I guess we have entered the post-pandemic era. Universal Robots is taking its latest technology on tour this summer. By the time I got to this news item, the first date was passed. If you are close to one of these areas, check out this cool technology.
Automating machine loading traditionally means integrating conveyors, bowl feeders, custom trays, shaker tables or various other components and processes. These approaches can lead to a range of obstacles and challenges, including complex programming and setup, poorly-utilized manpower, inefficient machine utilization and decreased output.
ActiNav changes all that, combining intelligent vision and sensor software with the autonomous motion control of Universal Robots’ world-leading cobots in one seamless Application Kit that solves the random bin picking challenge in machine tending applications. To give manufacturers an opportunity to experience ActiNav hands-on, Universal Robots and its partners are now hosting live demos, inviting attendees to bring their parts to be picked, experiencing how easy it is to set up a sophisticated machine loading system.
“We want manufacturers to experience in person the “wow factor” as they see ActiNav effortlessly pick their randomized parts and place them correctly in a designated place,” says Bryan Bird, Regional Sales Director for Universal Robots’ North America division. “We look forward to working with our partners in providing this unique experience.”
The ActiNav Tour dates are hosted by Universal Robots partners and systems integrators on the following dates and locations:
FPE Automation: July 13, Elk Grove Village, IL
Southwestern PTS: July 22, Coppell, TX
NEFF Wisconsin: August 3, Mequon, WI
CIMTEC: August 5, Charlotte, NC
Shaltz: August 10, Flint, MI
In addition to meeting ActiNav on tour, manufacturers can now leverage an expanded network of ActiNav Solution Providers (ASPs), a vetted and carefully selected group of systems integrators across the U.S. to deploy the next-generation machine loading solution. Joining the ASP network are:
Bird explains that UR’s selection process focused on integrators with expertise in both vision and robotics, that deliver superior value, and on time/on budget projects for customers.
Dan Carney, General Manager at Wisconsin-based PCC Robotics, is looking forward to sharing the benefits of Actinav with manufacturers in his region. “As a systems integrator we find parts staging to be a key component of nearly every application,” he says. “We have reviewed a number of bin picking offerings and ActiNav is simply in a different class.”
Festo has consistently presented me with some of the most impressive creativity within pneumatics, robotics, and automation. This is a fascinating use of artificial intelligence (AI) with robot gripping. Only a couple of years ago, I caught myself thinking that nothing could be as boring as robotic end-of-arm-effectors. How wrong could I have been! This is my second post on this technology in a couple of weeks. Check this out.
Production, warehouse, shipping – where goods are produced, stored, sorted or packed, picking also takes place. This means that several individual goods are removed from storage units such as boxes or cartons and reassembled. With the FLAIROP (Federated Learning for Robot Picking) project Festo and researchers from the Karlsruhe Institute of Technology (KIT), together with partners from Canada, want to make picking robots smarter using distributed AI methods. To do this, they are investigating how to use training data from multiple stations, from multiple plants, or even companies without requiring participants to hand over sensitive company data.
“We are investigating how the most versatile training data possible from multiple locations can be used to develop more robust and efficient solutions using artificial intelligence algorithms than with data from just one robot,” says Jonathan Auberle from the Institute of Material Handling and Logistics (IFL) at KIT. In the process, items are further processed by autonomous robots at several picking stations by means of gripping and transferring. At the various stations, the robots are trained with very different articles. At the end, they should be able to grasp articles from other stations that they have not yet learned about. “Through the approach of federated learning, we balance data diversity and data security in an industrial environment,” says the expert.
Powerful algorithms for industry and logistics 4.0
Until now, federated learning has been used predominantly in the medical sector for image analysis, where the protection of patient data is a particularly high priority. Consequently, there is no exchange of training data such as images or grasp points for training the artificial neural network. Only pieces of stored knowledge – the local weights of the neural network that tell how strongly one neuron is connected to another – are transferred to a central server. There, the weights from all stations are collected and optimized using various criteria. Then the improved version is played back to the local stations and the process repeats. The goal is to develop new, more powerful algorithms for the robust use of artificial intelligence for industry and Logistics 4.0 while complying with data protection guidelines.
“In the FLAIROP research project, we are developing new ways for robots to learn from each other without sharing sensitive data and company secrets. This brings two major benefits: we protect our customers’ data, and we gain speed because the robots can take over many tasks more quickly. In this way, the collaborative robots can, for example, support production workers with repetitive, heavy, and tiring tasks”, explains Jan Seyler, Head of Advanced Develop. Analytics and Control at Festo SE & Co. KG During the project, a total of four autonomous picking stations will be set up for training the robots: Two at the KIT Institute for Material Handling and Logistics (IFL) and two at the Festo SE company based in Esslingen am Neckar.
