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.

Siemens Industry is expanding its 1FK7 servomotor family, with the introduction of a new high-inertia style. The higher rotor inertia of this design makes the control response of the new 1FK7-HI servomotors robust and suitable for high- and variable-load inertia applications.

Siemens said these self-cooled 1FK7-HI servomotors provide stall torque in the 3 Nm to 20 Nm range and are offered in IP64 or IP65 with IP67 flange degree of protection, with selectable options for plain or keyed shaft, holding brake, 22-bit incremental or absolute encoders, as well as 18 color options.

A mechanical decoupler between the motor and encoder shaft protects the encoder from mechanical vibrations, providing a long service life. In cases where the encoder needs to be exchanged, the device automatically aligns the encoder signal to the rotor pole position, enabling feedbacks to be changed in the field in less than five minutes.

These new Siemens 1FK7-HI servomotors also feature the unique Drive-Cliq serial bus and electronic nameplate recognition, allowing virtual plug-n-play operation when paired to the Sinamics S drive platform. All servomotors in this new line are also configured to interface with Siemens Sinumerik CNC technology for machine tool applications and the motion controller Simotion for general motion control use.

Selecting the proper motor to suit the application is facilitated by the Siemens Sizer toolbox and compatible 3D CAD model-generating CAD-Creator package. For more information, visit www.usa.siemens.com/motioncontrol.

The post Siemens introduces high-inertia 1FK7-HI servo motors appeared first on The Robot Report.

ROBOTIS designed its Dynamixel-Y line of high-precision modular actuators forobotics applications. | Source: ROBOTIS

Robots including humanoids are complex and typically require components from multiple suppliers. Tokens.com Corp., now known as Realbotix, this week announced a strategic partnership with ROBOTIS Inc.

The companies said the agreement designates robotics and artificial intelligence developer Realbotix as an official partner to facilitate integration with technologies from ROBOTIS. As part of the agreement, Realbotix will have preferred purchaser status and pricing for ROBOTIS components, including its DYNAMIXEL line of actuators and motors.

The collaborators claimed that these actuators and motors allow for smoother, more human-like movements for Realbotix’s robot line.

ROBOTIS provides parts for a range of robots 

Seoul, South Korea-based ROBOTIS is a manufacturer of robotic hardware. It specializes in components and full robot platforms for use in all fields of study and industry. It has also offered systems based on the Robot Operating System (ROS) and educational robotics kits for all ages and skill levels. 

The company’s DYNAMIXEL line of modular actuators comes in various sizes, power levels, and features. 

In addition to its robot components, ROBOTIS also offers an indoor and an outdoor delivery robot. It said these robots are capable of autonomous deliveries of food, beverages, and parcels in urban areas, apartment communities, hotels, and offices. 

Inside Realbotix’s human-like robots

“Partnering with ROBOTIS Inc., a leader in advanced robotic technologies, allows us to integrate their state-of-the-art motors into our innovative customizable robots,” stated Andrew Kiguel, CEO of Realbotix.

“This collaboration enhances our product capabilities and expands our market reach,” he added. “Together, we are poised to push the boundaries of what’s possible in robotics and deliver exceptional value to our customers.”

Realbotix is a developer of humanoid robotics and relationship-based AI. The San Marcos, Calif.-based company said it is creating customizable robots with human-like appearance and movements. 

In addition, Realbotix asserted that it specifically developed its proprietary AI for human companionship. It asserted that its strength is in the integration of companionship AI and robotics to improve the human condition through connection, learning, and play. Realbotix said its algorithms are also customizable, allowing users to choose how their robots behave and speak.

Realbotix’s robots have a modular structure, which the company says allows for easier maintenance, support, and upgrades. The company offers customizable faces, created with human-synthetic skin, that have 14 movable points. Having more moveable points means the robots can show off a wider range of facial expressions. 

The post ROBOTIS and Realbotix become official development partners appeared first on The Robot Report.

FarmWise is an agtech company pushing the boundaries of automation in agriculture by harnessing the power of computer vision and artificial intelligence (AI). Its flagship product, the Vulcan precision weeding implement, is designed to optimize weed control management on vegetable farms in California, which have been slow to automate due to the complex and versatile nature of specialty crop farming.

By combining cutting-edge technology with custom-built components, FarmWise enhances efficiency, increases crop yields, and addresses labor shortages with a high-accuracy and fully mechanized process to remove weeds.

