Goodbye to the hydraulic version of Atlas and hello to the electric model designed for commercialization. That’s the message from Boston Dynamics Inc., which yesterday retired the older version of its humanoid robot after 15 years of development and today showed a preview of its successor.

“The next generation of the Atlas program builds on decades of research and furthers our commitment to delivering the most capable, useful mobile robots solving the toughest challenges in the industry today: with Spot, with Stretch, and now with Atlas,” said the company in a blog post. Spot is a quadruped used in facilities inspection and other tasks, and Stretch is designed to unload trucks.

Boston Dynamics began with humanoids by sawing one of its pneumatically powered quadrupeds in half back in 2009. By 2016, the Waltham, Mass.-based company showed that its robot could walk, open a door, and maintain its balance while being shoved by a person holding a hockey stick, all without a tether.

Roboticists continued to improve Atlas, giving it a smaller form factor and more sensors, training its artificial intelligence, and enabling it to do increasingly impressive feats. They ranged from parkour and dancing to taking tools through a mock construction site.

In fact, it was that demonstration of Atlas manipulating a plank, picking up a bag of tools, and taking it to a worker that earned Boston Dynamics an RBR50 Robotics Innovation Award. The company will be exhibiting at the RBR50 Showcase at the Robotics Summit & Expo on May 1 and 2.

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

Boston Dynamics evolves with the times

As capable as the YouTube darling was, the older version of Atlas still had limitations, both in range of motion and in terms of size and power usage. Boston Dynamics noted that it designed its legged robots to operate in unstructured environments, and it acknowledged that Atlas was initially a research and development project rather than a commercial product.

In the meantime, the company itself changed owners, from Google in 2013 to SoftBank in 2017 and most recently to Hyundai in 2020. Along with those changes came an increasing focus on robots such as Spot and Stretch serving industrial needs. To continue pure research, Hyundai founded the Boston Dynamics AI Institute in 2022.

“The AI Institute recently launched a new version of Spot with an API [application programming interface] designed for researchers,” said Robert Playter, CEO of Boston Dynamics. “We’re talking about how to jointly solve some big challenges — the diversity of manipulation tasks we need to do with this robot [Atlas] is huge, and AI is essential to enabling that generality.”

Playter told The Robot Report that Boston Dynamics needs results within two to three years, while the AI Institute has more of a five-year timeframe.

Robot lessons apply to fleets, new Atlas

“It takes a solid year from a clean sheet to a new robot,” said Playter. “We wanted to know that we could solve essential dexterous manipulation problems before releasing the product.”

Boston Dynamics learned numerous lessons from commercializing Spot and Stretch, he said. It has improved control policies, upgraded actuation, and minimized joint complexity. The new Atlas has three-fingered grippers.

The Orbit fleet management software, which initially applies to indoor deployments of Spot, could also help supervise Stretch and Atlas.

Atlas gets ready for mobile manipulation in industrial settings. Source: Boston Dynamics

“Everything we understood, from the time of launching Spot as a prototype to it being a reliable product deployed in fleets, is going into the new Atlas,” Playter said. “We’re confident AI and Orbit will help enhance behaviors. For instance, by minimizing slipping on surfaces at Anheuser-Busch, we proved that we can develop algorithms and make it reliable.”

“Now, 1,500 robots in our fleet have them running,” he added. “It’s essential for customers like Purina to monitor and manage fleets as a vehicle for collecting data. As we develop and download new capabilities, Orbit becomes a hub for an ecosystem of different robots.”

Safety and autonomy are basic building blocks

Boston Dynamics has considered safe collaboration in its development of the new Atlas. ASTM International is developing safety standards for legged robots.

“We recognized early on that Atlas is going to work in spaces that have people in them,” said Playter. “This sets the bar much higher than lidar with AMRs [autonomous mobile robots].”

“We started thinking about functionally safe 3D vision,” he recalled. “We started with Stretch inside a container, but ultimately, we want it going everywhere in a warehouse. Advanced, functionally safe, remote vision and onboard systems are essential to solving safety.”

While Spot and Atlas are often teleoperated, Playter said this is a necessary step toward greater levels of autonomy.

“Making the robots knowledgeable about different types of objects and how to grasp them, teleoperation is just a tool for providing examples and data to the robot,” he explained. “It’s not a useful way of building intuition, but it’s easier if you can operate robots at a higher and higher level. Like you don’t need to tell Spot where to plant its feet, you don’t want to tell Atlas where to grasp.”

In the new video below, the previous version of Atlas handles automotive parts and real products weighing up to 25 lb. (11.3 kg).

Atlas ready for rivals in the humanoid race

Over the past two years, the number of humanoid robots in development has rapidly grown. It now includes Agility Robotics‘ Digit, Tesla’s Optimus, and Figure AI‘s Figure 01. In the two past weeks alone, Rainbow Robotics, Sanctuary AI, and Mentee Robotics have all made announcements.

Investment has also been flowing to humanoid companies, with 1X Technologies raising $100 million in January, Figure AI raising $675 million in February, and Accenture investing in Sanctuary AI in March.

Humanoid robots have advanced in parallel with generative AI, and Playter said he welcomes the competition.

“There were three seminal events: Boston Dynamics got acquired for $1 billion, interest in Tesla’s robot validated what we’ve done for a long time, and the emergence of new AI holds the promise of generalization of tasks,” he said. “They’ve inspired lots of new players, but having new tech isn’t all you need to have a commercial product. You need to focus on a use case, build a reliable machine, and manufacture it in a way to build a business. We want to avoid a ‘humanoid winter,’ so rollouts have to be real.”

Playter added that practical design and proper implementation of AI will help differentiate robots rather than focusing on making them more human-like. The new version of Atlas demonstrated that point in how it stood up in the video at the top of this article.

“It’s not talking to a robot that moves the needle, but whether you can build a robot that eventually does 500 tasks,” he said. “Anthropomorphism blows things out of perspective. We did not want a human-shaped head for Atlas. We want people to remember it’s a machine and that it can move in ways humans can’t.”

The financial stability of the businesses involved will also be relevant for commercial success, said Playter. 

“It takes sustained investment; these are expensive products to launch,” he noted. “Having products already out helps build momentum.”

Atlas is humanoid — to a point. Source: Boston Dynamics

When will we see the new robot in the wild?

Boston Dynamics will begin testing the all-electric version of Atlas with parent company Hyundai and select partners next year, said Playter.

“We’re beginning in their factory,” he told The Robot Report. “In addition to the target application of a lot of parts movement — a special kind of logistics in automotive production — I think that will evolve as the dexterity of the robots improves over time.”

“We see robots in the workplace as an evolution, a continuum from Spot to Atlas,” asserted Playter. “Each product in the series informs the launch of the next.”

