North American paper mills are starting to use robotics for smelt spout cleaning. Source: Valmet

Recovery boilers represent a significant capital expenditure in the pulp and paper industry. While a well-maintained boiler can last for decades, routine care of this system can present challenges. Maintenance duties are often messy and risky for the operator, and many tasks are time-consuming and require full or partial boiler shutdown. This can harm overall productivity and mill safety.

One maintenance task that is particularly challenging in the care of recovery boilers is smelt spout cleaning. While cleaning smelt spouts is essential for efficient recovery boiler performance, it can pose serious safety risks to the operator when the spouts are cleaned manually.

These risks include the operator encountering molten smelt, green liquor, and hot gasses, as well as repetitive-motion back and shoulder injuries. Finding operators who are willing to perform these tasks, training them, and retaining them over time have also become part of the challenge.

To improve operator safety during smelt spout cleaning and increase both operator and boiler productivity, pulp and paper facilities now have automated robotic solutions that can take on these more difficult tasks.

Robotic technology for smelt spout cleaning has been available since 2008, but it has only recently entered North American paper mills. Its delayed entry has been largely due to low numbers of new recovery boiler installations, as the robot requires a certain amount of space that is often difficult to allocate within existing operations.

Now, as North American operations are in greater need of the benefits that accompany smelt spout cleaning robots, they can invest in retrofitting existing recovery boilers with robotic solutions.

Smart design removes barriers to robotics retrofits

For pulping operations, one of the biggest barriers to adopting a smelt spout cleaning robot is often the amount of space that’s required for the robot to move around the spout deck during the cleaning cycle. In many facilities, this area around the smelt spout systems is already tight, which is part of what makes manual smelt spout cleaning difficult and risky for operators.

As automation designers have continued to invest in understanding the safety and productivity challenges faced by the pulp and paper industry, new solutions have emerged that remove this common barrier to adding robotics.

For instance, one smelt spout cleaning robot offers the option of a standing mount or a hanging mount. All that’s required to employ the hanging mount and position the robot next to the recovery boiler is a linear rail assembly.

The assembly allows the robot to move side-to-side along the spout deck to clean all spouts. Then, it moves off the spout deck once it completes the cleaning cycle. This configuration maintains sufficient room for the robot to perform its tasks while also ensuring that operators can safely enter the area to perform other duties.

Protective fencing and multiple entry and exit points will also be incorporated for additional operator safety and efficiency. The majority of retrofit work can typically be completed pre-outage, leaving sufficient time during the maintenance outage for robot installation and commissioning.

Robots can relieve worker strain but require careful integration and deployment. Source: Valmet

Smelt spout-cleaning robots proven in the field

In June 2023, Valmet installed its first smelt spout-cleaning robot in North America at the Pixelle Specialty Solutions mill in Spring Grove, Penn. The new robot performs a smelt spout cleaning cycle every 30 minutes — twice as often as operators were previously able to perform the same task manually. Each cycle takes 15 minutes, and when the robot is not actively cleaning, it rests in its home position safely out of the way.

Physical safety barriers around the robot further protect the operators by triggering the robot to freeze if the barrier is broken. Operators can also remotely control the robot’s cleaning frequency and cycles using pre-programmed sequences. Meanwhile, an onboard camera mounted on the robot wrist allows for real-time inspection of the robot’s performance and troubleshooting from the safety of the control room.

By automating smelt spout cleaning with a robot, the manufacturer added another level of safety for its operators and improved productivity by freeing them up to perform other critical tasks. Additionally, the new robot has helped raise the boiler’s liquor quality, green-to-black liquor standard deviation, and smelt standard deviation by double digits.

Collaboration is key

When retrofitting a smelt spout robot to an existing recovery boiler or planning a new installation, it’s important to choose an automation designer that has industry experience and will collaborate on-site during the design phase.

Since every operation and facility is different, the installation of a smelt spout cleaning robot is not a cookie-cutter process. The designer will have to account for existing components around the spouts like piping, flex hoses and evaluate available structural beams for their ability to support the robot carriage and the linear rail.

A skilled designer will also provide an installation plan that avoids significant spout deck alterations, as changes can be costly and time-consuming.

Smelt spout cleaning robots are meant to work with operators, not replace them. Source: Valmet.

Technology works in harmony with humans

Automation often comes with the assumption of replacing human labor, but that is not the case with smelt spout cleaning robots. Instead, this technology works in harmony with boiler operators to increase their safety. It also frees them up to perform other essential recovery boiler tasks.

Helping operators feel safer and engaging them in a wider variety of tasks throughout their workday can make it easier for pulp and paper manufacturers to hire and retain personnel in these positions. With the efficiencies of automation and well-trained, experienced personnel, manufacturers can improve productivity in many areas, making robotics retrofits worth the investment.

About the author

Dan Morrison is Valmet’s product manager for Smelt Spout Systems and the Smelt Spout Cleaning Robot. The Espoo, Finland-based company is a leading global developer and supplier of process technologies, automation and services for the pulp, paper and energy industries.

Valmet and Körber recently established a joint venture to connect the FactoryPal platform with machinery expertise to streamline digital optimization across the production lines of tissue shop floors and beyond.

The post Smelt spout robots can improve safety, productivity in North American pulp and paper mills appeared first on The Robot Report.

GrayMatter automated manually intensive tasks at Lawrence Brothers. Source: GrayMatter Robotics

Like businesses in other industries, U.S. manufacturers face widening labor shortfalls and need automation to help fill those gaps. GrayMatter Robotics today announced that it has raised $45 million in Series B funding. The Carson, Calif.-based company said it plans to use the investment to expand to meet customer demand. 

“We founded GrayMatter to enhance productivity while prioritizing workforce well-being,” stated Ariyan Kabir, co-founder and CEO of GrayMatter Robotics. “With our physics-based AI-powered systems, we are fulfilling our mission while unlocking new levels of efficiency. With our investors’ support, we are making a real difference for shop workers and addressing the critical labor shortages in manufacturing today.”

GrayMatter Robotics said it bundles proprietary artificial intelligence with off-the-shelf robots, sensors, and tools for application-specific, turnkey solutions. The company offers its systems through a robotics-as-a-service (RaaS) model and said they relieve shop floor workers of tedious and ergonomically challenging tasks. They can also enhance production capacity and reduce scrap, repair, and rework costs, it said. 

GrayMatter applies AI to production tasks

The $2.5 trillion U.S. manufacturing industry is grappling with a growing backlog of unfilled orders due to a severe labor shortage. Many of these roles are hazardous and demand extensive training, leading to a critical gap of 3.8 million unfilled jobs, according to Deloitte.

SK Gupta, Ariyan Kabir, and Brual Shah founded GrayMatter Robotics in 2020. The company said it holds 10 patents and has processed more than 7.5 million sq. ft. (about 700,000 sq. m) of product surface area.

GrayMatter said its proprietary GMR-AI technology enables robots to self-program and adapt to high-mix, high-variability manufacturing environments, providing consistent quality and reducing cycle times. 

Smart workcells with GrayMatter technology can autonomously handle complex tasks such as sanding, polishing, grinding, coating, and finishing, it added. By automating such jobs, businesses can meet global demand while also improving the quality of life for their workers, said the company. 

Products including Scan&Sand, Scan&Polish, Scan&Buff, and Scan&Grind can increase quality and consistency while reducing costs, said GrayMatter. Manufacturers can benefit a system availability of 95% to 98%, and most contingencies can be resolved in under five minutes, it said.

GrayMatter claimed that its systems can work two to four times faster than manual operations and that employee training that used to take six months can now be done in less than a day. In addition, the company said its robots can help businesses address sustainability goals by reducing consumption and consumable waste by 30% or more over traditional methods.