FarmWise won an RBR50 Robotics Innovation Award for the weeding system in 2021 and will be speaking at RoboBusiness, which runs Oct. 16-17 in Santa Clara, Calif.

Vulcan Automated Weeding System

The Vulcan intra-row weeding implement is FarmWise’s answer to the challenges posed by weed competition in vegetable farms. Weeds can adversely impact crop yield by competing for essential resources such as water, light, and nutrients. Traditional cultivation methods, combined with hand weeding, are labor-intensive and costly, especially in regions like California where labor shortages and rising wages are prevalent.

FarmWise’s Vulcan Automated Weeding System is a pull-behind solution focused on in-season weed control management. The system leverages computer vision and AI to address three key challenges associated with weed removal:

• Precision
• Labor
• Herbicides

Traditional cultivation is imprecise. It either leaves some weeds or only partially removes weeds in between rows of plants. Such cultivators are also cumbersome and error-prone due to a lack of automation and precision control that can lead to mistakes such as crop kills.

Hand weeding is more precise, but it requires time-consuming, physically challenging, and repetitive manual labor that is also expensive for producers. Chemically suppressing weeds has been the most common, efficient, and cost-effective method for controlling weeds in row crops. Using herbicides is becoming less attractive for two major reasons: a shortage of herbicides on the market and the environmental call for farmers to use more sustainable weed control methods.

The Vulcan intra-row weeding implement accurately detects and differentiates crops from weeds, allowing for precision weed removal without damaging crops. This level of precision saves farmers up to $250 per acre, maximizes yield potential, and minimizes the need for expensive manual labor.

Key challenges and customization with PBC linear slides

One of the major challenges FarmWise faced was developing a system capable of adapting to the variety of crops, bed spacings, row spacings, and soil morphologies found on vegetable farms. Compared to corn farming in the Midwest, which has undergone significant automation, vegetable farming in California remains labor-intensive due to its complexity.

To meet this need, FarmWise leveraged advancements in deep learning and precision control software to develop Vulcan, which features a perception module combined with an actuator to perform consistent intra- and inter-row weeding at row level across a diverse portfolio of crops.

The weeder module has two translation axes, including a hydraulic z-axis actuator, allowing it to move up to a dozen inches or so vertically. A feeler wheel arrangement locates the weeder module relative to the crop surface and informs it of changes in the bed’s topology. The balance between automation and user control, however, was critical to the success of this application, according to FarmWise senior mechanical engineer David Olivero.

Register now.

“While the goal is to maximize automation, we acknowledge the farmers’ expertise,” Olivero explains. “Farmers understand the optimal depth for weeder blades to effectively remove weeds while avoiding root damage, and we wanted to empower farmers by allowing them to adjust blade depth according to their preference for deeper, more effective weeding or shallower weeding to protect crop roots.

To achieve this flexibility and reach in the z-axis, FarmWise specified UGA Low Profile Uni-Guide with a custom-positioned hand brake from PBC Linear. Up to 18 of these slides, located at the back of the implement, add a few inches of vertical travel. This addition extends bed capabilities and accommodates varying soil types. The slides offer a robust and customizable solution to adjust the system’s height, enabling it to cater to various farm configurations and terrains.

“We appreciated PBC Linear’s customization platform, which allowed them to create a slide with a specific mount offset tailored to our unique requirements,” says Olivero. “The low-profile design of the slides was vital to reduce the cantilever length of the weeder module, mitigating the risk of transport shock during field-to-field movement. PBC Linear’s reputation for quality products and ease of customization made them a preferred choice.”

A comparison of weeds on a farm before and after using FarmWise’s Vulcan weeding robot. | Credit: FarmWise

Role of computer vision and AI

Central to the Vulcan precision weeding implement’s success is the computer vision and AI in the FarmWise Intelligent Plant System (IPS) Scanner. The IPS Scanner integrates lighting with the camera sensor via a custom LED board. This package enables the capturing of consistent, high-resolution images at a high frame-per-second rate. The data immediately flows through the IPS pipeline, detecting and localizing each plant in real time.

Sophisticated detection models were developed by gathering a vast number of images and annotating them to accurately distinguish between individual crops and weeds. Using these detection models, the system determines the position of crops and the location of every crop stem and makes precise decisions on blade openings and adjustments.