Start-up DarwinAI and University of Waterloo from Canada are further partners
“DarwinAI is thrilled to provide our Explainable (XAI) platform to the FLAIROP project and pleased to work with such esteemed Canadian and German academic organizations and our industry partner, Festo. We hope that our XAI technology will enable high-value human-in-the-loop processes for this exciting project, which represents an important facet of our offering alongside our novel approach to Federated Learning. Having our roots in academic research, we are enthusiastic about this collaboration and the industrial benefits of our new approach for a range of manufacturing customers”, says Sheldon Fernandez, CEO, DarwinAI.
“The University of Waterloo is ecstatic to be working with Karlsruhe Institute of Technology and a global industrial automation leader like Festo to bring the next generation of trustworthy artificial intelligence to manufacturing. By harnessing DarwinAI’s Explainable AI (XAI) and Federated Learning, we can enable AI solutions to help support factory workers in their daily production tasks to maximize efficiency, productivity, and safety”, says Dr. Alexander Wong, Co-director of the Vision and Image Processing Research Group, University of Waterloo, and Chief Scientist at DarwinAI.
The FLAIROP (Federated Learning for Robot Picking) project is a partnership between Canadian and German organizations. The Canadian project partners focus on object recognition through Deep Learning, Explainable AI, and optimization, while the German partners contribute their expertise in robotics, autonomous grasping through Deep Learning, and data security.
KIT-IFL: consortium leadership, development grasp determination, development automatic learning data generation.
KIT-AIFB: Development of Federated Learning Framework
Festo SE & Co. KG: development of picking stations, piloting in real warehouse logistics
University of Waterloo (Canada): Development object recognition
Darwin AI (Canada): Local and Global Network Optimization, Automated Generation of Network Structures
There exist interesting developments in robotics beyond all the excitement of collaborative robotics (cobots). Companies are working on control platforms agnostic to the hardware. Although AI (usually machine learning) has been around for years, marketers and media have jumped all over the term. More important than the buzz is this example of something that actually works. Goes to show that there remain many areas for further development in our market.
Pioneering the next frontier of manufacturing through a combination of artificial intelligence (AI) and industrial robotics, Symbio Robotics, announced its work with Ford Motor Company to deploy an AI-controlled robot at the automaker’s Livonia Transmission Plant. The robot is programmed and managed with Symbio’s robot-agnostic platform, SymbioDCS, to assemble transmissions for the Bronco Sport, Escape and Edge, to name a few.
Assembly of transmissions is notoriously complex. Previously, operators installed heavy transmission components such as torque converters manually, a challenging process from an ergonomics and safety standpoint. In recent years, the process was automated. Now Symbio is helping Ford to control the robot with AI which more efficiently installs components into the transmission based on the large amounts of data it has collected. This new process allows the robot to predict how it should assemble components in the next transmission based off of its previous performance.
“Symbio’s focus is on delivering technology that allows companies like Ford to adopt AI as a core competency,” said Max Reynolds, Symbio CEO and co-founder. “AI-enabled automation looks very different. It’s not just about automation, it’s about providing tools that empower automation teams to deploy and maintain more general, flexible systems.”
Symbio builds automation that enables human-machine collaboration. Its technology is designed to fundamentally reframe existing manufacturing pain points by utilizing the best practices of AI and human robot interaction and the programmers that are already working in these environments. Through the use of AI applied by people, the robots quickly learn and execute tasks increasing efficiency, improving quality and reducing ergonomic hazards.
“As the mobility landscape continues to rapidly change there is an increasing demand for much faster product life cycles,” said Harry Kekedjian, Advanced Controls and Digital Factory Manager at Ford. “Using the Symbio technology, we’ve observed a 15% improvement in cycle time and greater than 50% reduction in adapting to new products over the previous manufacturing method.”
Founded in 2014, Symbio Robotics is dedicated to strengthening and revamping the fundamentals in industrial manufacturing through the creation of Al and Robotics technologies. Located in Emeryville, Calif., the company’s core product, SymbioDCS enables automation teams to build and deploy high-quality applications in any factory, at any scale that can assemble anything.
The Danish collaborative robotics (cobot) tools company OnRobot has been churning out innovative robotic tooling in a stream for the past year. It also taps the partnership stream of collaboration. I’ve run across Vention at a trade show a few years back but haven’t really seen something I could write about intelligently. Here is a partnership between the two that should bear fruit.