GrayMatter combines AI and robotics to improve finishing efficiency and reduce waste. Source: GrayMatter Robotics

Users report increased efficiencies

Over the past two years, GrayMatter Robotics has deployed robots across North America in aerospace, defense, specialty vehicles, marine, recreation, metal fabrication, and consumer products. The company said its RaaS model helps manufacturers enhance production capacity and reduce costs associated with scrap, repair, and rework.

“We are excited to partner with GrayMatter Robotics, as their AI-driven robotic solutions have enabled us to more efficiently address major demand growth in our operations stemming from increased football participation and market-share gains, ensuring consistent quality and throughput despite workforce staffing challenges,” said Drew Dixon, director of distribution and strategy at sports equipment maker Riddell.

“Collaborating with GrayMatter Robotics underscores Riddell’s ongoing commitment to innovation and excellence in both its manufacturing operations as well as the protective equipment it delivers to the field,” he added.

“GrayMatter helps us replace some of our more taxing manual labor,” said Melanie Protti-Lawrence, president of steel fabricator Lawrence Brothers Inc. “We are proud to partner with GrayMatter in an effort to provide longevity in the workforce. We’re constantly working toward a healthier work-life balance, with a focus on working to live rather than living to work.”

“Their robots are not just tools but [also] enablers of growth,” she said. “They allow our workers to engage in more meaningful and less physically taxing tasks, contributing to a healthier and more productive work environment.”

Investors help GrayMatter to grow

With the new capital, GrayMatter is actively hiring for a wide range of roles to meet customer demands, expanding its Los Angeles headquarters, and accelerating the development and deployment of its next-generation AI-powered robots.

Wellington Management led the Series B round, which also included NGP Capital, Euclidean Capital, Advance Venture Partners, and SQN Venture Partners. They joined existing investors 3M Ventures, B Capital, Bow Capital, Calibrate Ventures, OCA Ventures, and Swift Ventures.

“GrayMatter is driving a pivotal transformation in manufacturing with their advanced AI solutions,” said Sean Petersen, sector lead for private climate investing at Wellington Management. “Their ability to enhance productivity, energy efficiency and safety while managing costs, positions them uniquely in the market.”

Wellington Management Co. advises 2,500 clients in more than 60 countries. The Boston-based firm manages more than $1.2 trillion for clients, including pensions, endowments and foundations, insurers, and global wealth managers.

Wellington’s Private Investing Team has raised more than $8.5 billion in global assets, and it invests in multiple sectors and technologies. The team includes more than 1,000 professionals with private market experience with public market expertise, extensive networks, and robust research to benefit both investors and entrepreneurs.

“The combination of AI-driven technology and depth of domain expertise in the GrayMatter solution blew us away,” said Debjit Mukerji, partner at NGP Capital. “It is incredibly challenging to develop high-performance and ultra-reliable robots for such difficult manufacturing conditions.”

“Going to market with GrayMatter Robotics aligns with our mission to foster innovative solutions that drive efficiency and sustainability in manufacturing,” said Adi Leviatan, president of 3M’s Abrasives Division. “This technology addresses critical industry challenges and delivers significant value to our customers.”

The post GrayMatter raises $45M Series B to ease robot programming for manufacturers appeared first on The Robot Report.

Realtime Robotics demonstrates a multi-robot workcell during Mitsubishi Electric’s visit. Credit: Eugene Demaitre

BOSTON — As factories and warehouses look to automate more of their operations, they need confidence that multiple robots can conduct complex tasks repeatedly, reliably, and safely. Realtime Robotics has developed hardware-agnostic software to run and coordinate industrial workcells smoothly without error or collision.

“The lack of coordination on the fly is a key reason why we don’t see multiple robots in many applications today — even in machine tending, where multiple arms could be useful,” said Peter Howard, CEO of Realtime Robotics (RTR). “We’re planning with Mitsubishi Electric to put our motion planner into its CNC controller.”

The company last month received strategic investment from Mitsubishi Electric Corp. as part of its ongoing Series B round. Realtime Robotics said it plans to use the funding to continue scaling and refining its motion-planning optimization and runtime systems. 

Last week, a high-ranking delegation from Mitsubishi Electric visited Realtime Robotics to celebrate the companies’ collaboration. RTR demonstrated a workcell with four robot arms from different vendors, including Mitsubishi, that was able to optimize motion as desired in seconds.

“Mitsubishi Electric is a multi-business conglomerate, a technology leader, and one of the leading suppliers of factory automation products worldwide,” said Dr. Toshie Takeuchi, executive officer and group president for factory automation systems at Mitsubishi. “I see this partnership as the perfect point where experience meets innovation to create value for our customers, stakeholders, and society.”

She and Howard answered the following questions from The Robot Report:

Mitsubishi Electric, Realtime Robotics integrate technologies

How is Realtime Robotics’ motion-optimization software unique? How will it help Mitsubishi Electric’s customers?

Takeuchi: Realtime Robotics’ software is unique in many ways. It starts with the ability to do collision-free motion planning. From there, the motion planning in single robot cells as well as multirobot cells can be automatically optimized for cycle time.

Our customers will benefit by optimizing cycle time to improve production efficiency and reducing the amount of engineering efforts required for equipment design.

Howard: Typically, to provide access for multiple tools at once, you need an interlocked sequence, which loses time. According to the IFR [which recognized the company for its “choreography” tool], up to 70% of the cost of a robot is in programming it.

With RapidPlan, we automatically tune for fixed applications, saving time. Our cloud service can consume files and send back an optimized motion plan, enabling hundreds of thousands of motions in a couple of hours. It’s like Google Maps for industrial robots.

Does Mitsubishi have a timeframe in mind for integrating Realtime’s technology into its controls for factory automation (FA)? When will they be available?

Takeuchi: We are starting by integrating RTR’s motion-planning and optimization technology into our 3D simulator to significantly improve equipment and system design.

Our plan is to incorporate this technology into our FA control systems, including PLCs and CNCs, and this integration is currently under development and testing, with a launch expected soon.

Howard: We’re currently validating and characterizing for remote optimization with customers. We’re also doing longevity testing here at our headquarters.

In the demo cell, you couldn’t easily program 1.7 million options for four different arms, but RapidPlan automates motion planning and calculates space reservations to avoid obstacles in real time. We do point-to-point, integrated spline-based movement.

Toyota asked us for a 16-arm cell to test spot welding, and we can add a second controller for an adjacent cell. We can currently control up to 12 robots for welding high and low on an auto body.

Mitsubishi Electric recently launched the RV-35/50/80 FR industrial robots — are they designed to work with Realtime’s technology?

Takeuchi: Yes, they are. Our robots are developed on the same platform which seamlessly integrate with RTR’s technology.

Howard: For example, Sony uses Mitsubishi robots to manufacture 2-cm parts, and we can get down to submillimeter accuracy if it’s a known object with a CAD file.

Cobots are fine for larger objects and voxels, but users must still conduct safety assessments.

MELCO’s Dr. Takeuchi changes optimization parameters during RTR demonstration by Kevin Carlin, chief commercial officer. Source: Realtime Robotics

RTR optimizes motion for multiple applications

What sorts of applications or use cases do Mitsubishi and Realtime expect to benefit from closer coordination among robots?

Takeuchi: Our interaction with and understanding from customers suggest that almost all manufacturing sites are continuously in need of increasing production, efficiency, profitability, and sustainability.

With our collaboration, we can reduce the robots’ cycle time, hence increasing efficiency. Multi-robot applications can collaborate seamlessly, increasing throughput and optimizing floor space.

By implementing collision-free motion planning, we help our customers reduce the potential for collisions, thereby reducing losses and improving overall performance.

Howard: It’s all about shortening cycle times and avoiding collisions. In Europe, energy efficiency is increasingly a priority, and in Japan, floor space is at a premium, but throughput is still the most important.