As the system traverses the field, it makes micro-adjustments to ensure the highest quality weed removal. The actuation engine, controlled by the software, opens and closes the weeding blades as needed to clean the intra-row, or in between the crops located on the same line. In addition to the weeding blades that are connected to the actuator, the precision weeding implement includes a set of top knives that simultaneously clean the inter-row surface area between the rows of crops.

Operator interface and user control

FarmWise provides an operator interface mounted in the cab of the equipment. This touch screen–based interface enables the operator to set up and verify the system’s configuration for specific crop and field conditions. The operator can adjust precision, blade widths, and other parameters to achieve the desired results. The interface also offers diagnostics and feedback to fine-tune the system’s performance.

FarmWise’s Vulcan intra-row weeding implement represents a significant step forward in precision agriculture. By providing a tailored solution to weed control management, the system optimizes yield potential, reduces labor costs, and minimizes the need for harmful herbicides.

Through ongoing advancements in computer vision technology and machine learning algorithms, FarmWise continues to push the boundaries of automation in agriculture, offering farmers innovative tools to meet the challenges of modern farming. The collaboration with PBC Linear illustrates the importance of partnerships in developing tailored solutions that drive progress in the agricultural sector.

The post Inside the development of FarmWise’s weeding robot 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.

A robotics strategy should consider software development in parallel, says Radixweb. Source: Adobe Stock

In today’s fast-tech era, robotics engineering is transforming multiple industrial sectors. From cartesian robots to robotaxis, cutting-edge technologies are automating applications in logistics, healthcare, finance, and manufacturing. Moreover, automation uses modern software to execute multiple tasks or even one specific task with minimal human interference. Hence, software development is a critical player in building these robots.

The growing technology stack in robotics is one reason the software development market is expected to reach a whopping valuation of $1 billion by 2027. The industry involves designing, building, and maintaining software using complex algorithms, machine learning, and artificial intelligence to make operations more efficient and enable autonomous decision making.

Integrating robotics and software development

With the evolution of robotics, this subset of software engineering offers a new era of opportunities. Developers are now working on intelligent machines that can execute multiple tasks with minimal human intervention. Also, new software frameworks power these systems that are designed for them.

From perception and navigation to object recognition and manipulation, as well as higher-level tasks such as fleet management and human-machine interaction, reliable and explainable software is essential to commercially successful systems.

One of the essential functions software engineering is the building and testing of robotics applications. Hence, developers need to simulate real-world scenarios and accumulate insights for testing goals. The goal is to recognize and rectify bugs before implementing apps in a real environment.

In addition, developers should remember that they are building systems to minimize human effort, not just improve industrial efficiency. Their efforts are not just for the sake of novel technologies but to provide economic and social benefits.

Register now.

Software developers can advance robotics

Integrating software and robotics promises a symbiotic partnership between the two domains. Apart from collaborating on cutting-edge systems, coordinated development efforts enable the following benefits:

1. Consistency — Robots can be programmed to execute commands with consistency, eradicating human errors caused by distractions or fatigue.
2. Precision — Advanced algorithms also allow robots to enhancing overall product quality.
3. Increased speed — Software-driven robots can carry out tasks much faster than human beings, saving time and money in production activities.
4. Motion planning — Along with modern motors, motion control software allows robots to navigate through complex environments while avoiding potential injuries or collisions.
5. Minimal risk — Advanced robots can handle tasks that involve high physical risks, extreme temperatures, or exposure to toxic materials, ensuring employees’ safety.
6. Remote operations — Building advanced software systems for robots enables them to be monitored and controlled remotely, minimizing the need for human workers to be always present in hazardous settings.
7. AI and machine learning — The integration of AI can help robots understand, learn, adapt, and make independent decisions based on the data collected.
8. Real-time data analysis — As stationary and mobile platforms, robots can gather large amounts of data during their operations. With the right software, this data can easily be examined in real time to determine areas for improvement.
9. Scalability — Robot users can use software to scale robot fleets up or down in response to ever-changing business demands, providing operational flexibility.
10. Reduced downtime — With predictive maintenance software, robots can reliably function for a long time.
11. Decreased labor costs — Robotics minimizes the requirement for manual labor, reducing the cost of hiring human resources and emphasizing more complex activities that need creativity and critical thinking.

