” company.
Birand took me through an example that I could understand, since I had a customer in the 90s who did this sort of process.
Imagine a plant with piles of scrap steel in a yard. They have an electric arc furnace that melts all that disparate steel that will be poured out eventually to make their final product. Given that the feedstock has high variability as to the composition of the steel, the typical plant overdesigns the process to allow for variations. This, of course, is wasteful on the surface. But if the final chemical analysis shows that the output will not make the desired tensile strength or other spec, then the waste is even higher.
What if you accumulated the data (feedstock, process, finished steel) over time built a modern AI model? Its predictions could be used to drive profits, reduce waste, save time. But, would anyone trust yet another advanced process control system? We all know that models eventually goes out of whack sometimes and sometimes gets the wrong answer.
Here comes the “trust” part of the trust in AI model. They built an explainable model from the beginning. It can predict characteristics, say tensile strength of the mix because of chromium or carbon levels and so forth. Since we know that every model is wrong sometimes, they built in confidence levels in the prediction engine. Their AI looks at the material composition and suggests adding chemicals to the mix, but it gives an explanation and a confidence level. The engineer looks at the confidence report (I am confident in this prediction or I’m not confident in this prediction) and can decide whether to go with the AI or to go with gut feel based on years of experience.
He convinced me. Fero Labs has developed an AI engine that gives the engineer a level of trust in the prediction.
More explanation from the press release:
Expanding on Fero Labs’ white-box ML, which provides full transparency of Fero’s powerful machine learning models, the new ExplainIt feature provides a contextual explanation of anomalous factors involved in each live production optimization.
This type of analysis is typically addressed through linear Root Cause Analysis (RCA) tools. Unlike traditional methods, Fero Labs’ solution is non-linear, much like process operations, and delivers results in seconds rather than the hours or days typically needed. Traditional methods generally require the engineer to preselect a small sample of factors to investigate, which can introduce potentially misleading biases. Fero Labs’ software has the power to evaluate all relevant factors which improves insight and prediction accuracy.
by Gary Mintchell | Apr 1, 2024 | Automation, Robots
More robotics news with the added bonus of more NVIDIA AI-chip news. Usually I have written about Universal Robots and MiR, but each has been acquired by Teradyne. Looks like a new marketing angle with Teradyne Robotics. This company has collaborated with NVIDIA to add AI-type compute to its robot line.
Teradyne Robotics, which includes collaborative robot (cobot) company Universal Robots (UR) and autonomous mobile robot (AMR) company MiR, has announced a collaboration with NVIDIA to bring new AI capabilities to automation applications.
UR has integrated NVIDIA accelerated computing into its cobot for faster planning, making path planning 50-80x faster than today’s solutions. The combination of the NVIDIA Jetson AGX Orin, a complete system-on-module (SOM) designed for edge AI applications, the cuMotion path planner from the NVIDIA Isaac Manipulator platform, UR’s new PolyScope X software and its UR5e cobot platform is expected to increase application potential and efficiency for automation customers.
Teradyne Robotics has also announced the launch of a new AI-powered solution for pallet handling, the MiR1200 Pallet Jack. The newest product from MiR harnesses advanced AI pallet detection powered by the NVIDIA Jetson AGX Orin module. The MiR1200 Pallet Jack uses 3D vision to identify, pick up and deliver pallets with unprecedented precision, even in dynamic and complex environments. With the addition of this Pallet Jack to the portfolio, MiR has become a one-stop shop for autonomous material handling at factories and warehouses.
by Gary Mintchell | Apr 1, 2024 | Automation, Robots
ABB has entered the mobile robot fray and enhanced the offering through the recent acquisition of Sevensense. This acquisition gives the company an AI-based navigation technology it calls Visual SLAM. The company also adds a new AMR Studio software enabling even first-time robot users the ability to easily program and operate fleets of mobile robots.
ABB Robotics has announced its first Flexley Tug T702 autonomous mobile robot equipped with AI-based Visual SLAM navigation technology and the new AMR Studio software, enabling first-time robot users to easily program and operate entire fleets of mobile robots. The new capabilities simplify configuration and can reduce commissioning time by up to 20 percent, paving the way for a workplace where intelligent robots operate autonomously, amid a critical shortage of skilled labor.
“Following our acquisition of Sevensense in January, I’m pleased to offer our first AMR with AI-based Visual SLAM technology and AMR Studio software. This combination of mobile robotics and leading AI-powered navigation technology brings unmatched intralogistics flexibility and scalability for ABB’s customers, in an environment that is shifting from linear production to dynamic manufacturing networks,” said Marc Segura, President of ABB Robotics. “The AMR T702 is a perfect match for a wide range of industries, such as automotive, consumer goods sector or logistics, especially in large, busy warehouses and fulfillment centers where the environment is constantly changing.”
by Gary Mintchell | Mar 28, 2024 | Automation, News, Robots
Robotics news seems to present itself all the time. I’m writing this from an independent coffee house in a small town in northern Illinois. The guy at the table behind me is quoting a robotic packaging system to a client. Weird.
ABB held a big unveiling day at its Auburn Hills, MI facility that had recently been refitted and upgraded. I attended virtually—just could not work out the logistics to make it physically. Impressive event.
In short:
- Refit will support customers and ABB’s leadership in growing US robotics segments, including Packaging & Logistics, Food & Beverage, Construction, Lifesciences & Healthcare and Automotive electric vehicle production
- New factory serves as US hub, developing and manufacturing AI-enabled technology to help businesses respond to labor shortages, global uncertainty and the need to operate more sustainably
- Expansion is latest in over $30 million Robotics investment in the US since 2019 including Packaging & Logistics headquarters in Atlanta, Lifesciences and Healthcare Research Lab in Houston and Research and Development Center in San Jose.
The expanded facility reflects ABB’s commitment to long-term growth in the US market, which is predicted to follow global growth rates for robotics of 8% CAGR, as well as the company’s global investment to build Robotics and Automation capacity and create new, highly skilled jobs. This is ABB’s third global robotics factory expansion in three years across China, Europe and the Americas and is part of its efforts to further strengthen its local-for-local footprint.
With a 30 percent increase in facility space, the new Auburn Hills facility will enhance ABB’s ability to serve as the leading strategic robotics partner for its growing customer base. Through the new Customer Experience Center, ABB will showcase its leading hardware and software solutions, pioneering the latest digital and AI-powered automation technologies with customers, and developing and manufacturing next generation robots.
The expanded facility will support ABB Robotics’ specialist centers including its Packaging and Logistics hub in Atlanta, Georgia; its Life Sciences and Healthcare hub at the Texas Medical Center in Houston, Texas; and AI Research Lab in San Jose, California. Complete with a new training center, the facility will educate over 3,000 workers and students each year, equipping them with the skills to thrive in a new era of AI-powered automation.