Our mission is to make automation simpler to program. For customers like Mitsubishi, Toyota, and Siemens, the hardware has to be industrial-grade, and so does the software. We talk to all the OEMs and have close relationships with the major robot suppliers.

This is ideal for uses cases such as gluing, deburring, welding and assembly. RapidSense can also be helpful in mixed-case palletizing. For mobile manipulation, RTR’s software could plan for the motion of both the AMR [autonomous mobile robot] and the arm.

Members of Realtime Robotics and Mitsubishi Electric’s teams celebrate their collaboration. Source: Realtime Robotics

Mitsubishi strengthens partnership

Do you expect that the addition of a member to Realtime Robotics’ board of directors will help it jointly plan future products with Mitsubishi Electric?

Takeuchi: Yes. Since our initial investment in Realtime Robotics, we have both benefited from this partnership. We look forward to integrating the Realtime Robotics technology into our portfolio of products to continue enhancing our next-gen products with advanced features and scalability.

Howard: RTR has been working with Mitsubishi since 2018, so it’s our longest customer and partner. We have other investors, but our relationship with Mitsubishi is more holistic, broader, and deeper.

We’ve seen a lot of Mitsubishi Electric’s team as we create our products, and we look forward to reaching the next steps to market together.

The post Realtime Robotics celebrates motion-planning collaboration with Mitsubishi Electric appeared first on The Robot Report.

The industrial robot market is expected to grow by ~3.7% per year between 2024 and 2028. | Source: Interact Analysis

Overall global industrial robot shipment volumes exceeded 500,000 units in 2023, Interact Analysis reports. The global market research firm says the industry is starting to bounce back from a 2023 low point. 

Industrial robot shipments are similar to levels seen in 2022, although the average price of industrial robots decreased last year. The market saw record highs in 2021, and lows in revenues and shipments in 2023. 

“The average price per unit of an industrial robot is on a downward trajectory, following a rise for two consecutive years, and we expect a price decline of around 3% per year between 2024 and 2028. The COVID-19 pandemic coupled with high energy prices and inflation caused an average price increase in 2022,” Maya Xiao, research manager at Interact Analysis, said. “We originally expected robot prices to decrease again in 2023, but ongoing supply chain and inflation issues resulted in prices creeping up to levels close to those seen in 2022. This increased “price effect” was also partially due to the market trend towards heavy payload robots, which are materially a more expensive product.”

In the long term, however, the outlook remains positive. Interact Analysis expects the global industrial robot market to grow on average by 3.7% per year between 2024 and 2028.

Breaking down the industry by region

Breaking down the industry by region, sales of industrial robots to the automotive industry in the Americas faced significant pressure in 2023. This resulted in slow growth for this segment of the market, one of the largest downstream industries for industrial robots in the region.

According to Interact Analysis, Mexico, in particular, is highly dependent on the automotive industry, creating a greater impact on industrial robot sales in the region. Growth of industrial robots in the Americas dropped by 17.3% in 2023. In comparison, APAC saw a slight increase in growth, and EMEA remained stable. 

The American markets accounted for around 17% of global industrial robot revenues, compared to 62% for APAC and 22% for EMEA. In the Americas, the industrial robot market saw strong growth immediately post-COVID in both the automotive and non-automotive industries. This is because these manufacturers were continually looking for ways to improve their production processes and reduce manufacturing costs by adopting the technology. 

3 common applications for industrial robots

The top three most common applications for industrial robots are material handling, welding, and assembly, according to Interact Analysis. These accounted for over 70% of industrial robot market revenues in 2023, with material handling accounting for one-third on its own. 

This application is particularly dominant in the Americas and Europe. The American market has the highest market concentration globally, where the top 5 suppliers share nearly 80% of revenues and over two-thirds of unit shipments.

“It is important to note that our robotics forecasts are underpinned by the Interact Analysis Manufacturing Industry Output (MIO) Tracker,” Xiao said. “We can see from our data that the growth profile for industrial robots reflects the manufacturing slowdown during the pandemic era and the subsequent downturn in 2023. If we take a look at the manufacturing output figures for China, Europe and the Americas, the historic manufacturing contractions are synonymous with the decline in growth for the industrial robot market that we have observed in recent years.”

According to the Association for Advancing Automation (A3), robot sales continue to be slow in North America. A3 said robot sales in North America were down 6% in the first quarter of 2024 compared to the same period in 2023. Companies purchased 8,582 robots from January through March for a total of $494 million, A3 said.

The post Industrial robot shipments exceed 500,000 units in 2023 appeared first on The Robot Report.

ABB robot factory in Michigan. Credit: ABB

Robot sales continue to be slow in North America, according to the Association for Advancing Automation (A3). However, the industry association continues to say there are reasons to be optimistic about a turnaround.

A3 said robot sales in North America were down 6% in the first quarter of 2024 compared to the same period in 2023. Companies purchased 8,582 robots from January through March for a total of $494 million, A3 said. In Q1 2023, North American companies ordered 9,168 units for a total of $597 million.

“North American robot orders are showing signs of improvement as we approach the mid-way point of the year,” said Alex Shikany, A3’s VP of membership & market intelligence. “It’s particularly encouraging to see that non-automotive customers are continuing to grow their adoption of robots, demonstrating the expanding reach and impact of automation across various industries.”

North American robot orders declined by 30% in 2023 after two years of record sales. North American companies purchased 31,159 robots in 2023, compared with 44,196 ordered in 2022 and 39,708 in 2021. A3 attributed the 2023 slowdown to “obvious issues” such as a slow U.S. economy, higher interest rates, and even the over-purchasing of robots in 2022 from supply chain concerns.

It should be noted A3 only collects sales data on traditional industrial robots. It doesn’t collect data about autonomous mobile robots or collaborative robotic arms.

Robot sales to non-automotive companies increase

While overall orders decreased during Q1 2024, orders from non-automotive companies grew 16% over Q1 2023, A3 said. Non-automotive customers ordered 4,096 robots in Q1 2024, which accounted for 48% of total orders. Among these customers, the greatest growth in orders between Q1 2023 and Q1 2024 was seen in:

• Food & consumer goods: 120%
• Life sciences, pharmaceutical & biomedical: 72%
• Metals: 46%

Non-automotive companies purchased 15,436 robots total in 2023. Historically, the automotive industry has been the backbone of robotics sales, but 2020 and 2021 saw huge growth in non-automotive sales.

“Industrial automation is sculpting the future of work and production across myriad industries, truly amplifying human ingenuity rather than replacing it,” said Jeff Burnstein, president of A3. “With advancements in robotics, artificial intelligence (AI) and connectivity, we’re witnessing a paradigm shift that’s reshaping industries, driving productivity and unlocking new possibilities for growth. It’s clearly not just a trend but the cornerstone of modern manufacturing.”

The post Robot sales in North America dip 6% in Q1 appeared first on The Robot Report.

SMAC’s linear rotary actuators can be used for precision screw insertion and tightening. | Source: SMAC

SMAC Moving Coil Actuators today introduced its LBR and LDR Series of linear rotary actuators. The company said it equipped these actuators with its Smart Screwdriver technology for precise screw insertion and tightening in automated manufacturing processes.

With these new actuators, Carlsbad, Calif.-based SMAC said it intends “to set a new standard for efficiency, accuracy, and reliability.”

The LBR and LDR actuators can be used in industrial applications such as electronics assembly, where small screws and delicate materials pose unique challenges, according to the company. SMAC claimed that its actuators tackle these challenges “head-on with their industry-leading capabilities and advanced features.”

“Companies choose SMAC linear rotary actuators for their screwdriving needs due to the unique challenges posed by small, delicate screws and the demand for zero-defect production,” stated Ed Neff, founder and CEO of SMAC. “The LBR and LDR are game changers in automated manufacturing, offering unmatched precision, flexibility, and real-time feedback.”