Best practices for integrating software and robots

To fully leverage the benefits of software development for robotics, businesses must adopt effective strategies. Here are a few tailored practice to consider:

• Design an intuitive user interface for managing and configuring automated processes.
• Integrate real-time monitoring and reporting functionalities to track the progress of your tasks.
• Adopt continuous integration practices to integrate code modifications and ensure system durability constantly.
• Adhere to applicable data-privacy and cybersecurity protocols to maintain client trust.
• Analyze existing workflows to detect any vulnerabilities and areas for improvement.
• Use error-handling techniques to handle any unforeseen scenarios.
• Implement automated testing frameworks to encourage efficient testing.
• Provide suitable access controls to protect these systems from unauthorized access.
• Identify the applications that can be automated for a particular market.
• Break down complicated tasks into teeny-tiny, manageable steps.
• Perform extensive testing to recognize and rectify any issues or errors.

As robotics finds new use cases, software must evolve so the hardware can satisfy the needs of more industries. For Industry 4.0, software developers are partnering with hardware and service providers to build systems that are easier to build, use, repurpose, and monitor.

Innovative combinations of software  and robotics can result in new levels of autonomy and open new opportunities.

About the author

Sarrah Pitaliya is vice president of marketing at Radixweb, With a strong hold on market research and end-to-end digital branding strategies, she leads a team focused on corporate rebranding, user experience marketing, and demand generation.

Radixweb is a software development company with offices in the U.S. and India. This entry is reposted with permission.

The post Unleashing potential: The role of software development in advancing robotics appeared first on The Robot Report.

In Episode 153 of The Robot Report Podcast, editors Steve Crowe and Mike Oitzman discuss the news of the week. Our featured guest on the show this week is Sankalp Arora, co-founder and CEO of Gather AI. We catch up with Sankalp to learn how his company‘s drone inventory management product is evolving.

The second featured interview is with Jake Hall, the “Manufacturing Millennial,” and Scott Sizemore, director of commercial marketing at motor provider ElectroCraft.

Show timeline

• 5:45: News
• 25:20: Interview with Sankalp Arora, co-founder and CEO of Gather AI
• 58:59: Interview by Jake Hall, the Manufacturing Millennial, with Scott Sizemore, director of commercial marketing at ElectroCraft

Register now.

In the news this week

1. Investor Dean Drako acquires Cobalt Robotics
   • Cobalt Robotics has been acquired by investor Dean Drako, and the name of the security robot firm has been changed to Cobalt AI to more accurately represent the company’s direction and the products it offers.
   • Drako is the founder and CEO of Eagle Eye Networks, in addition to a number of other enterprises and side projects. Cobalt AI fits closest to the Eagle Eye Smart Video Surveillance portfolio.
2. Waymo expands its service area 
   • Robotaxi developer Waymo announced that it’s expanding its service area in Phoenix. The company has added 90 square miles to what was already its largest service area in Metro Phoenix. Waymo’s service now covers 315 square miles of the Valley.
   • In addition, Zoox announced that it will begin testing in Austin and Miami, the fourth and fifth public testing locations for the Amazon subsidiary.
3. OpenAI is restarting its robotics research group
   • OpenAI, which is best known for ChatGPT, is restarting its robotics research group. The San Francisco-based company has been a pioneer in generative artificial intelligence and is returning to robotics after a three-year break.
   • The reboot comes after the company shut down its robotics group in July 2021. That shutdown was prior to all of the interest in generative AI after OpenAI released ChatGPT to the world.
4. See this disc golf disc-throwing robot:

The post Gathering warehouse inventory data — plus an update from ElectroCraft 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.

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.

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.

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.

Motion control has become critical to mobile robot design, says Applied Motion Products. Credit: Gorodenkoff, Adobe Stock

Automated guided vehicles and autonomous mobile robots, or AGVs and AMRs, respectively, are the result of numerous design decisions and tradeoffs. In this free webinar, Applied Motion Products will discuss key factors for mobile robot design, such as performance, safety, and power availability.

Miguel Larios, applications engineer at the company, will explain crucial environmental considerations including IP protection and wheel specifications. He will guide viewers through the essential AGV/AMR specification and feature questions that are critical to ask when selecting the most appropriate motors and gearing for a new system.

Motor selection is increasingly important to include during the design phase because developers, integrators, and users continue to push performance requirements to new levels, according to Larios. He will also explore auxiliary axes for materials handling and jacking axes.