“Industries will have to figure out how to adapt and incorporate humanoids into their facilities,” he said. “We’ll actually see robots in the wild in factories beginning next year. We want a diversity of tasks.”

The post Boston Dynamics debuts electric version of Atlas humanoid robot appeared first on The Robot Report.

Here are the top 10 most popular stories on The Robot Report this past month. Subscribe to The Robot Report Newsletter or listen to The Robot Report Podcast to stay updated on the latest technology developments.

10. Robotics Engineering Career Fair to connect candidates, employers at Robotics Summit

The career fair will draw from the general robotics and artificial intelligence community, as well as from attendees at the Robotics Summit & Expo. Past co-located career fairs have drawn more than 800 candidates, and MassRobotics said it expects even more people at the Boston Convention and Exhibition Center this year. Read More

9. SMC adds grippers for cobots from Universal Robots

SMC recently introduced a series of electric grippers designed to be used with collaborative robot arms from Universal Robots. Available in basic and longitudinal types, SMC said the LEHR series can be adapted to different industrial environments like narrow spaces. Read More

8. Anyware Robotics announces new add-on for Pixmo unloading robots

Anyware Robotics announced in March 2024 an add-on for its Pixmo robot for truck and container unloading. The patent-pending accessory includes a vertical lift with a conveyor belt that is attached to Pixmo between the robot and the boxes to be unloaded. Read More

7. Accenture invests in humanoid maker Sanctuary AI in March 2024

In its Technology Vision 2024 report, Accenture said 95% of the executives it surveyed agreed that “making technology more human will massively expand the opportunities of every industry.” Well, Accenture put its money where its mouth is. Accenture Ventures announced a strategic investment in Sanctuary AI, one of the companies developing humanoid robots. Read More

6. Cambrian Robotics obtains seed funding to provide vision for complex tasks

Machine vision startup Cambrian Robotics Ltd. has raised $3.5 million in seed+ funding. The company said it plans to use the investment to continue developing its AI platform to enable robot arms “to surpass human capabilities in complex vision-based tasks across a variety of industries.” Read More

5. Mobile Industrial Robots launches MiR1200 autonomous pallet jack

Autonomous mobile robots (AMRs) are among the systems benefitting from the latest advances in AI. Mobile Industrial Robots at LogiMAT in March 2024 launched the MiR1200 Pallet Jack, which it said uses 3D vision and AI to identify pallets for pickup and delivery “with unprecedented precision.” Read More

4. Reshape Automation aims to reduce barriers of robotics adoption

Companies in North America bought 31,159 robots in 2023. That’s a 30% decrease from 2022. And that’s not sitting well with robotics industry veteran Juan Aparicio. After working at Siemens for a decade and stops at Ready Robotics and Rapid Robotics, Aparicio hopes his new startup Reshape Automation can chip away at this problem. Read More

3. Mercedes-Benz testing Apollo humanoid

Apptronik announced that leading automotive brand Mercedes-Benz is testing its Apollo humanoid robot. As part of the agreement, Apptronik and Mercedes-Benz will collaborate on identifying applications for Apollo in automotive settings. Read More

2. NVIDIA announces new robotics products at GTC 2024

The NVIDIA GTC 2024 keynote kicked off like a rock concert in San Jose, Calif. More than 15,000 attendees filled the SAP Arena in anticipation of CEO Jensen Huang’s annual presentation of the latest product news from NVIDIA. He discussed the new Blackwell platform, improvements in simulation and AI, and all the humanoid robot developers using the company’s technology. Read More

1. Schneider Electric unveils new Lexium cobots at MODEX 2024

In Atlanta, Schneider Electric announced the release of two new collaborative robots: the Lexium RL 3 and RL 12, as well as the Lexium RL 18 model coming later this year. From single-axis machines to high-performance, multi-axis cobots, the Lexium line enables high-speed motion and control of up to 130 axes from one processor, said the company. It added that this enables precise positioning to help solve manufacturer production, flexibility, and sustainability challenges. Read More

The post Top 10 robotics news stories of March 2024 appeared first on The Robot Report.

Glacier’s recycling sorting robot is able to sort up 45 items a minute. | Source: Glacier

Amazon.com Inc.’s Climate Pledge Fund recently invested in Glacier, an artificial intelligence and robotics company that aims to help the recycling industry work toward a world without waste. The investment firm said the funding is part of its ongoing commitment to support entrepreneurs and female-led companies in climate tech.

“Nearly 70 million tons of recycling are processed annually in the U.S. alone. This is already an immense undertaking, but we can recover so much more material by building accessible automation processes and then scaling it across our country’s recycling infrastructure,” Areeb Malik, co-founder of Glacier, said in a release. “That’s what Glacier is doing.”

The San Francisco-based company uses AI-powered robots to automate the sorting of recyclables. It collects real-time data on recycling streams fore recycling companies and consumer brands.

Glacier has also announced that it will be collaborating with Amazon to enhance traceability and recovery processes for recyclables. Its latest funding round, totaling $7.7 million, also included participation from New Enterprise Associates (NEA), AlleyCorp, Overture Climate VC, and VSC Ventures.

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

Glacier aims to help recycling industry reach its full potential

Malik and Rebecca Hu said they co-founded Glacier to make a positive impact on the climate crisis. Despite the potential of recycling as a climate solution, today only 21% of residential recyclables in the U.S. are actually recycled. This is often due to a lack of recycling infrastructure, they said.

“After researching a variety of climate solutions, we discovered that applying novel advances in AI and robotic automation to help the recycling industry run more efficiently is a powerful way to reduce waste, which has a direct link to reducing carbon emissions,” stated Hu.

Glacier said its robots can improve sorting and recycling rates to help prevent valuable materials, like metals and plastics, from ending up in landfills and oceans. The company’s approach to recycling innovation combines two core technologies.

The first is Glacier’s proprietary AI model, which is capable of identifying more than 30 categories of recyclable materials in real time. This includes things as broad as PET plastic and as narrow as a toothpaste tube. The company said the combination of this AI model with its custom-designed robot delivers consistent recyclable sorting power with minimal implementation costs.

Glacier added that its potential impact on the circular economy extends beyond its sorting robot. Its software and AI are generating a recycling data set to help recycling facilities and brands make better-informed decisions.

“We’re constantly looking for ways to improve recycling, and developing robots is just the first step,” said Malik.

“Our recycling AI is a powerful tool for everyone in the circular economy, and it couldn’t come at a more important time,” said Hu. “As we see mounting legislative, economic, and social pressure to recycle better, brands are using our data to measure and improve how their packaging is being recycled, while recycling facilities are using our data to improve their operations and rescue more recyclables from landfill. We’re thrilled to be collaborating with a circular-economy leader like Amazon so that we can accelerate our mission to end waste.”