SMAC designs for precision handling

Founded in in 1990, SMAC said it aims to replace older technologies such as pneumatic cylinders and electric ball screw actuators. It manufactures a wide range of precision programmable electric actuators based on its patented moving-coil technology. 

The company asserted that its electric actuators are unique because force, position, and speed are all programmable. SMAC designed them to perform at high speeds or very low speeds with sub-micron accuracy and repeatability that can be validated with as precise as 1 ms response time. 

SMAC said these characteristics makes its actuators ideal for a wide range of positioning, measuring, inspection, and pick-and-place applications. 

Register now.

LBR and LDR promise thread match, zero-defect production

As manufacturers increasingly seek systems for handling small screws with accuracy and reliability, SMAC said its LBR and LDR lines will become a go-to choice. 

“Our LBR and LDR linear rotary actuators represent a significant advancement in automated manufacturing technology,” said Neff. “With their SMART DRIVER capabilities and unmatched precision, they are poised to revolutionize the way screws are inserted and tightened in a wide range of industries.”

These two lines of linear actuators can address a number of challenges. First, SMAC highlighted its ability to precisely handle items. Small screws are notoriously difficult to assemble, which often leads to issues like cross-threading and damage to tapped hole threads.

The company noted that LBR and LDR’s Smart Driver technology ensures precision screw insertion by detecting the screw top, verifying the thread match, and monitoring screw movement in real time. 

LBR and LDR also provide guaranteed thread match every time, eliminating cross-threading, SMAC said. Using a 1 um encoder, the actuator rotates counterclockwise, recognizes the drop in the first thread pitch, defines the thread, and then begins its clockwise rotation to tighten the screw. 

Finally, the actuators offer zero-defect production, according to SMAC. In industries like medical, aerospace, and automotive, where zero-defect production is non-negotiable, the LBR and LDR offer high reliability, the company said.

The actuators’ advanced capabilities allow for 100% verification of correct processes for flawless assembly every time, said SMAC. 

The company also offers a range of linear rotary actuators that can be used for anything from very small screws to large screws. It is also adding integrated closed-loop torque sensor options to its LBR and LDR actuators. 

The post SMAC introduces LBR and LDR Series of linear rotary actuators appeared first on The Robot Report.

Mitsubishi’s ARIA standard (left) and machine tool tending base (right). | Source: Mitsubishi Electric Automation

Mitsubishi Electric Automation Inc. has announced the latest addition to its pre-engineered workcell product lineup, joining its LoadMate Plus. The company said its Automated Robotics Industrial Assistant, or ARIA, is designed to be a cost-effective system to address urgent challenges across industries. 

“ARIA fulfills an immediate need for flexible and cost-effective automation that addresses common industry problems such as labor shortages, productivity challenges, and the need to maintain quality standards,” stated David Simak, product manager (service) at Mitsubishi Electric. “ARIA is fully configurable and mobile, making it an ideal solution to tackle multiple applications within a given facility.” 

ARIA comes in two models

With a payload capacity of up to 13 kg (28.6 lb.) and a reach of 1,503 mm (59.1 in.), Mitsubishi Electric said ARIA is suitable for use as a standalone cell or implemented into a larger system. The company offers two base options for the system — standard and machine tool bases.

Mitsubishi designed ARIA’s Standard Base option for industrial applications applications where flexibility and mobility are a must. Its Machine Tool Base, on the other hand, works better for tending CNC mill, lathe, and Swiss applications.

The company said that both bases are compatible with Mitsubishi Electric collaborative, vertical/articulated, and SCARA robots. 

The ARIA package comes with an FX5 programmable logic controller (PLC), an external 120V outlet, casters with jackscrews, and a network switch with an external Ethernet port. It also comes with an operator station with a button panel, floor mounting brackets, and more. 

Mitsubishi also offers accessories including preprogrammed software packages, RT ToolBox3 software, MELFA Works for robot simulation, MELFA Safe Plus, Force Sensor, R86TB high-performance teach pendants, and two human-machine interface (HMI) options.

Register now.

Mitsubishi expands industrial robot lineup

Last month, Mitsubishi Electric launched a new robot series for applications that require heavier payloads and longer reach. The company said its new RV-35/50/80 FR series of industrial robots are designed for handling large workpieces and heavy objects to expand automation opportunities for OEMs and end-users. 

Mitsubishi claimed that its industrial robots are equipped with class-leading speed and precision, allowing them to meet the demands of today’s manufacturing applications. The company designed this robot series to allow for an expanded work envelope, as well as increased payload and reach compared with its prior series.

The post Mitsubishi Electric releases pre-engineered ARIA robotic workcell appeared first on The Robot Report.

The Robotics Manufacturing Hub is modular, adaptable, and multi-use, with OEM diversity. Source: The ARM Institute

When the ARM Institute launched its Robotics Manufacturing Hub about a year ago, it quickly realized that U.S. manufacturers weren’t looking at robotics and automation because they weren’t interested in the technology. Instead, the barriers to automation loomed so large that it was impossible for small and midsize firms to know where to start.

When the ARM Institute announced its no-cost Robotics Manufacturing Hub for manufacturers in the Pittsburgh region, its pipeline of interested manufacturers rapidly filled. With the ARM Institute offering a pathway to minimize the risks they associate with robotics and automation, U.S. manufacturers were, and still are, eager to explore the possibilities.

Larger manufacturing firms can more easily navigate the process of implementing automation. With greater general resources, in-house R&D, financing to invest in the upfront costs, and more time to explore solutions, they’ve more successfully been able to see the process through from start to finish.

Small and midsize manufacturers (SMMs) have to navigate more risk. They need to spend more time understanding how the changes will affect their operations. They often lack in-house robotics expertise, and they need systems that will dynamically meet their needs without requiring constant upkeep when, in many cases, their workforce is already strained.

The ARM Institute’s Robotics Manufacturing Hub is a free resource to help manufacturers navigate these barriers and others by identifying the best business cases for robotics, testing the systems within the manufacturer’s budget, and offering a path to implementation. Part of this solution includes the ability for SMMs in Southwestern Pennsylvania to work directly with the institute’s team of robotics engineers and get hands-on with advanced technologies in the institute’s Pittsburgh facility.

Register now.

ARM Institute shares case studies

Since the Robotics Manufacturing Hub’s creation, the ARM Institute has worked with several manufacturers in the Pittsburgh region to explore their challenges and help them understand where robotics can address these challenges.

For example, the ARM Institute worked with a manufacturer of castings and forgings to automate its manual quality-inspection process. Partnering with FARO and NEFF Automation through the Robotics Manufacturing Hub, the ARM Institute performed a proof-of-concept of a Universal Robots cobot controlling a FARO laser scanner. The manufacturer plans to pursue implementation.

The ARM Institute also worked with a company that needed to package heavy iron and steel parts into shipping containers, creating an ergonomically uncomfortable task for a human worker. In this situation, requirements for the robotic end effector were highly specific, and it’s critical to calculate the correct pick place on the parts and speed limitations of the robot to move heavy parts and prevent failure or injury.

The ARM Institute is working with its member CapSen Robotics on a solution.

CapSen Robotics has designed end effectors to sort metal parts. Source: CapSen Robotics

Inside the Robotics Manufacturing Hub facility

Much of this work is completed using the ARM Institute’s headquarters as a neutral ground for exploration and prototyping, giving manufacturers access to equipment before they commit to installing any system.

This facility is modular, adaptable, and multi-use, with OEM diversity to directly meet each manufacturer’s individual needs. ARM Institute engineers work directly in the lab and interface between suppliers and manufacturers to act in the SMM’s best interest and ensure that the work will address the specific challenges the company is facing.

