In high-dynamic environments, such as multi-head combination weighers, dynamic filling processes, or robotic systems exposed to variable load profiles, manufacturers are under growing pressure to achieve short cycle times, high throughput and high repeatability, whilst maintaining Overall Equipment Effectiveness (OEE) and advanced diagnostic capabilities. As a result, conventional weighing solutions are increasingly reaching their mechanical and digital limits.

To address these cross-industry requirements, HBK has developed the PW22i single point load cell, specifically designed for high-dynamic mechatronic systems, spanning both high-speed packaging applications and advanced robotic use cases. By embedding IO-Link communication directly at sensor level, the PW22i turns weighing into an intelligent automation component, seamlessly connected to the control layer.

Thanks to its exceptional mechanical stiffness and very high natural resonant frequency, the PW22i has an extremely short settling time, which is a critical requirement for fast cycle applications. These characteristics enable precise and repeatable measurements, supporting giveaway reduction in packaging processes, as well as measurement stability under dynamic loads in robotic systems. Available in 10 kg, 20 kg and 50 kg capacity – and certified to accuracy class C3MR – the PW22i ensures reliable results under demanding operating conditions.

“The PW22i was designed for environments where mechanical dynamics are high and measurement reliability is critical in real time,” said Product Manager Weighing Sensors at HBK, Simon Kleefeldt. “Whether in high-speed packaging lines or robotic applications with rapidly changing load profiles, we combine ultra-fast dynamic weighing with IO-Link intelligence directly at sensor level. This enables plug-and-play integration, faster commissioning and direct use of weighing data within existing control architectures.”

The standardised IO-Link interface and M12 4-pin connector simplifies commissioning, replacement and retrofit of existing systems. Smart functions such as data preprocessing, self-monitoring and diagnostics provide continuous visibility into sensor condition and process behaviour, supporting predictive maintenance strategies and OEE optimisation, across both packaging lines and robotic cells – or end-of-arm tooling systems.

Designed for demanding industrial environments, the PW22i features an IP67 degree of protection and a patented overload stop, allowing it to withstand up to five times its nominal capacity. This robustness ensures reliable operation under mechanical stress, eccentric loading and transient forces, which are common in high-dynamic industrial and robotic applications.

The PW22i supports machine builders, system integrators and manufacturers in designing faster, more connected and more intelligent systems, where weighing becomes a key enabler of operational performance, product quality and data-driven process control, across packaging automation and industrial robotics.

This session will show how PPS’s TactileGlove captures real human touch data, including force, pressure and grip and uses it to train humanoid robots to manipulate objects with greater precision and reliability.

Hosted by Dr. Jae Son, Founder and CEO of PPS, the webinar will bring together engineers, innovators, and robotics specialists to examine why modern robots still struggle with physical interaction and better understanding of contact mechanics. While advances in vision systems and motion control have enabled significant progress, they fail to truly capture contact mechanics information required for dexterous manipulation.

Without tactile data, robots cannot accurately judge how to grip, adjust or handle objects, limiting their ability to replicate human performance.

PPS will introduce tactile sensing in practical, engineering terms, helping attendees understand how pressure distribution and contact mechanics underpin reliable robotic manipulation. A key demonstration will show how humans instinctively adjust their grip when handling objects, such as differentiating between an empty and a full water bottle, an ability that robots currently cannot replicate due to the absence of meaningful tactile data.

“Robots today can replicate movement, but they don’t understand contact mechanics,” said Dr. Jae Son, Founder and CEO of PPS. “Without tactile data, they are effectively operating without feel. What we’re showing is how capturing and learning from human touch enables robots to move from simply performing tasks based on vision.”

Central to the discussion is a new approach to robotic learning – using human manipulation data for AI based robotic systems. PPS’s TactileGlove enables this by capturing real human interaction data via 65 sensing elements, allowing organisations to measure how humans handle objects and use that data to train or inform robotic systems. This approach allows companies to bypass the long hardware development process and begin collecting meaningful data immediately.

PPS will also showcase RoboTact, which integrates tactile sensors directly into robotic finger tips, enabling real-time force control and slip detection to close the loop between learning and execution. The session will also feature guest speaker Tesollo, who will present insights from their humanoid robotics programme and robotic hand development. Having already deployed both the TactileGlove and RoboTact, Tesollo will share real-world findings, demonstrating how tactile sensing is already being applied in practice.