Keeping plastic out of landfills and oceans

Glacier claimed that just one of its robots can prevent over 10 million items per year from ending up in landfills. In the near term, the company said its technology can help improve the quality of recycling content. This way, more post-consumer material is available for use in new packaging.

In the longer term, Glacier’s founders said they hope to enable recycling for more types of packaging and materials that are not currently recycled. This is why Amazon is collaborating with Glacier to pilot a sortation project for novel biomaterials.

Amazon said its vision is to reduce plastic use and shift toward materials that are bio-based, as well as those that are biodegradable and compostable. This includes testing new biomaterials for applications without other sustainable solutions, such as some flexible plastics, and then recycling them.

The post Recycling automation startup Glacier brings in $7.7M appeared first on The Robot Report.

SMC recently introduced a series of electric grippers designed to be used with collaborative robot arms (cobots) from Universal Robots (UR). Available in basic and longitudinal types, SMC said the LEHR series can be adapted to different industrial environments like narrow spaces.

The new series offers gripping forces between 60 to 140 N and have M8, 8-pin plug-and-play connectors. SMC said it can be operated with the connection of 1 electrical wire. The grippers feature a battery-less absolute encoder and a motor type rated 24VDC.

SMC said that by using the dedicated software certified for Universal Robots, URCap, the teach pendant can conduct various operations of SMC grippers intuitively, allowing for sensor signals to be easily incorporated. SMC also said all that’s needed to install the software is to save a copy of the URCap software to a USB flash drive and insert it into the cobot’s teach pendant.

SMC will be exhibiting in booth 301 at the Robotics Summit & Expo, which takes place May 1-2 in Boston. Produced by The Robot Report and parent company WTWH Media, the Robotics Summit will have 5,000 attendees from the commercial robotics development ecosystem and 200+ exhibitors. The event will feature 75-plus speakers in 45 technical sessions, including keynotes from Agility Robotics, Amazon, Disney, Medtronic and Teradyne, which owns UR. Register by March 8 to save 25% on full access passes to the Robotics Summit & Expo.

SMC’s new LEHR grippers are design for Universal Robots’ collaborative robot arms. | Credit: SMC

SMC said the new LEHR series has a durable and flexible design with IP20-rated housing with a rounded protective cover and simplified tool changing. SMC added that the durable design makes the gripper resist vibration and impacts and is also able to work in relatively harsh environments.

UR is the world’s leading developer of cobot arms. The Denmark-based company generated $304 million in revenue in 2023. While its sales were down 7% year-over-year from the record $326 million generated in 2022, the cobot maker ended the year on a high note. The fourth quarter of 2023 was UR’s largest revenue quarter ever. This represented 21% growth from Q4 2022 and 47% growth from Q3 2023, which the company attributed to demand for its the UR20 and UR30 cobots.

Ujjwal Kumar, who was named president of Teradyne’s robotics group in mid-2023, will deliver a keynote at the Robotics Summit. Kumar has a 25-year career spanning multiple industries and major multi-national corporations, including General Motors, General Electric, and Honeywell. He has a Master of Business Administration from the University of Michigan’s Ross School of Business, a Master of Science in Mechanical Engineering from the University of Maryland and Bachelor of Science in Mechanical Engineering from the Indian Institute of Technology.

The conversation with Kumar will discuss ways to drive the transformation of the robotics industry. He will share some lessons he has learned and how they can be applied to accelerate the transformation of industry with robotics.

The post SMC adds grippers for cobots from Universal Robots appeared first on The Robot Report.

Bosch Rexroth’s Smart Flex Effector its in between the robot and its gripper to make it more flexible and precise. | Source: Bosch Rexroth

In 2022, there were 3.9 million operational robots in the world, an all-time high, according to the International Federation of Robotics. Bosch Rexroth said it expects that number to grow in the coming years as new innovations make it possible for robots to do more tasks more successfully. 

The Buchanan, Mich.-based company creates intelligent systems for factory automation, mobile and machining applications, and engineering. It said it hopes to help the industry keep up with rising demand by making robots more flexible and easier to use. 

Brad Klippstein, a product manager at Bosch, gave insight into the company’s Smart Flex Effector. This end effector, which sits between the robot and its gripper, gives a robot tactile feedback. This allows a robot to know when it’s touching an object and how to get into position to best pick that object. 

“We’ve had vision systems for robotics for a number of years,” Klippstein told The Robot Report. “Now, we’re adding tactile sensing to that process to increase accuracy, increase repeatability and process transparency, and do some of these operations that were incredibly difficult or impossible before.”

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

Bosch Rexroth makes industrial arms more adaptable

Robots, particularly large industrial robots, can be inflexible and difficult to train on new tasks, noted Bosch Rexroth. Robots used in picking processes typically have “teach positions,” which are ideal positions for the robot and the item it’s picking to be in.

Industrial robots will typically pick the same item over and over again, so when the item or the robot is slightly off position, the robot may struggle to complete the task. 

“Lots of things can happen to make that teach position be a little bit misaligned or off position,” said Klippstein. “The Smart Flex Effector gives you the ability to feel the environment.”

“So now I don’t have to know the exact position of an object or location,” he added. “I can get somewhat close and then have the Smart Flex Effector tell me exactly where to go based on tactile sensing or touch.” 

While vision systems can provide important feedback for robots, tactile feedback adds a new level of flexibility to robots, asserted Bosch Rexroth.

“As soon as the robot touches the workpiece you get that feeling, that feedback. And that can tell the robot that it’s in position,” explained Klippstein. “For high picking and placing operations, we don’t need to be exact. With all of these teach positions we can get somewhat close and the smart flex effector adds flexibility to that process so that you don’t have to reteach that position each and every time.” 

“So if we know that the position is off half a millimeter in the X direction, three-quarters of a millimeter in the Y direction, and 2.5 degrees about the X-Y axis, and we know all of those dimensions immediately, we can send that information back to the robot,” he said. “Then it knows the exact position to correct.”

Designing a tool that can work with any robot, in various use cases

The Smart Flex Effector can work with any robot or gripper, according to Bosch Rexroth. The system simply uses an adapter plate that allows end-users to connect any equipment. It’s also designed to benefit robots in a variety of use cases, not just picking. 

Klippstein said Bosch’s end effector is used in assembly operations, the electronics industry, machine tending, welding, and various other industrial applications. It wasn’t easy for the company’s team to create something that can work in so many scenarios. 

“We needed to make something that was compact, durable, and that, of course, performed this operation by taking in all of this data,” said Klippstein. “And by the way, this data is six degrees of freedom, or six degrees of rotation about the robots. We needed to be able to provide compensation for each one of those six axes in almost real-time, because we don’t want to slow down operation.”

“So we needed to quickly determine the offset, the positional deviation from where that robot currently is in all six degrees, and then quickly send that result back to the robot control so that it can make a compensation move,” he said.