Vention, a manufacturing automation platform (MAP), today announced its partnership with OnRobot, which makes tools for collaborative applications. This partnership combines Vention’s online-first manufacturing automation platform with OnRobot’s library of plug-and-play end-of-arm tools to accelerate the design and deployment of end-to-end cobot applications.
Vention’s MAP provides users with the engineering software and modular hardware they need to design, automate, order, and deploy factory equipment in a single digital environment. With thousands of modular parts, smart design tools, and real-time pricing, factory equipment can be designed in minutes—from anywhere, on any web browser. With the addition of OnRobot’s plug-and-play tools for collaborative and light industrial robotics, manufacturing professionals can focus on scaling production with greater flexibility and efficiency.
The combination of offerings makes it even easier to automate tasks like machine tending, material handling, material removal and assembly. With solutions for grippers—parallel, flexible, magnetic, and vacuum alike—as well as vision cameras, sanding tools, screwdriving tools, and more, the application possibilities have now been significantly expanded.
“We’re thrilled to be working with OnRobot to offer a range of industry-leading cobot solutions,” says Patrick Tawagi, Director of Application Development at Vention. “OnRobot’s suite of grippers and end-of-arm tools covers almost every application in the cobot market, and their straightforward interface combined with Vention’s platform makes them incredibly easy to deploy.”
“OnRobot’s exciting partnership with Vention will make it easier than ever for companies of all sizes and skill levels to deploy collaborative automation,” says Kristian Hulgard, General Manager of the Americas division at OnRobot. “The combination of Vention’s superb MAP platform and OnRobot’s ever-expanding, award winning range of no fuss tools for collaborative applications will empower users to design and deploy advanced automation with unprecedented ease.”
One of the dirtier applications has come to the cobot world—welding. Here is a smartphone app that interfaces to a Universal Robotics Cobot with an attached Miller welding system to transform it into a welding machine.
Hirebotics’ Cobot Welder, Powered by Beacon, is a complete, user-friendly collaborative robot (cobot) welding system that enables painless automated welding deployments. “The Cobot Welder is a major leap forward in easy-to-use welding automation that combines industrial grade robot welding functionality with consumer level ease-of-use and a phenomenal price point,” says Rob Goldiez, Cofounder and CEO, Hirebotics.
Complete and ready to go right out of the box, Cobot Welder provides all the hardware and software required to get started on an automated welding deployment, including: a UR10e collaborative robot, a Miller Invision 352 MPa cobot package, a Tregaskiss robotic torch, a mobile cart with a standard 5/8” diameter on 2” center hole pattern, and Hirebotics’ Cobot Welder smartphone application.
“With Cobot Welder, Hirebotics has managed to eliminate the pain points from robot welding system deployments. At the heart of the system is our Cobot Welder smartphone app, which turns welders into robot programmers in a matter of minutes, no pendant required,” says Mitch Dupon, Director of Business Development at Hirebotics. “By reducing the time taken to teach new parts by as much 60%, Cobot Welder reduces downtime, improves welding quality and productivity and ensures painless automated welding deployments. I’m excited to talk about this and the other productivity benefits provided by Cobot Welder at the forthcoming launch.”
“The welding profession is experiencing a labor crisis. The average age for skilled welders is 55, most are likely to retire within 10 years, and younger people aren’t entering the profession in sufficient numbers to sustain industry demand,” Joe Campbell, Universal Robots’ Senior Manager of Applications Development & Strategic Marketing, North America says. “There is an urgent need for collaborative welding systems that are safe to use around human beings and can be used to support expert human welders by taking over the tedious and unergonomic aspects of the welding process,” says Campbell.
One company consistently sending news is ABB. PR on the process side has moved to Europe, but robotic and related PR is still handled locally. I find it interesting that the major European suppliers have moved marketing out of the US, while some US-based suppliers have just pulled back. Not sure what they know about US manufacturing that I should know.
Technology additions to Ethernet have become interesting. They’ve existed a while, but products and momentum are growing. One is 2-wire Ethernet; but this news relates to power over Ethernet. ABB has released a flowmeter. The other news relates to a hot topic—electric vehicle (EV) battery manufacturing. This will remain a focus for quite some time.
ABB launches world’s first Power over Ethernet flowmeters
ABB has incorporated power supply through Ethernet connectivity on board the latest edition of its electromagnetic flowmeter ProcessMaster* and mass flowmeter CoriolisMaster, opening a new chapter in instrumentation and industrial communication.