Below is a brief overview of the equipment available through the Robotics Manufacturing Hub and application areas that can be addressed using this equipment:

Collaborative robots:

• Universal Robots (UR) 5e
• Yaskawa HC10
• FANUC CRX-10 Ai/L
• FANUC CRX-20 Ai/L

The cobots can be configured for the following applications:

• Small part handling
• Pick and place
• Vision-guided grasping for pick-and-place applications
• Machine tending
• Process tasks including gluing and dispensing
• Inspection with Faro ARM Quantum with Laser line probe and CMM
• Inspection with Cognex 2D imaging
• Inspection with Cognex 3D imaging

Industrial robots

• Epson VT6L
• Yaskawa GP-88
• Yaskawa GP-180
• Yaskawa Weld Cell with positioner

The industrial robots can be configured for the following applications

• Large part handling
• Large part palletizing
• Large part pick and place
• Force controlled grinding and polishing
• Welding

Get involved with the Robotics Manufacturing Hub

Small and midsize manufacturers in the Pittsburgh region can get a free automation assessment and use the Robotics Manufacturing Hub at no cost, thanks to funding from the Southwestern Pennsylvania Region’s Build Back Better Regional Challenge Award. Now is a great time to get started with the hub, as the ARM Institute is looking to work with more manufacturers.

In the future, the ARM Institute hopes to expand these services to manufacturers beyond this region and encourages those with interest in using or housing these services to reach out. In addition, the ARM Institute’s member ecosystem can use the Robotics Manufacturing Hub as a benefit of membership.

According to the ARM Institute’s “Future of Work” study released last week, industry trends include keeping people in the loop and the need for organizations to learn how to use data as artificial intelligence increases in importance. As a result, the institute noted that manufacturers and training centers must develop programs to help workers develop the skills needed to stay competitive and adapt to new technologies.

U.S. manufacturing resiliency is the cornerstone of our national security. The ARM Institute’s Robotics Manufacturing Hub addresses a critical need in helping to provide SMMs with the resources that they need to explore and implement automation, enhancing their competitiveness and benefiting the full manufacturing ecosystem.

About the author

Larry Sweet last year became director of engineering at the Advanced Robotics for Manufacturing (ARM) Institute in Pittsburgh. He has experience in bringing emerging technologies into production by increasing their Technology Readiness Level, concurrent with improvements in factory floor processes and workforce skills.

Sweet was previously the director for worldwide robotics deployment at Amazon Robotics, leading technology transition and system integration for all internally developed automation into Amazon’s global network. He has also held senior manufacturing and technology roles at Symbotic, the Frito-Lay, United Technologies, ABB, FANUC, and GE. Sweet spoke at the 2024 Robotics Summit & Expo in May.

Editor’s note: This article is syndicated from The Robot Report sibling site Engineering.com.

The post Robotics Manufacturing Hub to help small and midsize U.S. manufacturers compete appeared first on The Robot Report.

Operators use OmniCore V400XT to control a large robot with Robot Studio. Source: ABB Robotics

Thanks to advances in cloud computing, perception technology, and artificial intelligence, industrial and other robots are becoming smarter and more capable. ABB Robotics today launched its next-generation OmniCore platform, which can now control most of its automation line.

“For our customers, automation is a strategic requirement as they seek greater flexibility, simplicity, and efficiency in response to the global megatrends of labor shortages, uncertainty, and the need to operate more sustainably,” said Sami Atiya, president of ABB’s Robotics & Discrete Automation Business Area. “Through our development of advanced mechatronics, AI, and vision systems, our robots are more accessible, more capable, more flexible, and more mobile than ever.”

“But increasingly, they must also work seamlessly together, with us, and each other to take on more tasks in more places,” he added. “This is why we are launching OmniCore, a new milestone in our 50-year history in robotics; a unique, single control architecture – one platform, and one language that integrates our complete range of leading hardware and software.”

Three out of four European companies struggle to find workers for jobs such as welding and fulfillment, noted Atiya. He added that more than 2.1 million U.S. manufacturing jobs will be unfilled by 2030, and businesses need supply chain resilience. In response, Atiya said, OmniCore will provide greater simplicity and flexibility to ABB’s customers.

ABB Robotics, which has offices in Zurich; Vasteras, Sweden; and Auburn Hills, Mich., noted that OmniCore is the product of more than $170 million in investment. The unit of ABB Group called it “a step change to a modular and futureproof control architecture that will enable the full integration of AI, sensor, cloud, and edge computing systems to create the most advanced and autonomous robotic applications.”

While ABB has offered OmniCore since 2018, its plan was always to make it its unified control platform, explained Marc Segura, division president of ABB Robotics. “Now we are in our pivotal moment where we are launching it to the cover almost our entire robotics portfolio,” he told The Robot Report.

Register now.

OmniCore offers speed and accuracy

ABB Robotics said OmniCore delivers robot path accuracy at a level of less than 0.6 mm, and it can control the motion of multiple robots running at speeds of up to 1,600 mm per second (3.5 mph). This builds on ABB’s experience with automotive manufacturing. It also opens opportunities for precision automation in areas such as arc welding, assembly of mobile phone displays, gluing, and laser cutting.

“Our automotive customers are extremely competent and helped push the boundaries of what is possible,” Segura said. “OmniCore also complies with and exceeds the most stringent cybersecurity standard and is future-proof for AI and digitalization.”

He claimed that the updated platform enables its robots to operate up to 25% faster and to consume up to 20% less energy compared with its previous controller. It is open to peripherals including sensors, as well as external devices such as dispensers or welding tools, for numerous processes. It also supports up to 100 safety configurations.

Platform covers hardware, software ecosystem

OmniCore is built on a scalable, modular control architecture that offers a wide array of functions, making it suitable for new industries embracing automation, such as biotechnology and construction, said ABB. It also includes more than 1,000 hardware and software features to help customers design, operate, maintain, and optimize operations.

OmniCore is the top level of a software stack that includes the RobotWare operating system and Robot Studio for simulation and design, said Segura. He cited software features such as OptiFact for managing data, Absolute Accuracy, and PickMaster Twin, as well as hardware options spanning from external axis and vision systems to fieldbuses.

“The OmniCore difference is its ability to manage motion, sensors, and application equipment in a single holistic unified system,” he said. “Our new, next-generation platform is more than a controller. It is the backbone of value creation, which includes a complete, integrated software ecosystem.”

“For example, OmniCore enables automotive manufacturers to increase production speed, offering tremendous competitive advantage, increasing press-tending production from 12 to 15 strokes per minute to produce 900 parts per hour,” Segura said. “Some of these applications are now available even as pre-integrated configurations, enabling our systems integrators to reduce commissioning times even further.”

“Software and AI are paramount for us at ABB,” Atiya said. “We have more than 100 projects ongoing to bring AI into our products and for our own productivity.”

He noted that AI enables inspection of welds 20 times faster than with humans, and up to 1,400 picks per hour with its robots. Atiya predicted that generative AI such as ChatGPT will broaden accessibility of robotics.

ABB says OmniCore offers seven benefits for robotics deployment and management. Source: ABB Robotics

ABB plans for compatibility across its robots

ABB said its history of robotics innovation began with “the world’s first microprocessor-controlled robot” in 1974. It launched the RobotStudio software in 1998 and acquired Sevensense in 2024 to bring industry-leading AI-based navigation technology to its autonomous mobile robots (AMRs) purchased with ASTI in 2021.

OmniCore replaces ABB Robotics’ IRC5 controller, which will be phased out in June 2026. The company plans to continue to support its customers with spare parts and services through the remaining lifetime of robots using it. Is new hardware needed to upgrade?

Existing users need only to make some minimal re-engineering for connectivity, wiring, and the customized user interface on the FlexPendant, replied Segura. No additional equipment or training is needed, but online and in-person training are available.