“The engineering challenge was we needed to obtain this information,” Klippstein said. “So how do we even get that?”

“We need to be able to process that and determine the position, not just the force or the torque or anything like that,” he said. “You program a robot with position, so it’s very easy to tell the robot how far to move if you know the exact degree or the millimeter that it needs to move to. We get that information, send it to the robot, and it knows the exact position to move to for the correct movement or to find the nominal position.” 

While the tool has primarily been used in six-axis robots, it can be implemented in any robot that needs more flexibility and accuracy, Klippstein claimed. 

Why flexibility is necessary for the industry as a whole

As robots become more and more mainstream, flexibility and ease of implementation have become increasingly important topics for the industry. 

“As far as trends, I would say it’s making [end effectors] easy to implement into whatever robot the customer wants to use,” Klippstein said. “As far as establishing the communication, making it really easy to program from that teach pendant is a really big trend and something that is necessary to allow customers to quickly implement the solution.”

Klippstein also said that recent advances in artificial intelligence should help end-of-arm tooling like the Smart Flex Effector become more accurate over time. 

“[More information] gives you insights to what is actually going on so that you can either program around it, or have a better understanding of that process in general, and find new ways to implement that solution or that process in other areas as well,” Klippstein said. 

The post Bosch Rexroth emphasizes flexibility with Smart Flex Effector appeared first on The Robot Report.

The range of manipulation tasks that robots can carry out is growing, according to FAULHABER. It includes everything from grasping and holding to clamping and screwing, as well as foaming and welding, said the German company.

When it comes to standardized mass production, specialized robots can perform the same tasks day and night. But many processes require flexibility, such as when it comes to batch size 1. This is also important to save on investment costs. The greater the range of tasks that a robot can carry out, the better, FAULHABER said in a blog post.

Tool changer with brushless flat motor. Source: FAULHABER

Intelligent Peripherals for Robots (IPR) aims to solve these problem with its TKX tool changer. Mounted to the end of a robot arm, it can remove a variety of tools from a rack, according to IPR.

For example, TKX enables the robot to first grip and position a workpiece, then process it with tools, and finally check and document the quality with a contour sensor or a camera. For this, the adapter needs suitable feed-throughs for the corresponding tool functions.

The TKX series provides options, as well as several lateral screw-on surfaces for additional modules. However, the main task of the tool changer is to securely lock the tool when it is picked up and to quickly and consistently release the lock again when it is set down after use.

Applications determine chose of pneumatic or electric

Traditionally, many industrial applications use pneumatic power transmissions, said FAULHABER. Compressed-air technology has proven itself over decades, and it is suitable for handling very heavy objects, the company noted. But a pneumatic system requires compressors, lines, and its own control system with numerous mechanical components – a considerable investment in new systems.

In industries with increased demands on cleanliness and hygiene, such as microelectronics or food, pneumatics are out of the question because of the unavoidable emission of compressed air. And pneumatics are an absolute no-go in clean rooms. Eppingen, Germany-based IPR said it has seen a significant trend towards the use of electric drives instead of pneumatic ones.

“In addition to the hygienic safety, electric motors are much more flexible in use,” said the company. “Unlike compressed air connections, power sockets are available almost anywhere.”

“In newly built industrial plants, pneumatic systems are generally no longer installed,” IPR added. “For cobots and smaller robots as well as for decentralized locations, the electric version is almost always the better solution.”

The fact that the electric drive is a real alternative to pneumatics today also has something to do with motor technology, explained Roman Batz, development engineer at IPR.

“Great strides have been made in recent years,” he said. “For our applications, we basically need a lot of power with very small dimensions. FAULHABER offers motors that can easily hold their own compared to pneumatic drives.”

FAULHABER motors to open, close, and hold

Holding up is also meant quite literally here. Currently, the most powerful electric model in the TKX series, the TKE 300, is suitable for handling objects weighing up to 300 kg (661.3 lb.), said IPR.

In metal processing, robots can handle heavy loads such as cast blocks or large forged parts. The pulling force of their overall mass then acts upon the locking ring in the TKX changer.

The torque supplied by the motor in standby mode would be enough for safe holding. But to ensure particularly reliable fixation, IPR has also installed self-retaining kinematics, which were developed in-house.

“A brushless motor from the FAULHABER BXT family provides the driving force for opening, closing, and holding,” FAULHABER said. “With its external rotor technology, it achieves a ratio of torque to weight and volume that is unrivaled on the market. This power density is one of the prerequisites for the unique selling point of the new product family from IPR.”

“The TKX series are the first tool changers on the market that are available on the same platform with both pneumatic and electric drives – we also have a manual version in the product range,” Batz said. “This means that the entire range of accessories can be used with all drive types without retooling. And switching to electric operation is also quite easy. This opens up new possibilities for robotic automation.”

IPR’s TKX tool changer includes an electric FAULHABER motor. Source: FAULHABER

Components designed to be reliable, easy to combine

The TKE changers will be available in seven sizes for handling workpieces from 3 to 300 kg (6.6 to 661.3 lb.), according to IPR. The electric variant of the product family thus covers a wide range of applications, from lightweight robots to stationary applications. The dimensions of the BXT motors used are adapted to the application.

“The range of sizes and the large selection of suitable gears for the optimum reduction in each case was an important criterion for us,” Batz said. “Robots should be able to achieve seven-digit cycle numbers without maintenance. So only a brushless motor with the highest possible processing quality can be used. It should be easy to control and manage without additional control – the integrated speed controller takes care of that. Last but not least, the components have to be able to withstand temperatures of up to +80°C.”

IPR procures all of its micromotors from FAULHABER. “We started working together many years ago, long before my time,” Batz said. In addition to the unique quality of the products, other aspects play an important role for him.

“It starts with the very simple design of motor-gear combinations on the FAULHABER website,” said Batz. “It takes just a few clicks to get a comprehensive overview. The technical details are very well documented, and when it comes to precisely calculating the finer points – efficiency, power consumption, temperature development over time, etc. — I always get the support I need.”

An example IPR workcell with the robotic tool changer. Source: FAULHABER

Editor’s note: This article was syndicated with permission from FAULHABER’s blog.

The post Adaptability is key for robotic arms, FAULHABER says appeared first on The Robot Report.

Top row, from left to right: the Ella smart stroller, Soft Robotics’ food packer, and the TM25S. Bottom row: Salidrone, M4, and Zipline’s delivery drone. | Source: NVIDIA

Outside the glare of the klieg lights that ChatGPT commanded this past year, a troupe of autonomous machines nudged forward the frontiers of robotics, according to NVIDIA.

Ella smart stroller makes a splash at CES

Ella — a smart stroller from Glüxkind Technologies, a startup in Vancouver, Canada — kicked off the year when it was named an honoree in the CES 2023 Innovation Awards.