At the core of the webinar is a simple message: without understanding contact mechanics, robotic systems remain incomplete. PPS aims to guide the audience to this conclusion and position itself as the partner to help organisations move forward in building more capable, intelligent robotic systems.

The first session will take place on 21 April at 4pm PST / 8am KST, followed by a second session on 22 April at 8am PST / 4pm UK, with a recorded replay of Tesollo’s presentation also available. Registration details can be found on the PPS website.

Recent industry conferences and technology showcases have highlighted major advancements shaping the future of AI and robotics. This year, Physical AI is taking centre stage – with rapid advances in foundation models, simulation-to-real workflows, and increasingly capable robotic systems.

In this webinar, experts from Robotiq and Universal Robots will share key insights from these events and highlight the Physical AI applications and trends that robotics teams should be watching closely.

The webinar will break down the top five Physical AI breakthroughs demonstrated across recent industry gatherings, discuss where AI still faces challenges when interacting with the physical world, and explore why richer multimodal sensing, especially touch, is becoming critical for training and deploying intelligent robots.

During the session, Robotiq will also introduce its new TSF-85 tactile sensor fingertips, designed to bring pressure, vibration, and proprioception sensing directly to robot grippers. You’ll see how tactile sensing can help generate richer datasets, improve grasp reliability, and support the next generation of Physical AI systems.

Click here to register for the webinar

Visit the Robotiq website for more information

See all stories for Robotiq

With an exceptionally high participation rate, the survey reflected strong employee engagement at SICK and a willingness to contribute to its future development. Responses confirmed the trust that exists within and across teams, providing clear direction on how SICK UK can build on its strengths.

Great Place To Work sets a global standard for workplace culture, employee experience, and leadership, and it comes at a significant moment for SICK UK. The organisation is continuing its strategic transformation within the Europe South and West Cluster and the survey results demonstrate the strength of business growth and people focus working hand-in-hand.

The SICK UK team worked consistently on enhancing leadership, fostering communication within the workforce, creating a more structured and transparent working environment, and putting practical initiatives in place that make the company a Great Place To Work. These include development, mentoring, community engagement, organising company-funded social events bringing together both office-based and remote-based staff to enhance team cohesion, and even arranging for fruit deliveries to promote healthy eating.

Praising SICK UK for achieving its certification, Sarah Lewis-Kulin, the Vice President of Global Recognition at Great Place To Work states, “By successfully earning this recognition, it is evident that SICK stands out as one of the top companies to work for, providing a great workplace environment for its employees.” Being recognised by Great Place to Work serves as proof of a healthy workplace environment, boosting the morale and productivity of employees, and helping to both attract and retain high-quality talent.

Alan Reeves, UK Managing Director of SICK, says, “We are thrilled to receive Great Place to Work certification, as it is a direct reflection of our employees’ feedback. We pride ourselves on creating a positive workplace culture. It is more important than ever to maintain trust, transparency and community during a period of strategic transformation. This certification really comes down to our dedicated leaders and teams, who work hard in pursuit of our shared goals. It is well-deserved recognition of their hard work creating a workplace in which people feel included, supported and proud to belong.”

Following the survey, SICK UK has put in place a structured action plan focused on measurable follow-up on employee feedback and sustainable improvement. SICK continues to invest in people development and remains committed to strengthening its position as an employer of choice within the industrial technology sector.

Visit the SICK website for more information

See all stories for SICK

This powerful new sensor is engineered for universal application in materials handling, robotics, assembly automation, and logistics, offering a versatile solution for confined spaces and complex detection tasks.

The O6D100 leverages PMD time-of-flight technology to ensure reliable and robust object detection, regardless of an object’s colour, angle, or surface characteristics. A key feature is its high excess gain, which enables it to accurately detect challenging objects, including those that are deep black or highly reflective. With an extended detection range of up to 3 metres, the sensor provides flexibility for applications both within and outside the immediate process environment.