Attendees can learn more about the following in this webinar:

• AGV/AMR performance requirements and the impact on motor selection
• Powering the motion control in your mobile robot
• Safety and environmental considerations around automated systems
• How to select wheels based on operational requirements
• Auxiliary axis types and motion control solutions

“Get Your AGV/AMR Moving! Motion Control in AGVs and AMRs” will be at 2:00 p.m. EDT on Wednesday, May 29, 2024. Register now, and ask questions during the live discussion. The webinar will be accessible on demand after the initial broadcast.

About the speakers, Applied Motion Products

Miguel Larios is an applications engineer at Applied Motion Products Inc. and has worked in industrial automation for five years. During that time, he has worked in both sales and engineering roles and has been exposed to many industries implementing automation. Most recently, Larios has started to work in a product management capacity, focusing on AGV/AMR users.

Founded in 1978, Applied Motion Products has been committed to innovation and advancement of motion-control systems, supplying components to original equipment manufacturers (OEMs). The company sponsoring this webinar said it provides motors and drives for applications where precise control of position, speed, and torque is required. They include robotics, machine control, factory automation, semiconductor handling, packaging machines, and medical devices.

Morgan Hill, Calif.-based Applied Motion Products formed a joint venture in 2014 with Moons’ Shanghai to focus on developing cutting-edge technologies. The partners have research and development centers, as well as more than 200 patents for inventions, utility models, appearances, and software copyrights.

Eugene Demaitre is editorial director for robotics at WTWH Media, which produces The Robot Report, Mobile Robot Guide, RoboBusiness, and the Robotics Summit & Expo. He has extensive experience in business-to-business technology journalism and has participated in conferences worldwide, as well as spoken on many webcasts and podcasts. He is always interested in learning more about robotics. Demaitre has a master’s from the George Washington University and lives in the Boston area.

The post Webinar: Get your mobile robots moving with the right motion control appeared first on The Robot Report.

Researchers reported at ICRA that they can vectorize controllers to be available during training and deployment. | Source: NVIDIA

NVIDIA Corp. research teams presented their findings at the IEEE International Conference on Robotics and Automation, or ICRA, last week in Yokohama, Japan. One group, in particular, presented research focusing on geometric fabrics, a popular topic at the event. 

In robotics, trained policies, like geometric fabrics, are approximate by nature. This means that while these policies usually do the right thing, sometimes they make a robot move too fast, collide with things, or jerk around. Generally, roboticists can not be certain of everything that might occur. 

To counteract this, these trained policies are always deployed with a layer of low-level controllers that intercept the commands from the policy. This is especially true when using reinforcement learning-trained policies on a physical robot, said the team at the NVIDIA Robotics Research Lab in Seattle. These controllers then translate the commands from the policy so they mitigate the limitations of the hardware. 

These controllers are run with reinforcement learning (RL) policies during the training phase. It was during this phase that the researchers found that a unique value could be supplied with the GPU-accelerated RL training tools. This value vectorizes those controllers so they’re available during training and deployment. 

Out in the real world, companies working on, say, humanoid robots can demonstrate with low-level controllers that balance the robot and keep it from running its arms into its own body.

Register now.

Researchers draw on past work for current project 

The research team built on two previous NVIDIA projects for this current paper. The first was “Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior,” which won a best paper award at last year’s ICRA. The Santa Clara, Calif.-based company‘s team used controllers produced in this project to vectorize. 

The in-hand manipulation tasks the researchers address in this year’s paper also come from a well-known line of research on DeXtreme. In this new work, the researchers merged those two lines of research to train DeXtreme policies over the top of vectorized geometric fabric controllers.

NVIDIA’s team said this keeps the robot safer, guides policy learning through the nominal fabric behavior, and systematizes simulation-to-reality (sim2real) training and deployment to get one step closer to using RL tooling in production settings. 

From this, the researchers formed a foundational infrastructure that enabled them to quickly iterate to get the domain randomization right during training. This sets them up for successful sim2real deployment. 

For example, by iterating quickly between training and deployment, the team reported that it could adjust the fabric structure and add substantial random perturbation forces during training to achieve a higher level or robustness than in previous work. 

In prior DeXtreme work, the real-world experiments were extremely hard on the physical robot. It wore down the motors and sensors while changing the behavior of underlying control through the course of experimentation.