The canny carriage uses computer vision running on the NVIDIA Jetson edge AI platform to follow parents. Its AI-powered abilities, like smart braking and a rock-my-baby mode, captured the attention of media outlets like Good Morning America and The Times of London as well as an NVIDIA AI Podcast interview with its husband-and-wife cofounders.

A member of NVIDIA Inception, a free program for cutting-edge startups, Glüxkind was one of seven companies with NVIDIA-powered products recognized at the Las Vegas event in January. They included:

• John Deere for its fully autonomous tractor
• AGRIST for its robot that automatically harvests bell peppers
• Inception member Skydio for its drone that can fly at a set distance and height without manual intervention
• Neubility, another Inception member, for its self-driving delivery robot
• Seoul Robotics, a partner in the NVIDIA Metropolis vision AI software, for its Level 5 Control Tower that can turn standard vehicles into self-driving care
• WHILL for its one-person vehicle that automatically guides a user inside places like airports or hospitals

mGripAI dexterously packs food

Bedford, Mass.-based Inception member Soft Robotics introduced its mGripAI system to an $8 trillion food industry hungry for automation. It combines 3D vision and AI to grasp delicate items such as chicken wings, attracting investors that include Tyson Foods and Johnsonville.

Soft Robotics uses the NVIDIA Omniverse platform and NVIDIA Isaac Sim robotics simulator to create 3D renderings of chicken parts on conveyor belts or in bins. With help from AI and the ray-tracing capabilities of NVIDIA RTX technology, the robot gripper can handle as many as 100 picks per minute, even under glare or changing light conditions.

“We’re all in on Omniverse and Isaac Sim, and that’s been working great for us,” David Weatherwax, senior director of software engineering at Soft Robotics, said in a January interview.

TM25S provides a keen eye in the factory

In a very different example of industrial digitalization, electronics manufacturer Quanta is inspecting the quality of its products using the TM25S, an AI-enabled robot from its subsidiary, Techman Robot.

Using Omniverse, Techman built a digital twin of the inspection robot — as well as the product to be inspected — in Isaac Sim. Programming the robot in simulation reduced time spent on the task by over 70%, compared with programming manually on the real robot.

Then, with optimization tools in Isaac Sim, Techman explored a massive number of program options in parallel on NVIDIA GPUs. The end result, shown in the video below, was an efficient solution that reduced the cycle time of each inspection by 20%.

Saildrone takes to the seas for data science

Saildrone, another Inception startup in Alameda, Calif., created uncrewed watercraft that can cost-effectively gather data for science, fisheries, weather forecasting and more.

NVIDIA Jetson modules process data streams from their sensors, some with help from NVIDIA Metropolis vision AI software such as NVIDIA DeepStream, a development kit for intelligent video analytics.

The video below shows how three of Saildrone’s smart sailboats are helping evaluate ocean health around the Hawaiian Islands.

Caltech M4 sets its sights on Mars

The next stop for one autonomous vehicle may be the red planet.

Caltech’s Multi-Modal Mobility Morphobot, or M4, can configure itself to walk, fly, or drive at speeds up to 40 mph (see video below). An M42 version is now in development at NASA as a Mars rover candidate and has attracted interest for other uses such as reconnaissance in fire zones.

Since releasing a paper on it in Nature Communications, the team has been inundated with proposals for the shape-shifting drone built on the NVIDIA Jetson platform.

Zipline delivery drones fly high

The year ended on a high note with Zipline announcing that its delivery drones flew more than 55 million miles and made more than 800,000 deliveries since the company’s start in 2011. The San Francisco-based company said it now completes one delivery every 70 seconds, globally.

That’s a major milestone for the Inception startup, the field it’s helping pioneer, and the customers who can receive everything from pizza to vitamins up to seven faster than by truck.

Zipline’s latest drone uses two Jetson Orin NX modules. It can carry 8 lb. of cargo for 10 miles at up to 70 mph to deliver packages in single-digit minutes while reducing carbon emissions 97% in comparison with gasoline-based delivery vehicles.

NVIDIA notes maker machines that inspire and amuse

Individual makers designed two autonomous vehicles this year worth special mentions.

Goran Vuksic with his AI-powered droid. | Source: NVIDIA

Kabilan KB, a robotics developer and student in Coimbatore, India, built an autonomous wheelchair using Jetson to run computer vision models that find and navigate a path to a user’s desired destination. The undergrad at the Karunya Institute of Technology and Sciences aspires to one day launch a robotics startup.

Finally, an engineering manager in Copenhagen who’s a self-described Star Wars fanatic designed an AI-powered droid based on an NVIDIA Jetson Orin Nano Developer Kit. Goran Vuksic shared his step-by-step technical guide, so others can build their own sci-fi companions.

More than 6,500 companies and 1.2 million developers — as well as a community of makers and enthusiasts — use the NVIDIA Jetson and Isaac platforms for edge AI and robotics.

To get a look at where autonomous machines will go next, see what’s coming at CES in 2024.

Editor’s note: This blog reposted with permission from NVIDIA.

The post NVIDIA picks 6 noteworthy autonomous systems of 2023 appeared first on The Robot Report.

Sanctuary asserts that robotic manipulation including tactile sensing is critical to the success of humanoids. | Credit: Sanctuary AI

Sanctuary AI, which is developing general-purpose humanoid robots, has announced the recent acquisition of intellectual property, or IP, adding to its asset portfolio of touch and grasping technologies.

The Vancouver, Canada-based company said it expects this IP to play a pivotal role in its ambitious roadmap for the construction of general-purpose robots. According to Sanctuary AI, the integration of vision systems and touch sensors, which offer tactile feedback, plays a pivotal role in the realization of embodied artificial general intelligence (AGI).

It has already secured patents for numerous technologies developed both internally and through strategic acquisitions from external sources. The company acquired the latest assets from Giant.AI Inc. and Tangible Research.

Sanctuary AI is one of several robotics companies developing humanoid robots. The company unveiled the Phoenix humanoid robot in May 2023, when it publicly demonstrated its sixth-generation unit. This was also the first generation of humanoids from Sanctuary to feature bipedal locomotion.

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

Sanctuary AI takes touch-oriented approach

Unlike its competitors, Sanctuary AI said it has taken a different approach by starting with an intense investment in grasping capabilities combined with hand-eye coordination of human-analog hands and arms. 

Geordie Rose, co-founder and CEO of Sanctuary, was one of three executives from humanoid robotics companies to speak at RoboBusiness 2023’s keynote on the “State of Humanoid Robotics Development.” He described the importance of humanoids being able to do real work by manipulating any object that they might encounter.

This philosophy is a cornerstone to Sanctuary’s development roadmap, and Rose said it is essential to the success of humanoid robots in the future. It is also key to the company’s acquisition plan.