To meet the demands of a wide range of applications, the O6D100 features three distinct operating modes – Fine, Standard, and Fast – which can be easily switched via IO-Link. This adaptability allows a single device to fulfil multiple sensing requirements, enhancing efficiency and reducing stockholding. The sensor also includes adjustable hysteresis, with a factory setting optimised for stable switching states even with changing object colours, which can be customised by the user for single-colour object detection.

Designed for rapid integration, the O6D100 fits seamlessly into existing machine setups using the industry-standard O6 design and a simple M8 connector for electrical connection. Its IO-Link capability allows for quick integration into modern control architectures and enables remote configuration, streamlining setup and maintenance procedures for automation professionals.

If you are looking for the widest range of sensors which offer the important combination of best-in-class precision, optimum measuring ranges and frequencies, backed-up by in-depth expertise, Baumer delivers the complete connectivity solution from Sensors to PLC and lloT. Whatever challenges you face in your application, you will find the right sensing solution in the Baumer toolbox.

Sensing applications requiring precise position control, quality inspection and thickness measurement performed to the highest levels of precision and repeatability, is where Baumer’s OM60 Laser Distance Sensors excel. Typical applications are in the automotive, electronics and robotics industries where the benefits of OM60 sensors include the ability to measure distances up to 1000mm, linearity deviation up to 0.03 % MR, measurement frequency up to 3.3 kHz, along with a digital interface such as IO-Link or RS485.

Furthermore, thanks to an exceptionally fine line beam shape, reliable measurement performance, even on challenging surfaces, can be achieved, means these sensors are ideal for applications requiring very precise positioning, or tight tolerances in quality inspection.

Other highlights of Baumer’s IO-Link sensor portfolio include the 50 Series Process Sensors, which the company says offer best-in-class precision, measuring range and response time. Although a compact design, they feature an-easy-to-view large touch colour display within a robust, sealed stainless steel housing, along with easy and standardised operation across the entire 50 series. When a processing application demands the need to measure pressure precisely and reliably across different media, the 50 series are ideal for demanding hygienic and other similar applications.

Baumer’s Incremental Encoders are another important product in the range offering Low Harmonics signal correction and wear-free design for precision under the most testing conditions. Other key features include auto calibration which eliminates temperature and mechanical signal errors, resolution up to 65,536 ppr, accuracy up to 0.05deg, along with smart condition monitoring and flexible configuration of switching output.

Completing the Baumer portfolio are Ultrasonic Sensors which meet the latest IO-Link standard of 1.1 and ensure outstanding ultrasonic object detection and distance measurement. Features include modification of the sensor cone, filtering, individual sensor setting, fast implementation and easy sensor exchange with automatic parameter transfer.

Visit the Baumer website for more information

See all stories for Baumer

The brochure opens with the latest sensing technology, with sections on Smart inductive and photoelectric measurement sensors; the innovative PocketCodr No-code IO-Link sensor configurator; and Contrinex’s new 3D Smart camera.

The vast array of inductive and photoelectric sensors, which include unique solutions, is detailed before outlining Contrinex’s Machine Safety and RFID ranges.

Visit the PLUS Automation website for more information

See all stories for PLUS Automation

In modern production, process automation plays a crucial role in creating cost-efficient and high quality products. High precision is particularly important when assembling complex and flexible components such as cable harnesses. The precise handling of flexible components is extremely challenging, as they are easily deformed and their position can change. To make this process efficient and reliable, non-contact position detection is required so that robots can precisely detect cables and insert them into the connector housing.

Real-time synchronisation

High-resolution laser profile scanners from Micro-Epsilon’s scanCONTROL 3010-200 series have proven effective for these tasks. The sensors measure the position and geometry of the cables in real time so that the robot can grip them securely and fit them in the designated slots. Another building block for successful implementation is software, which processes the measurement data and synchronises it immediately with the movement of the robot. In this way, the manufacturer can ensure that the robot determines the exact pick-up point and inserts the cables precisely into the intended connectors – a decisive advantage for cable harness assembly automation.

Real-time synchronisation between the sensor and the robot ensures precise position detection and reliable processing. It is also a flexible automation cell that can be reprogrammed at any time without the need for complex mechanical modifications. The combination of standard components creates an economical solution that replaces cost-intensive, rigid special machines and significantly increases production efficiency.