“We are still compliant with all the sensors used on IRC5 and have added more opportunities on the OmniCore platform,” Segura said. 

In addition to managing motion, sensors, and application equipment, OmniCore will be able to manage ABB’s collaborative robots, acknowledged Segura. “We also plan to run all our AMRs and mobile manipulators to run on OmniCore in the near future,” he said. 

After the “Fanta challenge” in 2009, which showed three robots working together, ABB demonstrated three robot arms moving around with champagne glasses to show off OmniCore’s precise motion control for production and safety purposes.

OmniCore is now available, and ABB is taking orders. The company is hosting a virtual conference for the new OmniCore platform at 10:00 CEST (4:00 a.m. EDT) on June 4, 2024. It will be available to those who register after the launch event.

The post ABB releases OmniCore platform for control across its robotics line appeared first on The Robot Report.

Mitsubishi Electric’s new RV-35 heavy payload industrial robot. | Source: Mitsubishi Electric

Mitsubishi Electric Automation launched a new robot series for applications that require heavier payloads and longer reach. The company says its new RV-35/50/80 FR series of industrial robots are designed for handling large workpieces and heavy objects to expand automation opportunities for OEMs and end-users. 

“The RV-35/50/80FR series is going to be a game changer for Mitsubishi Electric. These heavier-payload robots give us the ability to do applications that were previously inaccessible to us, such as end-of-line palletizing and machine tending for large parts,” Curtis Sylliaasen, product manager (robot) at Mitsubishi Electric Automation, said.

The RV-34/50/80 FR series has a maximum reach of 2100 mm (around 82.7 inches) and a maximum payload of 80 kg (around 176.4 lbs). The company says this makes the robots well suited for palletizing and machine tending applications.

Mitsubishi Electric says its industrial robots are equipped with class-leading speed and precision, allowing them to meet the demands of today’s manufacturing applications. The company designed this robot series to allow for an expanded work envelope and increased opportunity through its increased payload and reach compared to its prior series.

Register now.

RV-34/50/80 FR series is designed for seamless integration

The company says this new series of robots can connect to a variety of factory automation equipment. This allows users to integrate the robot’s functionality with IT systems. Mitsubishi also said the robots offer a range of safety functions, including position and speed monitoring. Additionally, users can pair with Mitsubishi Electric’s MELFA Smart Plus card for installation and programming.

Mitsubishi Electric said it has more than 100 years of experience in manufacturing and selling electrical and electronic equipment for factory automation, information processing and communications, space development and satellite communications, consumer electronics, energy, transportation, and building equipment. The company recorded a revenue of 5,257.9 billion yen ($34.8 billion U.S.) in the fiscal year ended March 31, 2024.

Yesterday, Mitsubishi announced it will be leading Realtime Robotics Series B round. The Tokyo-based company, which also participated in Realtime Robotics’ Series A round, will be adding a senior representative to Realtime’s board of directors. Mitsubishi said that it plans to “further integrate Realtime’s motion-planning technology into 3D simulators and other software to optimize manufacturing through the power of digital twins.”

The post Mitsubishi Electric unveils higher payload, longer reach robots appeared first on The Robot Report.

Comau is expanding from automotive manufacturing to logistics applications such as pick and place. Source: Comau

If change is constant in technology, even established industrial automation providers must adapt to keep up. Comau SpA recently said it is shifting from traditional robotics to software-driven systems and industry-agnostic technologies.

The company has been expanding from the automotive industry and systems integration to new markets including logistics and energy, noted Allesandro Piscioneri, global head of strategic marketing, advanced robotics, and digital segments at Comau.

“The transition has been happening from our traditional business of body in white to new batteries for mobility, including hydrogen cells and power for robots,” he told The Robot Report. “Our business is evenly divided between North America, Europe, and Asia.”

The Turin, Italy-based unit of Stellantis said it expects the market for automation to experience a 10% compound annual growth rate (CAGR) between 2022 and 2030, with an increase from 1.2 million industrial robots today to 2.6 million by 2029. Comau has 50 years of experience with manufacturers and employs more than 3,700 people in 13 countries.

The company also supplies collaborative robots, wearables, vision-based systems, and software. At Automate this month, Comau announced new products, including its S-Family welding and materials handling systems, the MI.RA/OnePicker system, and the MATE-XB and MATE-XT exoskeletons.

Register now.

Comau debuts S-Family robot arms

The new S-Family of small, six-axis robot arms can handle payloads up to 13 and 18 kg (28.6 and 39.6 lb.). They are designed with hollow wrists and protected cabling to avoid damage and the risk of contamination in sensitive environments such as in food and beverage, battery manufacturing, or electronics.

“We squeezed knowledge from internal and external customers to focus on high-performance, precise production,” said Piscioneri. “It’s also rated IP68 for water and dust resistance and can be mounted on the floor, wall, or ceiling.”

The S-Family is designed to be compact for tight spaces and includes integrated arc and gigabit dressings, according to Comau. The S-13 can reach up to 1,960 mm (77.1 in.), and the S-18 can reach up to 1,730 mm (68.1 in.).

Comau demonstrated welding with its S-Family robot at Automate. Source: Comau

Comau also shows picking, identification systems

Comau’s Machine Inspection Recognition Archetypes, or MI.RA/OnePicker line, is a hardware-agnostic machine vision product intended to ease robotic piece picking. It uses sensors and artificial intelligence to identify and pick random objects from bins without relying on CAD data or prior information about the items’ size, shape, color, or other characteristics.

MI.RA/OnePicker is “adaptable to any brand of commercial robot, customized bin, or customized gripper,” said Comau. This makes it suitable for pick-and-place, kitting, sorting, e-commerce, and other warehouse applications, it said.

Customers can use virtual simulation tools and predictive algorithms for optimal path management and collision-free trajectories, Comau said. The software comes with Comau’s Racer5 five-axis cobot, which can switch from collaborative mode to industrial mode to work at full speed without the need for safety cages, explained Piscioneri. A safety assessment is still necessary for the payload and application.

Exoskeletons and collaboration to improve accessibility

Comau displayed non-powered exoskeletons intended to help workers with repetitive lifting and overhead tasks, addressing widespread labor shortages. The MATE-XB is designed to support the lower back, and the MATE-XT is designed for the upper back and shoulders.

MATE-XT upper-body exoskeleton. Source: Comau

In addition, Comau showcased in Chicago its partnership with Rockwell Automation in a demonstration cell using its Racer-3 robot and Rockwell’s Unified Robot Control (URC) library and Emulate3D for palletizing, color sorting, and depalletizing. All of Comau’s robots can be controlled via PCs with its Open Controller software.

Another collaboration is with Intrinsic, whose Flowstate development platform can “make the next generation of robotics more accessible to all,” Comau said. In March, Intrinsic co-founded the Open Source Robotics Alliance (OSRA). It had acquired Robot Operating System maker Open Source Robotics Corp. in 2022.

Speaking of accessibility, Comau’s e.DO robot was originally intended to help STEM (science, technology, engineering, and mathematics) students, but industrial customers have found it useful for training and building complete systems, Piscioneri said.

Register now.

The post Comau changes with robotics market, adds focus on software and new applications appeared first on The Robot Report.

Organization: Mecademic
Country: Canada
Website: https://www.mecademic.com/
Year Founded: 2013
Number of Employees: 11-50
Innovation Class: Technology, Product & Services

Editor’s note: The 2024 RBR50 Robotics Innovation Awards were announced on April 9. The RBR50 has been around for the past 12 years, and the inaugural RBR50 Gala was held during the Robotics Summit & Expo in Boston. The Robot Report will be highlighting each RBR50 winner throughout the year.