Grasping is a cornerstone in Sanctuary’s product development roadmap, as shown here in this screenshot from a recent Sanctuary USPTO patent. | Credit: USPTO

Surveying the landscape on the way to AGI

Rose told The Robot Report that he believes that “the humanoid competitive landscape is bisecting into two general theses:”

1. Single-purpose bipedal robots to move totes and boxes in retail, warehousing, and logistics
2. General-purpose robots developing generalized software control systems for robots with hands that can act across multiple use cases and industries

Bipedal robots that can walk on two legs have been around for several decades, yet no significant supplier has matured or commercialized the technology despite having the necessary resources, Rose said, citing Honda, Boston Dynamics, and Toyota as examples.

Rose added that the “technology gap” for general-purpose humanoids is related to dexterous manipulation and grasping, which his company is developing and for which it has obtained patents. 

“Replicating human-like touch is potentially more important than vision when it comes to grasping and manipulation in unstructured environments,” said Jeremy Fishel, principal researcher at Sanctuary AI and founder of Tangible Research. “It has been an effort many years in the making to meet the complex blend of performance, features, and durability to achieve general-purpose dexterity.”

Sanctuary claimed that the best way to build the world’s first AGI is to build software for controlling sophisticated robots with humanlike senses (vision, hearing, proprioception, and touch), actions (movement, speech), and goals (completing work tasks).

RoboBusiness 2023 featured a keynote panel with speakers from three leading humanoid manufacturers. Seated left to right: moderator Mike Oitzman | Jonathan Hurst, chief robot officer of Agility Robotics | Geordie Rose, CEO of Sanctuary | Nick Paine, CTO of Apptronik.

IP portfolio around grasping grows

Sanctuary AI’s new IP assets expand on a growing patent portfolio that already protects several key grasping technologies for both non-humanoid and humanoid robots, including visual servoing, real-time simulation of the grasping process, and mapping between visual and haptic data. All of these are key to enabling any robot that must interact with and manipulate objects in unstructured or dynamic environments.

“In dynamic and unstructured environments, coordination between touch and vision is an absolute necessity,” said Rose. “We spent over a year performing industry-wide analysis before acquiring Jeremy’s team. Beyond the functional sensitivity, the technology is designed to be simulateable, enabling us to fast-track our AI model development.” 

According to Rose, “Sanctuary AI is focused on creating the world’s first human-like intelligence in general-purpose robots that will help address the massive labor shortages that organizations are facing around the world. This is a civilization-scale initiative that requires long-term planning and prioritization.”

“Our strategy is unique in that the prioritized focus is on the highest value part of the value chain, which is our clear focus on hand dexterity, fine manipulation, and touch,” he noted. “We believe hands, or more specifically grasping and manipulation, are the key pathway to applying real-world AI to the labor market, given that more than 98% of all work requires the dexterity of the human hand.”

“The acquisition of Tangible Research, the purchase of Giant.AI’s entire patent portfolio, along with our own independent activity, further deepens our IP and expertise in this critical area,” Rose explained.

The Phoenix humanoid robot has taken a deliberate and careful path to market, based on an IP portfolio to support Sanctuary’s product roadmap. | Credit: USPTO

Sanctuary AI patents show multi-purpose robot progress

You can learn a lot about a company’s technical trajectory by looking closely at its IP portfolio. Sanctuary AI’s patents from the past few years include “software-compensated robotics” (USPTO US 11312012 B2), which uses recurrent neural networks and image processing to control the operation and/or movement of an end effector.

A patent for “systems, devices, and methods for grasping by multi-purpose robots” (USPTO 11717963 B2) describes the training and operation of semi-autonomous robots to complete different work objectives.

Finally, the most cryptic of this group of patents is “haptic photogrammetry In robots and methods for operating the same” (USPTO US 11717974 B1), which describes methods for operating robots based on environment models including haptic data.

The market for humanoids has made notable progress in 2023, with plenty of product announcements. Agility Robotics offers one of the most mature systems on the market and has announced publicly that it is testing its robots in both Amazon warehouses and at GXO Logistics.

You can see Phoenix do things like placing items in a plastic bag, stacking blocks, and more as part of Sanctuary AI’s “Robots Doing Stuff” series on its YouTube channel.

The post Sanctuary AI secures IP assets to advance touch, grasping in general-purpose robots appeared first on The Robot Report.

igus has developed a robotic hand for its ReBeL low-cost automation. Source: igus

igus GmbH has developed a finger gripper for its ReBeL collaborative robot. “The ReBeL can now perform a variety of simple humanoid tasks with the new low-cost robotic hand,” said the company.

Automation is entering small and midsize enterprises (SMEs), particularly in the form of collaborative robots or cobots. They can sort, pick and move items with the help of cameras, suction devices, and gripper systems.

The new gripper for the ReBeL cobot is made entirely of self-lubricating plastics and is designed to be cost-effective and easy to integrate, said Cologne, Germany-based igus.

“As the ReBeL is very light and inexpensive with a weight of around 8 kg [17.6 lb.] and a price starting at $6,899, it is often used in humanoid applications,” explained Alexander Mühlens, head of the low-cost automation business Unit at igus. “For this reason, we have received several customer requests for a robot hand that can be easily connected to the ReBeL via plug and play.”

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

igus gives ReBeL a hand for diverse tasks

The compact ReBeL provides a cost-effective way to start working with robotics, claimed igus. ReBeL stands for “Robotic Embedded-BLDC (brushless direct current motor) and electronics link.”

It is suitable for assembly, quality inspections, and tasks in the service sector, the company stated in a release. For these applications, igus offers a wide range of end effectors from various manufacturers on the RBTX.com marketplace.

“The ReBeL can take on a wide range of simple humanoid tasks and applications with the new low-cost hand,” said Mühlens. “We are thinking of such fields as research and development at universities, as well as tasks in the catering or entertainment industries.”

The ReBeL finger gripper is available for as little as $2,760, said igus. The robotic hand is compatible with all ReBeL models and is controlled via DIO (digital input/output) at the tool center point.

In addition, the new gripper can imitate a person’s hand movements, according to the company, whose U.S. headquarters are in Rumford, R.I. Last week, Top Workplaces named igus a top employer in Rhode Island. 

High-performance plastics enable precise motion

igus said it directly provides all components of its finger gripper, including its flange, cables, and control unit. This guarantees 100% compatibility for ReBeL customers, it noted.

Self-lubricating high-performance plastics help keep the price low, asserted igus. Not only are plain bearings in the joints made of iglide polymers to be cost-effective and self-lubricating, but they also ensure smooth and precise movements of the individual fingers, it said.