Laser scanners for every measurement task

The wide selection of sensor models and measuring ranges now available in the scanCONTROL range of laser scanners enable engineers to solve every profile measurement task. Smart laser scanners with integrated data processing allow users to solve common measurement applications without the need for external data processing. For more complex applications, sensors with programmable software are available.

With Micro-Epsilon’s Configuration Tools software, more than 40 measurement programs with a total of more than 90 evaluations are available. The programs are transferred to the SMART sensor, which performs the measurement, evaluation and output in standalone mode.

Fast, high precision 2D/3D measurements

The scanCONTROL 30×0 series is among the highest performing profile sensors in terms of their size, accuracy and measuring rate. They provide calibrated 2D profile data with up to 7.37 million points per second. A profile frequency of up to 10kHz enables precise profile measurements in dynamic high speed processes.

The high resolution sensor matrix offers a resolution of 2,048 points with an ultimate point distance of just 12µm, enabling extremely fine details to be detected reliably. The sensors are available with either blue or red laser diodes.

Visit the Micro-Epsilon website for more information

See all stories for Micro-Epsilon

Having been used to great success in the automotive industry for several years already, WireSense can now be used in the construction and agricultural machinery sector, commercial transportation and the metalworking industry or the first time. More versatile than ever before, WireSense delivers impressively accurate results with all common seam geometries, including in steel and container construction or on chrome-nickel components.

Despite the great care taken in industrial production with robot welding systems, inaccuracies still occur due to clamping tolerances or upstream processes. A challenge for companies and robot integrators alike, Fronius has created a pioneering solution with the WireSense robot assistance system.

WireSense turns the welding wire into a sensor to precisely determine the position of the component, making it possible to react precisely to positional deviations and correct weld paths accordingly. Rework and component rejects are thereby reduced to an absolute minimum.

WireSense uses the wire electrode not only for welding, but also for measuring component geometries. Thanks to the high-frequency, reversing wire movement, the system detects precise component and seam geometries, edges, height differences and air gaps – and all without any additional sensor hardware. The benefits of WireSense are particularly pronounced on reflective surfaces such as aluminium, where optical systems such as cameras often fail.

“The measurement is contact-based and works on the basis of a weld-free short circuit being established. What’s more, WireSense is compatible with all standard filler metals,” explains Philipp Schlor, Strategic Product Manager at Fronius International. “The Fronius welding machine – an iWave or TPS/I – detects edges or impacts and transmits this information to the robot controller. This then compares the data with the programmed path and automatically corrects the tool centre point (TCP), ensuring that the seam is always welded at exactly the desired location.”

New version, new application possibilities

The new WireSense version now supports all seam geometries: fillet welds, square butt joints, flange welds, and complex, rounded shapes. It can also be used flexibly and reliably with materials such as steel, stainless steel, aluminium, and CrNi alloys, making it attractive for significantly more applications – especially for companies that work with varying sheet thicknesses and complex geometries. Even thicker materials of 4 mm and more can now be reliably detected and processed.

WireSense is a prime example of the transition to intelligent manufacturing. It offers a number of advantages that benefit system integrators in particular:

• Precise position measurement even with difficult component accessibility
• Reliable weld quality, process security, and repeat accuracy
• Detection of sheet thicknesses from 0.5 mm
• Evaluation of gap sizes for automatic selection of stored welding parameters
• Reduction of rework and rejects by up to 100%
• No additional sensors: no cameras, calibration, or maintenance required

The assistance system requires a CMT-Ready setup consisting of the Robacta Drive CMT drive unit and the corresponding CMT wire buffer as well as the WireSense software package (the CMT software itself is not required). It is integrated via the Fronius welding machine, which transmits the sensor signal to the robot controller at lightning speed. Fronius works closely with robot manufacturers so that all the most common robots can process WireSense signals without issue.

A free software update will be all it takes to enjoy all the new features from mid- 2026. Tip: An update may also be needed for the robots too – please contact the robot manufacturer for more information.

“Many of our customers are already using the hardware, i.e., the Robacta Drive CMT drive unit, but not yet WireSense. Now is the perfect time to exploit the full potential of this powerful solution,” emphasises Schlor. “WireSense is a software-only feature, which in this case can be activated without additional components to extract the maximum benefit from an existing investment.”