At one point, the robot even broke down and started smoking. With geometric fabric controllers underlying the policy and protecting the robot, the researchers found they could be much more liberal in deploying and testing policies without worrying about the robot destroying itself. 

NVIDIA presents more research at ICRA

NVIDIA highlighted four other papers its researchers submitted to ICRA this year. They are: 

• SynH2R: The researchers behind this paper proposed a framework to generate realistic human grasping motions that can be used for training a robot. With the method, the team could generate synthetic training and testing data with 100 times more objects than previous work. The team said its method is competitive with state-of-the-art methods that rely on real human motion data both in simulation and on a real system.
• Out of Sight, Still in Mind: In this paper, NVIDIA’s researchers tested a robotic arm’s reaction to things it had previously seen but were then occluded. With the team’s approaches, robots can perform multiple challenging tasks, including reasoning with occluded objects, novel objects in appearance, and object reappearance. The company claimed that these approaches outperformed implicit memory baselines. 
• Point Cloud World Models: The researchers set up a novel point cloud world model and point cloud-based control policies that were able to improve performance, reduce learning time, and increase robustness for robotic learners. 
• SKT-Hang: This team looked at the problem of how to use a robot to hang up a wide variety of objects on different supporting structures. This is a deceptively tricky problem, as there are countless variations in both the shape of objects and the supporting structure poses.

Surgical simulation uses Omniverse

NVIDIA also presented ORBIT-Surgical, a physics-based surgical robot simulation framework with photorealistic rendering powered by NVIDIA Isaac Sim on the NVIDIA Omniverse platform. It uses GPU parallelization to facilitate the study of robot learning to augment human surgical skills.

The framework also enables realistic synthetic data generation for active perception tasks. The researchers demonstrated ORBIT-Surgical sim2real transfer of learned policies onto a physical dVRK robot. They plan to release the underlying simulation application as a free, open-source package upon publication. 

In addition, the DefGoalNet paper focuses on shape servoing, a robotic task dedicated to controlling objects to create a specific goal shape.

Partners present their developments at ICRA

NVIDIA partners also showed their latest developments at ICRA. ANYbotics presented a complete software package to grant users access to low-level controls down to the Robot Operating System (ROS).

Franka Robotics highlighted its work with NVIDIA Isaac Manipulator, an NVIDIA Jetson-based AI companion to power robot control and the Franka toolbox for Matlab. Enchanted Tools exhibited its Jetson-powered Mirokaï robots.

NVIDIA recently participated in the Robotics Summit & Expo in Boston and the opening of Teradyne Robotics’ new headquarters in Odense, Denmark.

NVIDIA partner Enchanted Tools showed Mirokai at CES and ICRA. Source: Enhanted Tools

The post NVIDIA researchers show geometric fabric controllers for robots at ICRA appeared first on The Robot Report.

The CL Series of collaborative robots. | Source: Kawasaki Robotics

CHICAGO — Kawasaki Robotics (USA) Inc. gave a first look at its new CL family of collaborative robots at Automate this week. The company also showed off new applications using the Kawasaki R Series and BX Series of industrial robots. 

“From our AI-enabled robots to our rich library of technology partners, it’s the collective use of human ingenuity that fuels Kawasaki’s product offerings,” stated Seiji Amazawa, president of Kawasaki Robotics. “Our goal is to harness industrial automation in a way that makes the possibilities virtually limitless for our customers, and our Automate showing will help to reinforce that.”

Kawasaki Robotic added that the CL Series and new applications demonstrate its “commitment to continually optimizing its product offerings, aided by its technology-agnostic stance and expanding network of partners.” The Wixom, Mich.-based company is a unit of Kawasaki Heavy Industries, which has more than 50 years of automation experience and is a leading supplier of industrial robots.

Register now.

CL series combines cobot, industrial features

Kawasaki Robotics claimed its CL series combines the safety and intuitiveness of collaborative robots with a robust design that “unlocks the speed and productivity of industrial robotics.” The new robots, designed and built in Germany, use robot assistance technology from NEURA Robotics, a Kawasaki partner.

Kawasaki had a dual-armed cobot nine years ago, but it had an absence in its product range, Alexandre Boffi, manager for general industries sales at Kawasaki, told The Robot Report.

“We observed what the industry needed — more repeatability, accuracy, robustness, and environmental protection,” he said. “A cobot also had to do what Kawasaki’s industrial robots can do, which led to our collaboration with NEURA.”