Extensive tests in the company’s 3,800-sq.-m (40,902.8-sq.-ft.) laboratory has proved the longevity of the humanoid hand. They are intended to be flexible and can be controlled via various interfaces, including USB, TTL (5V) serial, and internal scripting.

Beyond the finger gripper, igus offers other products for the ReBeL platform. These include, for example, fire-resistant smoke hoods, a seventh axis, gripper sets, adapter plate sets, power supplies, a finished workstation, and connection cables.

The company recently said its igusGO mobile app can enhance machine optimization using maintenance-free plastics for more than 450 industrial applications.

The post ReBeL cobot gets low-cost, human-like hand from igus appeared first on The Robot Report.

ISO and ASTM have jointly defined standards for additive manufacturing in construction. Credit: Adobe Stock

Robotic arms and additive manufacturing are changing how materials are handled and how buildings are constructed. However, as robots enter new environments and take on new tasks, the need grows for developers, integrators, and end users to be aware of quality and safety requirements. The International Organization for Standardization, or ISO, has posted documents to help them meet those requirements.

Standard defines safe design for industrial end effectors

An example of relevant industrial standards, ISO/TR 20218-1:2018 provides guidance on the safe design and integration of end effectors for robots. It also adds to ISO 10218-2:2011 on how to integrate robots.

The document covers collaborative robot applications, where robots share workspace with people.

“In such collaborative applications, the end-effector design is of major importance, particularly characteristics such as shapes, surfaces and application function (e.g. clamping forces, residual material generation, temperature),” wrote ISO.

It emphasized the importance of conducting safety assessments. Even when robots are marketed as collaborative, their payloads or motion may not be.

Safety incidents are rare, but interested parties should do their due diligence when developing and deploying robots, noted Aaron Prather, director of robotics and autonomous systems at ASTM International.

ISO and ASTM publish first joint standard for AC

Announced this week, ISO/ASTM 52939:2023 specifies qualification principles for structural and infrastructure elements in additive manufacturing for construction. It provides criteria for additive construction (AC) processes, quality, and factors for system operations, as well as processes on a site.

The new standard applies to all additive manufacturing technologies in building and construction of load bearing and non-load bearing structures, as well as structural elements for residential and commercial applications. It does not cover metals, material properties, operational safety, packaging of equipment and materials, or guidelines for operating specific robots.

ISO/ASTM 52939:2023 is the first jointly published standard from ISO and ASTM International, said Prather. Standards bodies typically focus on different technologies, applications, and industries, but global cooperation can improve worker safety, product quality, and regulatory environments, he noted.

“This addresses moving from traditional construction standards and bridging over to additive,” Prather told The Robot Report. “[It could be] the first step on many to come.”

“This standard also sets the basis for the coming construction robot standards that are in the works across numerous organizations,” he added.

The standard is voluntary, and builders must follow local and regional requirements, noted ISO. In October, ASTM International announced a roadmap for digitalization of the construction industry, sponsored by the National Institute of Science and Technology (NIST).

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

Additive manufacturing changing construction 

Several companies have demonstrated the potential of additive manufacturing for production-grade elements and 3D-printed buildings, including ABB, Branch Technology, HS2, ICON Technology, Mighty Buildings, and SQ4D.

These systems often combine concrete extruders with gantry robots or industrial robot arms. There has also been research into using drones for repair of difficult-to-reach structures, and NASA conducted a 3D-printed habitat challenge in 2019.

Possible advantages include stronger and unique architectures, less waste of materials, and even reduction in carbon emissions, according to research reports from Palgrave Macmillan and Frontiers Media. The global market for 3D printing systems in construction is modest but could increase from $13.38 million in 2023 to $22.63 million by 2030 at a compound annual growth rate (CAGR) of 7.8%, predicted Virtue Market Research.

The post ISO and ASTM define standard for additive manufacturing in construction appeared first on The Robot Report.

SCHUNK said its pneumatic positioning device makes pneumatic grippers more flexible through free positioning, gripping force and speed adjustment. | Credit: SCHUNK

SCHUNK released a pneumatic positioning device (PPD) that it said allows free pneumatic positioning with pneumatic grippers. SCHUNK said this solution is designed for any gripper application that requires flexibility, including robot applications that move workpieces of different sizes or in close proximity to each other.

Developed as an accessory for pneumatic grippers, the PPD is controlled via IO-Link. Together with a position sensor, any position of the gripper fingers can be approached. SCHUNK said this overcomes the gripper open/gripper closed principle. The system set-up consists of just three components: the PPD, a positioning sensor and a standard gripper.

According to SCHUNK, the setup means neither modifications nor special variants of the gripper are necessary. With the PPD, this new dimension of gripping can be retrofitted in an existing operating process.

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

SCHUNK said the new PPD will enable users to optimize their cycle times as the gripper fingers don’t have to move to the end positions before and after each gripping operation. The device avoids collisions with closely positioned workpieces, as it pre-positions the gripper fingers. The gripping force can also be adjusted with the unit by adjusting the output pressure.

The unit features four integrated high-speed 2/2 valves, which together with the integrated electronics and position sensor, ensure a closed control loop. The sealed design with IP67 makes the PPD suited for use in industrial environments.

SCHUNK said the PPD can be installed at the end-of-arm, which can create a positioning accuracy of up to 0.5 mm. The PPD is available in three versions that differ in the flow rate of the internally installed valves. Size and weight always remain the same. SCHUNK said one of its own IO-Link sensors, or all common analog sensors from other suppliers, can be used as sensors for the PPD.

SCHUNK said collisions with closely positioned workpieces can be avoided since the gripper fingers are pre-positioned with the pneumatic positioning device. | Credit: SCHUNK

The post SCHUNK releases pneumatic positioning device for robotic grippers appeared first on The Robot Report.

ATI Industrial Automation’s MC-50 Manual Tool Changer. | Source: ATI Industrial Automation

ATI Industrial Automation has introduced the MC-50 Manual Tool Changer, which provides high performance, reliability, and quality for the manual exchange of robotic tooling.

With intuitive and ergonomic lever operation, the patent-pending MC-50 provides a simple solution for quickly changing robotic end-of-arm tooling by hand. This compact and robust Tool Changer is designed for applications on collaborative robots that support payloads up to 25 kg, and small industrial robots supporting payloads up to 10 kg.

Featuring an ISO 50 mm mounting interface on the Master-side and Tool-side, the low-profile MC-50 mounts directly to most cobots, and seamlessly integrates with many common cobot marketplace grippers and end-effectors.

The MC-50 also includes a safety latch button on the lever to provide secondary locking for increased safety and prevention of involuntary uncoupling. A variety of electrical and pneumatic utilities for downstream end-effectors are supported through four M5 integrated pneumatic pass-through ports and a mounting flat for optional ATI Utility Modules.

Target industry segments include electronics, aerospace, automotive and general industry.

