Beamr Imaging and Intempora, a dSPACE company, have announced that Beamr’s ML-safe video data technology is now available on the RTMaps AI Store, ready to use across the AV stack. The collaboration lets AV teams reduce their data volumes while preserving ML accuracy, without changing the stack they already rely on.

Real-Time Multisensor Applications (RTMaps) is a modular development and execution middleware, designed to acquire, synchronize, process, record and replay heterogeneous data streams in real time. Beamr’s ML-safe compression can be deployed at the stages where video data accumulates: at logging, where compression lets constrained storage hold more recorded footage; in the cloud and data center, where it cuts existing petabyte-scale storage and transfer costs; and in simulation and training, where it reduces the real-world and synthetic datasets feeding hardware-in-the-loop (HIL) testing.

At each stage, Beamr’s content-adaptive bitrate technology (CABR) reduces file sizes by up to 50% while the object boundaries, edges and scene detail that perception and detection models rely on are preserved. CABR reduces file sizes beyond standard encoding alone, and runs GPU-accelerated for high-throughput processing.

“The RTMaps AI Store gives AV teams ready-to-use software components they can easily drop straight into their development pipelines, and compression is a capability our users have been asking for,” said Nicolas Du Lac, CEO of Intempora. “Beamr is the first compression technology in the store. It lets teams significantly cut the size of their video data without compromising the models that data feeds, inside the framework they already work in.”

“Managing the volume of data AV programs generate is a constant challenge for the teams we work with, and video is the largest part of it,” said Jacob Perrin, ADAS/AD engineering manager, dSPACE. “In our testing, Beamr reduced that video data while preserving the detections perception models depend on – which is what makes it the right fit for the petabyte-scale workflows across our ecosystem.”

“AV programs run many video pipelines, real-world capture, simulation, synthetic data – each feeding different models – and all need to meet their accuracy targets,” said Sharon Carmel, Beamr CEO. “Our content-adaptive compression achieves improved results over existing workflows, so the same technology reduces data volumes through the AV lifecycle. On the RTMaps AI Store, Beamr’s technology fits into existing pipelines without changing how downstream models behave. AV teams want certainty before making changes, and our Beamr Blueprint methodology provides them an end-to-end assessment of their own video workflows.”

In recent news, Yanfeng reveals XiM27 smart cabin concept with reconfigurable layout and AI-adaptive seating

The ATTI Forum has been curated exclusively for professionals across vehicle development, testing and quality assurance, dedicated solely to discussing next-generation analysis practices and technologies, including hardware and software, that will shape tomorrow’s development landscape.

What themes or trends are you seeing emerge most strongly right now?
Over the past few years, several themes have become major auto news for various reasons. One of those is Euro 7 because it introduces the testing of non-exhaust emissions for the first time (brake and tire emissions), as well as stricter limits on nitrogen oxides and an extended compliance window of 200,000km or 10 years, compared with Euro 6’s 100,000km or five years. As such, we have organized a panel discussion – Euro 7 compliance requirements: Challenges and industry preparedness – with specialists from across the sector to help our audience share strategies and insights.

At one point, it seemed that revelation after revelation was emerging about the vulnerability of vehicles to hacking, alongside data privacy issues linked to the application of AI in vehicles (see our feature on the topic, No free rides, in the June 2025 issue of ATTI). We’ll also be hosting a panel discussion on this and other safety topics – Safe by design, secure by default: Navigating SOTIF, functional safety and cybersecurity in modern automotive testing.

Another key thread is data. Big data has been at the forefront of discussions throughout my 14 years working on ATTI, but there now seems to be a realization that action is needed if the sector is to fully exploit the potential of all the data it has been capturing. Having it is one thing, using it is another – and people seem to be springing into action. It’s a theme throughout the ATTI Awards and Forum, as well as the show itself, and I’m looking forward to learning how developers are tackling the challenge. I am personally looking forward to the presentation from Bugatti Rimac’s vehicle dynamics controls manager, Alessandro Pino, and Marple CEO and co-founder, Matthias Baert – A modern lakehouse architecture for automotive testing. The audience will learn how the two companies have worked together to create a next-gen data architecture, having stored, queried and analyzed 300TB+ of powertrain data from the Tourbillon. 

What topic do you expect attendees to be discussing long after the ATTI Forum ends?
Data and digital twins. I was at another industry event recently and asked various people how they define a digital twin, and whether they would agree with the statement that many digital twins are “static 3D models with a few datapoints layered on top.” These words were written by Dr Ahmed Abada, a senior product manager at BMW Group, in a column he wrote for the March 2026 edition of ATTI. At first, the answer I received was simply, “It depends.” But once I got people talking, we ended up discussing and debating different viewpoints for quite some time.

I’m really looking forward to chatting with Dr Abada and getting his thoughts on digital twin applications, data security and other industry issues, including how regulations affecting exports to the USA are impacting European OEMs. For example, regulations around components, software and hardware, and where automated testing can help.