Mecademic launched its micro-SCARA robot in 2023, offering high speed and repeatability in a small and flexible format. The new tabletop SCARA follows the company‘s tradition of developing high-quality, high-precision, smaller-footprint robots for assembly applications in electronics and healthcare. Mecademic has carved out a niche in the industrial robotics market with two of the tiniest yet fully capable robots on the market today.

The new MCS500 SCARA robot boasts repeatability of 0.005 mm. It features an embedded controller in the base of the robot and eight digital I/O and various communication ports, simplifying integration possibilities. The robot can be programmed with Mecademic’s software or integrated with any other robot control software. The company’s robot arms include external 24/36V power supplies and are equipped with embedded safety modules, E-Stops and a safety I/O interface.

This industrial robotic innovation fills a crucial gap in the automation market amidst the growing trend towards miniaturization, and will create a strong demand across various industries where space is a premium. Mecademic claimed that the MCS500 is the world’s most compact and most precise SCARA robot with a reach of 225 mm (8.8 in.) and a maximum payload of 1 kg (2.2 lb.).

With fast cycle times and mounting flexibility, the MCS500 is suitable for a variety of applications. It can be mounted on a table or hung from an overhead mounting platform, depending on the application requirements. This robust robot is unique in that it offers a combination of simplicity, precision, and high performance in a small package.

Explore the RBR50 Robotics Innovation Awards 2024.

RBR50 Robotics Innovation Awards 2024

The post RBR50 Spotlight: Mecademic accelerates microautomation with SCARA robot appeared first on The Robot Report.

Realtime is working with Mitsubishi Electric to develop its motion planning software. Source: Realtime Robotics

Manufacturing can benefit from increasingly intelligent robots as much as any other industry. Realtime Robotics today announced that it has secured a strategic investment from Mitsubishi Electric Corp., leading its recently opened Series B round. The company said it plans to use the funding to refine and scale its robot workcell and runtime systems, which will help engineers reduce costs and increase productivity.

“For years, industrial robot programming has remained a rigid, costly and labor-intensive process,” stated Peter Howard, CEO of Realtime Robotics. “Realtime is helping manufacturers realize the next wave of efficiency improvements necessary to get the most out of their new and existing automation applications.”

“Our optimization and runtime technologies constitute a powerful artificial intelligence that operates much like the human brain’s motor cortex, efficiently managing multiple actions at the same time,” he added. “Think of several cooks in a crowded kitchen being able to seamlessly work around each other to produce meals without error or collision. That’s the power of our technology.”

“We’re planning on using the funds to further scale and refine our optimization and runtime solutions,” Howard told The Robot Report.

Realtime Robotics refines motion control

Realtime Robotics said it is a leader in automatic, collision-free motion planning for industrial robots. In iterative design stages, the optimization software rapidly generates and evaluates hundreds of thousands of possible solutions.

“Our technologies reduce costs and improve productivity across the lifecycle of robotic workcells for both design engineers and manufacturers,” Howard explained. “For example, at the design stage, our optimization solution quickly finds the lowest cycle time on highly complex multi-robot cells with tight space such as spot welding for automotive framing.”

The Boston-based company claimed that its systems expand the potential of automation, empowering multiple robots to work closely together in collaborative workspaces. It added that runtime control further simplifies deployment and production, enabling multiple robots to work closer together, while simultaneously reacting to dynamic changes.

“In runtime, our auto-homing and dynamic obstacle avoidance unleashes the power of multiple robots in high-mix, low-volume or unstructured applications like machine tending, depalletizing, bin picking, and container unloading,” said Howard.

When the workcell needs to be retooled, the complex robot control can be reprogrammed for optimal cycle time from the first iteration, said Realtime Robotics. The company said its interfaces with leading simulation software brands and industry-standard controllers help customers and partners access its systems through their preferred methods.

Realtime’s customers include automotive manufacturers BMW and Volkswagen Commercial Vehicles, as well as integrators Valiant TMS and Schaeffler Group. They have reported improved cycle times, reduced downtime, and increased throughput as a result of working with Realtime.

Mitsubishi Electric expects efficiencies from automation

Mitsubishi Electric, which also participated in Realtime Robotics’ Series A round, will be adding a senior representative to Realtime’s board of directors. The Tokyo-based company said that it plans to “further integrate integrate Realtime’s motion-planning technology into 3D simulators and other software to optimize manufacturing through the power of digital twins.”

Later, Mitsubishi Electric said it expects to incorporate Realtime’s technology into factory automation (FA) control system devices, such as programmable logic controllers (PLCs), servo motors, and computer numerical controllers (CNCs). The manufacturer said it expects to eliminate production interruptions by expanding automation capabilities, streamlining plant operations for improved efficiency, and quickly responding to unexpected events.

“We’re excited to continue working directly with Mitsubishi on ways that they can utilize our technology throughout various aspects of their operations,” said Howard. “This will further enable their transformation into a circular digital-engineering company.”

Mitsubishi Electric said it has more than 100 years of experience in manufacturing and selling electrical and electronic equipment for factory automation, information processing and communications, space development and satellite communications, consumer electronics, energy, transportation, and building equipment. The company recorded a revenue of 5,257.9 billion yen ($34.8 billion U.S.) in the fiscal year ended March 31, 2024.

Register now.

Realtime fundraising, AI development continue

While the companies didn’t specify the amount of the investment, Realtime Robotics said Mitsubishi Electric’s expertise will help guide its development of automation for manufacturing.

“Mitsubishi has been a valued partner since our Series A was first announced, and we’ve worked closely with them on various projects,” said Howard. “Our technology has of course benefited from what we’ve learned as a part of this partnership — and we’re really excited to take this further.”

Realtime Robotics is also communicating with other investors, which Howard said he hopes to announce in the coming months. Ongoing improvements in artificial intelligence will also help robot control, he said.

“One thing I’ve learned from years in this industry is that there’s always room for improvement,” said Howard. “As simulation improves and AI matures, there will be an opportunity to become even more efficient in the ways a manufacturer’s process is analyzed and optimized.”

“Digital twins will become more exact, and AI can make better decisions faster than humans, as long as the data remains accurate,” he said. “Right now, there are a great deal of ways our programming and optimization solutions can advance the industry, but we’re keeping our eyes on how to make them even stronger as technology advances.”

The post Realtime Robotics gets Series B funding from Mitsubishi Electric appeared first on The Robot Report.

America Quartz Technology (AQT) specializes in the manufacturing and processing of formed quartz products for the electronics and semiconductor industries at its plant in Hue, Vietnam. The production of AQT’s products demands the highest level of meticulousness and accuracy.

Challenges

Previously, components were processed manually, with workers performing high temperature heating processes. This dangerous and repetitive work meant that staff turnover was high, with an increased risk of accidents. There was also the risk of errors that could lead to serious production losses.

To solve these challenges, AQT decided it needed robots that would avoid labor shortages, reduce risk and improve productivity.

Solution

Having used ABB robots at its plants in the U.S., AQT approached ABB for a solution for its Hue plant. The result is a robot production cell consisting of an ABB IRB4600 industrial robot, an IRB2600 industrial robot and a moulding machine.

The ABB IRB4600 picks up the quartz workpiece and places it into position for the heat treatment process. Following this, the IRB2600 robot heats the workpiece evenly. Then, the cylinder mechanism sucks the heated quartz plate into the mould and shapes it. After 30 seconds, the vacuum valve shuts off, and the IRB 4600 robot removes the product and repeats the cycle.

Results

Since the introduction of the robots, plant efficiency and performance has been significantly improved, with five times fewer defective products due to production errors.

“Using the solution provided by ABB, our products are now consistently completed to the highest quality, with less manual intervention required and a reduction in errors. Conditions have also improved for workers as all of the dangerous and repetitive work is now taken care of by the robots,” said Tran Phuoc Thanh Vu, factory manager, America Quartz Technology.