The new cobots can reach a speed of 200º/s and repeatability of ±0.02 mm (0.0007 in.). The robots have payload capacities and reaches of 3 kg/590 mm (6.6 lb./23.2 in.), 5 kg/800 mm (11 lb./31.5 in.), 8 kg/1,300 mm (17.6 lb./51.2 in.), and 10 kg/1,000 mm (22 lb./39.3 in.), respectively.

“Customers don’t want to sacrifice speed, accuracy, or reliability,” said Boffi. “Ease of use is driving demand for cobots.”

In addition, the CL series has free mounting orientations, small footprints, and IP66 classification. Kawasaki noted that the cobots’ components include integrated 24-bit encoders, high resolution, and lightweight construction.

The CL series also includes an intuitive user interface and proprietary safety architecture to facilitate human-robot collaboration, said the company.

Like NEURA’s 4NE-1 in the adjacent booth, Kawasaki’s “skunkworks” has worked on its own humanoid robot, the Kaleido, Boffi said.

“Humanoids are like Formula 1 racecars compared with passenger cars,” he said. “They’ll result in smaller controllers and optimized motion control, like our KRNX API [application programming interface], which provides low latency, real-time control, and full access to the BIOS. We’re really focused on building the best tools to help businesses.”

Kawasaki Robotics jointly shows new applications

Kawasaki also demonstrated applications developed with its partners, such as an adaptable finishing system designed by Advanced Machine & Tool (AMT) Precision Parts that can handle diverse materials and surface types. It also showed unstructured parcel sorting with the Kawasaki R Series and Mech Mind‘s 3D camera and AI-powered software.

CRG Automation displayed multi-SKU palletizing and depalletizing using a BX130X robot and an automated corner-board application using a RS00L robot. Olis Robotics‘ Olis Connect edge-hosted product provided remote control and monitoring of the entire system.

“As customer demand for products of all kinds increases and the unceasing need for skilled labor remains, robotics and automation are clear answers to this widespread industry problem,” said Amazawa. “We are motivated by our passion for creating the best possible robotic solutions to ensure our customers see nothing but excitement, potential, and growth when they look to the future.”

Kawasaki Robotics and Olis Robotics have also jointly offered robots and controls they said will enable customers to restart production faster, reduce troubleshooting and downtime costs by up to 90%, and gain access to expert support more quickly.

The post Kawasaki Robotics gives first look at its collaborative robots appeared first on The Robot Report.

The new linear brake solution uses electrical fields to hold the axis. | Credit: ESTAT

ESTAT Actuation engineers and manufactures electronic brakes and clutches that use the physics of electric fields to deliver a braking or clutching interaction when powered on. The company spun out from Carnegie Mellon University in 2019 and introduced its first innovation with a rotary joint clutch/brake product, useful for robotics applications. Now the company is expanding its product line to offer what it describes as an electroadhesive braking solution for linear motion axes.

ESTAT clutches utilize the phenomenon of static electricity to adhere and detach surfaces. You can generate static voltage fields using little energy and thin components, making them an advantageous choice for actuator design due to their lightweight and efficient nature.

The new Linear Clutch from ESTAT offers the adhesion function along a linear path, rather than the rotational path of its first product offering. In its off-the-shelf configuration, the Linear Clutch is capable of transmitting up to 100 N (approx. 25 lbs) in tension while consuming just milliwatts of power.

Note: The Linear Clutch is designed to support tensile loads only, however, the company is also exploring compressive loads use cases.

ESTAT clutches are load-bearing capacitors. When voltage is applied to the clutch webs, positive charges and negative charges build up on either side of the clutch. This leads to the formation of adhesion between the clutch webs, which hinders any further expansion of the clutch.

When not in use, the clutch may move smoothly with very little resistance from tensioners. ESTAT clutches, functioning as capacitors, only need a small amount of maintenance current (< 10 µA) to stay engaged. The clutch disengages when the electrical potential is eliminated.

The new ESTAT linear brake leverages the same physics as its rotary brake, offering a low energy option to mechanical brakes for linear axis. | Credit: ESTAT

Kirby Witte, ESTAT VP of Engineering, will present a live presentation and demonstration of the new linear brake at Automate on Thursday, May 9 at 12:45  PM (Eastern) on the Innovation Stage.

The post ESTAT introduces new linear electroadhesive brake for motion control appeared first on The Robot Report.