Power over Ethernet (PoE) offers several benefits for process engineers, as it omits the need for a separate DC power infrastructure, providing power and communications via the same cable. This brings new agility as flowmeters can be installed wherever needed. In addition, ABB 4-wire Ethernet combines classic outputs with future communication protocols. Offering a modular design allows the combination of both worlds and ensures that devices are futureproof, increasing the longevity of the flowmeters.
Furthermore, flowmeters with Ethernet connectivity increase simplicity, flexibility and reliability to operations in process automation, while enhancing real-time visibility of data. Previously hidden data in field devices, such as measurement values on density, conductivity or concentration of the medium, can be unlocked. This in turn will help customers across all industries identify redundant measurement points in their plants to achieve savings along the way.
“ProcessMaster and CoriolisMaster with Ethernet will support our customers’ digital journey towards smart cities and Industry 4.0. Ethernet is the leading communications technology. By incorporating it into the ABB flowmeters, we can help even more customers reduce complexity of operations and lower costs of infrastructure in more plants around the world – safely and remotely.” said Frank Frenzel, Global Product Line Manager Process Flowmeters.
An integrated secure webserver based on the ABB Ability Cyber Security framework ensures robust and secure operations that offer instrumentation engineers support during commissioning and troubleshooting. It also provides access to configuration, diagnostics and measurement data through a built-in QR code. This allows verification of all parts of the flowmeter and provides insights into its operating condition with automatically generated reports.
Combining 4-20 mA or digital outputs with new 1- or 2-port Ethernet makes classic instrumentation truly future-proof, with speeds of up to 100Mbit/s. The flowmeters use various Ethernet based communication protocols, such as simple Modbus TCP or high performance EtherNet/IP. This prepares them for IT/OT convergence, cloud connectivity and the requirements needed for secure and encrypted communication both today and tomorrow.
*Ethernet connectivity for the electromagnetic flowmeter ProcessMaster is currently available in North America only. It will be released globally later in 2021.
Global EV battery production needs significant boost to meet demand
According to the ‘Electric Vehicle Battery Supply Chain Analysis,’ sponsored by ABB Robotics and authored by the automotive intelligence unit of Ultima Media, while 2036 is the changeover year when all-electric passenger vehicles are predicted to overtake sales of ICE-equipped equivalents, concerns over EV battery supply to meet the escalation in demand poses serious risk to the growth of electricity as a clean propulsion fuel, despite plans for 80 new global battery gigafactories.
The report outlines that although Asia leads electric vehicle battery production, Europe will make up vital ground over the next few years while US manufacturers are also planning increases in capacity.
“Automation is key to increasing assembly safety, quality and traceability and delivering battery technologies cost effectively, which is critical to the expansion of electric vehicles.” said Tanja Vainio, Managing Director of ABB Robotics Auto Tier 1 Business Line. “With production speed and flexibility essential to the successful scale-up of the EV battery industry, our cellular production architecture enables manufacturers to quickly validate a cell design and then roll out production cells globally with uniform quality, safety and productivity standards. Roll-outs can be scaled to demand with the flexibility to adjust capacity in real time.”
The report’s researchers point to the importance of battery pack assembly being located close to or within car assembly facilities.
“Co-locating battery pack assembly not only boosts sustainability by reducing transportation, it increases flexibility. A cellular approach to production is easily integrated alongside existing lines. If the demand curve moves, cells can be added or removed quickly to maintain accurate production scale. Our robots are designed to be quickly repurposed as needed, boosting flexibility and adding to our sustainable approach by maximizing the life of each robot we build,” added Vainio.
“We believe that building a robust battery supply chain will create a distinct competitive advantage for OEMs, setting a trend towards maximum production flexibility, whether battery pack production is insourced or outsourced, to further reduce costs and boost productivity,” Vainio added.
The high price of EVs will increasingly create a barrier to further market penetration, reducing vehicle cost has therefore become a whole-industry focus. Given that the battery represents up to a third of vehicle costs, ABB is focused on solutions that improve battery manufacturing productivity.
“Increasingly we see that higher productivity and lower costs are driven by assembling battery cells straight into packs,” concludes Vainio. “ABB is working in partnership with a number of manufacturers, using its systems and knowledge to increase productivity, quality and safety levels, as well as reduce finished pack costs through automated assembly – vital if EVs are to meet their required cost and adoption targets.”
The ‘Electric Vehicle Battery Supply Chain Analysis’ examines the current and future state of EV battery supplies – sources of materials, technologies available, demand analysis and potential risks.