Another improvement has been a dramatic reduction in production cycle times. With the robotic process, production time has been reduced from 25 to just five minutes, with a current average output of 100 pieces a day, a four-fold increase on the previous manually-based production process.

“The solution brings enormous value to the plant – it improves production capacity, ensures on time delivery of customer orders and offers high stability during the production process,“ said Vu. “We always aim to have a modern and professional factory, using the latest techniques and technologies to achieve a lean production process and improve productivity. Our good experience with ABB robots means that we plan to invest in several robot stations for the plant in the coming year.”

The post Quartz plant cuts cycle time 80% with ABB robots appeared first on The Robot Report.

The Robot Report recently spoke with Ph.D. student Cheng Chi about his research at Stanford University and recent publications about using diffusion AI models for robotics applications. He also discussed the recent universal manipulation interface, or UMI gripper, project, which demonstrates the capabilities of diffusion model robotics.

The UMI gripper was part of his Ph.D. thesis work, and he has open-sourced the gripper design and all of the code so that others can continue to help evolve the AI diffusion policy work.

AI innovation accelerates

How did you get your start in robotics?

Stanford researcher Cheng Chi. | Credit: Huy Ha

I worked in the robotics industry for a while, starting at the autonomous vehicle company Nuro, where I was doing localization and mapping.

And then I applied for my Ph.D. program and ended up with my advisor Shuran Song. We were both at Columbia University when I started my Ph.D., and then last year, she moved to Stanford to become full-time faculty, and I moved [to Stanford] with her.

For my Ph.D. research, I started as a classical robotics researcher, and I started working with machine learning, specifically for perception. Then in early 2022, diffusion models started to work for image generation, that’s when DALL-E 2 came out, and that’s also when Stable Diffusion came out.

I realized the specific ways which diffusion models could be formulated to solve a couple of really big problems for robotics, in terms of end-to-end learning and in the actual representation for robotics.

So, I wrote one of the first papers that brought the diffusion model into robotics, which is called diffusion policy. That’s my paper for my previous project before the UMI project. And I think that’s the foundation of why the UMI gripper works. There’s a paradigm shift happening, my project was one of them, but there are also other robotics research projects that are also starting to work.

A lot has changed in the past few years. Is artificial intelligence innovation is accelerating?

Yes, exactly. I experienced it firsthand in academia. Imitation learning was the dumbest thing possible you could do for machine learning with robotics. It’s like, you teleoperate the robot to collect data, the data is paired with images and the corresponding actions.

In class, we’re taught that people proved that in this paradigm of imitation learning or behavior, cloning doesn’t work. People proved that errors grow exponentially. And that’s why you need reinforcement learning and all the other methods that can address these limitations.

But fortunately, I wasn’t paying too much attention in class. So I just went to the lab and tried it, and it worked surprisingly well. I wrote the code, I applied the diffusion model to this and for my first task; it just worked. I said, “That’s too easy. That’s not worth a paper.”

I kept adding more tasks like online benchmarks, trying to break the algorithm so that I could find a smart angle that I could improve on this dumb idea that would give me a paper, but I just kept adding more and more things, and it just refused to break.

So there are simulation benchmarks online. I used four different benchmarks and just tried to find an angle to break it so that I could write a better paper, but it just didn’t break. Our baseline performance was 50% to 60%. And after applying the diffusion model to that, it was like 95%. So it was a jump in terms of these. And that’s the moment I realized, maybe there’s something big happening here.

The first diffusion policy research at Columbia was to push a T into position on a table. | Credit: Cheng Chi

How did those findings lead to published research?

That summer, I interned at Toyota Research Institute, and that’s where I started doing real-world experiments using a UR5 [cobot] to push a block into a location. It turned out that this worked really well on the first try.

Normally, you need a lot of tuning to get something to work. But this was different. When I tried to perturb the system, it just kept pushing it back to its original place.

And so that paper got published, and I think that’s my proudest work, I made the paper open-source, and I open-sourced all the code because the results were so good, I was worried that people were not going to believe it. As it turned out, it’s not a coincidence, and other people can reproduce my results and also get very good performance.

I realized that now there’s a paradigm shift. Before [this UMI Gripper research], I needed to engineer a separate perception system, planning system, and then a control system. But now I can combine all of them with a single neural network.

The most important thing is that it’s agnostic to tasks. With the same robot, I can just collect a different data set and train a model with a different data set, and it will just do the different tasks.

Obviously, collecting the data set part is painful, as I need to do it 100 to 300 times for one environment to get it to work. But in actuality, it’s maybe one afternoon’s worth of work. Compared to tuning a sim-to-real transfer algorithm takes me a few months, so this is a big improvement.

Register now.

UMI Gripper training ‘all about the data’

When you’re training the system for the UMI Gripper, you’re just using the vision feedback and nothing else?

Just the cameras and the end effector pose of the robot — that’s it. We had two cameras: one side camera that was mounted onto the table, and the other one on the wrist.

That was the original algorithm at the time, and I could change to another task and use the same algorithm, and it would just work. This was a big, big difference. Previously, we could only afford one or two tasks per paper because it was so time-consuming to set up a new task.

But with this paradigm, I can pump out a new task in a few days. It’s a really big difference. That’s also the moment I realized that the key trend is that it’s all about data now. I realized after training more tasks, that my code hadn’t been changed for a few months.

The only thing that changed was the data, and whenever the robot doesn’t work, it’s not the code, it’s the data. So when I just add more data, it works better.

And that prompted me to think, that we are into this paradigm of other AI fields as well. For example, large language models and vision models started with a small data regime in 2015, but now with a huge amount of internet data, it works like magic.

The algorithm doesn’t change that much. The only thing that changed is the scale of training, and maybe the size of the models, and makes me feel like maybe robotics is about to enter that that regime soon.

Two UR cobots equipped with UMI grippers demonstrate the folding of a shirt. | Credit: Cheng Chi video

Can these different AI models be stacked like Lego building blocks to build more sophisticated systems?

I believe in big models, but I think they might not be the same thing as you imagine, like Lego blocks. I suspect that the way you build AI for robotics will be that you take whatever tasks you want to do, you collect a whole bunch of data for the task, run that through a model, and then you get something you can use.

If you have a whole bunch of these different types of data sets, you can combine them, to train an even bigger model. You can call that a foundation model, and you can adapt it to whatever use case. You’re using data, not building blocks, and not code. That’s my expectation of how this will evolve.

But simultaneously, there’s a there’s a problem here. I think the robotics industry was tailored toward the assumption that robots are precise, repeatable, and predictable. But they’re not adaptable. So the entire robotics industry is geared towards vertical end-use cases optimized for these properties.

Whereas robots powered by AI will have different sets of properties, and they won’t be good at being precise. They won’t be good at being reliable, they won’t be good at being repeatable. But they will be good at generalizing to unseen environments. So you need to find specific use cases where it’s okay if you fail maybe 0.1% of the time.

Safety versus generalization

Robots in industry must be safe 100% of the time. What do you think the solution is to this requirement?

I think if you want to deploy robots in use cases where safety is critical, you either need to have a classical system or a shell that protects the AI system so that it guarantees that when something bad happens, at least there’s a worst-case scenario to make sure that something bad doesn’t actually happen.

Or you design the hardware such that the hardware is [inherently] safe. Hardware is simple. Industrial robots for example don’t rely that much on perception. They have expensive motors, gearboxes, and harmonic drives to make a really precise and very stiff mechanism.

When you have a robot with a camera, it is very easy to implement vision servoing and make adjustments for imprecise robots. So robots don’t have to be precise anymore. Compliance can be built into the robot mechanism itself, and this can make it safer. But all of this depends on finding the verticals and use cases where these properties are acceptable.

The post Stanford researcher discusses UMI gripper and diffusion AI models appeared first on The Robot Report.