ATI Industrial Automation, a Novanta company, is a leading engineering-based developer of robotic accessories and robot arm tooling including Robotic Tool Changers, Multi-Axis Force/Torque Sensing Systems, Material Removal Tools, Utility Couplers, Manual Tool Changers, Robotic Collision Sensors, and Compliance Devices.

Its robotic end-effector products are found in thousands of applications around the world.  ATI products enable customers to achieve a high level of flexibility in robotic automation. Its flagship product is the Robotic Tool Changer, a robotic wrist coupling that locks and unlocks automatically, allowing a single robot to perform many different tasks. ATI products can be found at some of the world’s most renowned corporations and organizations including NASA, Ford, Honda and Johns Hopkins University. 

The post ATI releases MC-50 Manual Tool Changer appeared first on The Robot Report.

Piab’s lightweight bag gripper, the LBG-50. | Source: Piab

Piab strengthens its grip on the palletizing solutions market with a lightweight bag gripper, the LBG-50. The new gripper lifts sacks and bags with weights of up to 110 lbs (50 kg). As it is a pre-engineered tool, valuable development time can be saved. 

An unavoidable challenge when defining a new bag gripping system in a palletizing line is to get the exact measurements to align with the conveyor rollers for a smooth lifting and releasing process. This demands time-consuming analysis and design and, later on, even more time for adaptation and adjustments.  
 
Furthermore, additional solutions may have to be considered, e.g., for slip sheet handling, which prolongs the implementation process and may interfere with the original set-up and purpose of the gripper. 
  
Piab’s newborn in the palletizing tool family, the lightweight bag gripper LBG-50, aims to solve all of that.  
 
“LBG-50 is the result of our long experience from developing custom palletizing End-of-Arm-Tooling (EOAT)”, Madeleine Sheikh, Product Manager at Piab Vacuum Automation Division, said. “What we have here is a complete pre-engineered bag gripper that is easy to install, adjust and maintain. It offers flexibility to fit any roller conveyor on the market, and slip sheets are handled just as easily by our vacuum-based upgrade option with Duraflex suction cups and COAX technology.” 
  
Handling sacks normally poses a challenge as they are heavy and flexible, yet with a surface that is sensitive to pinching, puncture or rough treatment. LBG-50 avoids that by providing a gentle but firm lift while a built-in top clamp plate secures the bag from above during motion. This, in turn, allows higher cycle speed. 
  
Both the arm and the framework of LBG-50 are made of aluminum, which makes it robust yet lightweight. Other positive features are flexible width and finger positioning and generous mounting options. Flexibility also goes for the valve package, which can be configured with either Discrete I/O, Ethernet/IP or Profinet.  
  
“LBG-50 will be built-to-order in both the EU and the US. We recommend consulting an Application Engineer to ensure the correct gripper selection before purchase”, Madeleine Sheikh said.

The post Piab releases lightweight bag gripper appeared first on The Robot Report.

ATI Industrial Automation has introduced the CGV-900 Compliant Angle Grinder to provide an automated alternative to grinding and finishing by hand. The end-of-arm tool brings versatility to robotic grinding processes while reducing employee safety concerns.

The CGV-900 offers built-in compliance, allowing the unit to compensate for irregularities in part surfaces and maintain contact with a workpiece. The compliance force is adjustable, enabling users to fine-tune their finishing processes in real time.

The CGV-900 also provides position sensing data to help indicate media wear. This lets users establish media replacement intervals, eliminating unexpected rework and downtime. Additionally, the data can be used for process verification.

The Compliant Angle Grinder contains a governed, vane-style motor which provides a more consistent speed during grinding and finishing processes. This ensures an even finish throughout the contact path of the tool.
It is compatible with industry-standard grinding media such as flap wheels, sanding discs and wire brushes that are commonly used with handheld grinding tools.

Combining familiar grinding media with adjustable compliance force makes the Compliant Angle Grinder a safe and efficient replacement for the dull, dirty, dangerous work of grinding by hand. It can mount to a robot arm via bolt up or bolt down pattern or 30 degree mounting patterns.

ATI said the target industry segments for the new Compliant Angle Grinder include metal fabrication, automotive, aerospace and general industry.

In July 2021, ATI Industrial Automation was acquired by Novanta, a leading motion control company, for $172 million in cash. Founded in 1989, ATI is a leading developer of end-of-arm tooling, including robotic changing systems, force/torque sensors, and collision sensors for industrial, collaborative, and medical robotic applications.

ATI Industrial Automation CGV-900 Compliant Angle Grinder. | Credit: ATI

The post ATI Industrial Automation introduces compliant angle grinder appeared first on The Robot Report.

Researchers from Carnegie Mellon University (CMU) and UC Berkeley want to give quadrupeds more capabilities similar to their biological counterparts. Just like real dogs can use their front legs for things other than walking and running, like digging and other manipulation tasks, the researchers think quadrupeds could someday do the same.

Currently, we see quadrupeds use their legs as just legs to navigate their surroundings. Some of them, like Boston Dynamics’ Spot, get around these limitations by adding a robotic arm to the quadruped’s back. This arm allows Spot to manipulate things, like opening doors and pressing buttons, while maintaining the flexibility that four legs give locomotion.

However, the researchers at CMU and UC Berkeley taught a Unitree Go1 quadruped, equipped with an Intel RealSense camera for perception, how to use its front legs to climb walls, press buttons, kick a soccer ball and perform other object interactions in the real world, on top of teaching it how to walk.

The team started this challenging task by decoupling the skill learning into two broad categories: locomotion, which involves movements like walking or climbing a wall, and manipulation, which involves using one leg to interact with objects while balancing on three legs. Decoupling these tasks help the quadruped to simultaneously move to stay balanced and manipulate objects with one leg.

By training in simulation, the team taught the quadruped these skills and transferred them to the real world with their proposed sim2real variant. This variant builds upon recent locomotion success.

All of these skills are combined into a robust long-term plan by teaching the quadruped a behavior tree that encodes a high-level task hierarchy from one clean expert demonstration. This allows the quadruped to move through the behavior tree and return to its last successful movement when it runs into problems with certain branches of the behavior tree.

For example, if a quadruped is tasked with pressing a button on a wall but fails to climb up the wall, it returns to the last task it did successfully, like approaching the wall, and starts there again.

The research team was made up of Xuxin Cheng, a Master’s student in robotics at CMU, Ashish Kumar, a graduate student at UC Berkeley, and Deepak Pathak, an assistant professor at CMU in Computer Science. You can read their technical paper “Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion” (PDF) to learn more. They said a limitation of their work is that they decoupled high-level decision making and low-level command tracking, but that a full end-to-end solution is “an exciting future direction.”

The post Researchers taught a quadruped to use its legs for manipulation appeared first on The Robot Report.