Optical distance sensors with time-of-flight technology (TOF) offer practical benefits. The sensors enable fast, contactless measurement of large distances, are insensitive to ambient light and provide continuous distance data in real time.

The sensor’s operating principle measures distances by recording the time it takes for emitted light to travel to the object and back. Laser or LED pulses are generally used for this purpose. However, time-of-flight technology also has limitations in measurement accuracy: How precise the results are depends heavily on the nature of the object surface.

Dark surfaces can weaken the reflected signal. They generate narrower pulses and the echo is detected later. Bright surfaces, on the other hand, generate stronger signals with a wider pulse width that are detected earlier. That means the returning signal is detected at different times depending on whether the object’s surface is light or dark. This can cause measurement errors that must be compensated for.

Polynomial function: limited flexibility

Until now, mathematical models based on defined algorithms have been used to correct these errors. A correction value is calculated for many different surfaces and distances, which is later applied automatically. This calculation is based on a so-called polynomial function.

Polynomial functions offer an efficient solution for stable, continuous error curves. One disadvantage, however, is the limited imaging accuracy in the case of complex factors, such as strongly varying surface reflections. As the model parameters are fixed, the functions cannot automatically adapt to changing environmental conditions.

Neural network for correction value calculations

Leuze has a much more precise and flexible solution. Instead of working with rigid formulas, Leuze uses a neural network to determine the correction value. A neural network is a form of artificial intelligence that is modelled on the human brain. It consists of nodes (neurons) in three types of layers: the input layer, hidden layers and the output layer.

The neural network processes information by passing input data step through these one layer at a time. The neurons weigh their results, summarise them and convert them using functions so that a precise result is produced at the end. A so-called activation function decides how strongly a neuron becomes ‘active’, i.e. what value it passes on to the next layer. This activation function enables the network to learn even complex, non-linear relationships and is not limited to simple calculation patterns.

Learning from real data

The AI solution developed by Leuze uses sample data to learn how brightness and surface texture affect the optical distance sensor’s measurements. This makes it much easier to correct the measured values. The neural network is trained with data consisting of raw distance values and pulse widths as input parameters as well as the corresponding standardized correction values at the output.

The training data can be generated from the production process, in which many measured values are collected: for light, dark and differently textured surfaces as well as for different distances. These measured values are communicated to the production facility’s control system. From this, the production facility’s neural network calculates the correction values for the sensor. The sensor then requires no additional computing power during operation – the AI has already ‘learned’ everything.

Five steps for precise values

The Leuze neural network consists of five layers. In each layer, all neurons are fully connected to each other. This means that all information flows into the calculation. A so-called ReLU activation function is used: ReLU stands for ‘Rectified Linear Unit’. This ensures that the network sets negative counters to zero and only processes positive values – similar to a filter that only lets positive signals through, making the learning process stable and reliable.

This has two advantages: Firstly, the network works faster, and secondly, it avoids the computing problems that can occur with other methods. The last layer of the network – the output layer – determines the final correction value. Here, ‘tanh’ (hyperbolic tangent) is used as the activation function. This ensures that the calculated correction value is always within a defined range between -1 and +1. The system then converts this value so that it directly indicates how much the sensor must correct the measured distance in order to deliver precise results.

Calibrated to Leuze sensors

Time-of-flight distance sensors with AI-based correction are particularly useful in industrial automation where precise measurement results are essential. Typical applications include:

• Navigation and collision avoidance: On robots and mobile platforms
• Materials handling: Checking positions and distances on conveyor belts
• Quality assurance: Checking distances on workpieces with difficult surfaces
• Automated guided vehicle systems (AGVs): Precise distance control when parking and manoeuvring
• Safety applications: Detection of proximity to machines and systems

In summary, Leuze is raising the precision of optical distance sensors to a new level with artificial intelligence. Tests have shown that the method’s AI-based calibration reduces systematic measurement errors, i.e. the dependence of measurement results on surface and distance, by more than half. Customers benefit from more robust and accurate measurements without any effort during operation, even with difficult surfaces. This makes it the ideal solution for challenging industrial applications.

Visit the Leuze Electronic website for more information

See all stories for Leuze Electronic