What are you hoping to learn from the conversations happening here?
Every day I am fed content from external sources about the latest testing innovations and groundbreaking vehicle projects. It’s easy to be fooled into thinking everyone has it sorted, that every vehicle tester is doing their job with their eyes closed. Don’t get me wrong, I have no doubt our audience members take everything in their stride. After all, it is the engineer’s job to experiment, learn and develop new solutions. However, I am interested in hearing about the day-to-day challenges engineers are facing in the lab behind closed doors.

For example, it’s all well and good to say that test automation is helpful, but where are facilities struggling to integrate automated testing and AI into digital twin processes so that these technologies are not standalone tools, but part of a broader workflow? And, crucially, how can our exhibitors help visitors meet those niggles head-on?

Hear from Rachel on June 23 at the ATTI Forum, where she will be joined by engineering experts from AVL, Ford, Nissan, Volkswagen Commercial Vehicles and Daimler Truck, among others

Visit the website to register for your free pass to Automotive Testing Expo Europe. The event is part of Vehicle Tech Week and will take place at Messe Stuttgart, Germany, June 22-24, 2026

“VDA 4.1 is the result of listening closely to our customers’ needs,” said Mike Weglarz, ATI’s executive director for software products. “Engineers told us they needed greater flexibility in how they view and compare data across multiple monitors, native access to CAN and LIN bus trace data without switching tools, and smarter ways to collaborate on large MDF4 datasets across distributed teams. VDA 4.1 addresses all of this – and more.”

One of the key features is the floating and dockable workspace. Pages and tabs can be freely undocked into independent windows and repositioned across multiple monitors. Panel pages enable side-by-side views of graphs, data grids, GPS maps and CAN/LIN bus trace data simultaneously. Chain cursors link navigation across all open windows in real time, significantly improving multiscreen analysis workflows for rapid MDF4 file analysis.

VDA 4.1 introduces native display of CAN and LIN bus messages recorded within MDF4 files, complete with message filtering, a time slider and cursor synchronization with trace pages. Furthermore, engineers can now inspect raw bus traffic correlated directly with measured signals inside the single VDA 4.1 application – eliminating the need for a separate CAN analysis tool.

ATI’s new software includes a new dashboard page and live gauges. The new page type hosts circular and linear gauges, data lists and text boxes that can be locked once configured and linked to trace page cursors. VDA 4.1’s dashboard provides a quick view of different data and a professional, presentation-ready data view purpose-built for test debriefs and live review sessions.

It also comes with optional Vision Enterprise integration. VDA 4.1 integrates fully with the forthcoming optional Vision Enterprise (VE) 1.0 collaboration platform, which will provide centralized MDF4 file storage, powerful 21-criteria metadata search, folder notifications, tag/property editing and upload/download with progress tracking. Vision Enterprise is available as a separately licensed add-on and is expected to launch later this year.

In terms of performance and reliability, more than 30 targeted bug fixes address stability across calculated channels, MDF file handling, GPS visualizer with KML export, layout reapplication and ASCII export.

Vision Data Analyzer 4.1 is available as a subscription-based software license for 64-bit Windows 10 and Windows 11. Site licenses for corporate volume deployments are available on application. The soon-to-be-launched Vision Enterprise collaboration module requires a separate VE server license.

“For engineering teams already using ATI Vision data acquisition hardware, VDA 4.1 is the natural next step,” noted Peter Knivett, executive VP for commercial at ATI. “And for teams using any MDF4-compatible datalogger, VDA 4.1 offers a professional-grade analysis environment at a price point that is highly competitive with far more complex toolchains. The combination of flexible workspace, CAN/LIN trace viewing and optional future Vision enterprise collaboration makes this a compelling choice for control system development teams.”

VDA 4.1 is designed for test engineers, calibration engineers, data analysts and validation teams at OEMs, Tier 1 suppliers and engineering service providers. It supports automotive powertrain, chassis, EV/HEV and ADAS development, as well as heavy truck and bus, agricultural, marine, aerospace and off-highway applications – wherever ASAM MDF4-format test data is used.

Look out for a feature on data acquisition, the data pipeline and other aspects such as edge computing in the June edition of ATTI – due to land soon. Read the latest issue for FREE here

Aqira, supplied by Hottinger Brüel & Kjær (HBK), reportedly improves on the previous system with a streamlined, customizable search experience and richer metadata, enabling engineers to quickly find and retrieve data in usable formats. The aim is to offer greater insight and efficiency in Ford’s next-generation engineering workflows.

Dan Clatterbuck, CAE/TEST engineer at Ford Motor Company, commented, “Aqira has been an extremely positive experience for our engineering teams. It’s a solution built by engineers, for engineers, allowing us to shape the system to fit our workflows and reducing our reliance on IT support.”

In related news, automotive Ethernet compliance simplified with Anritsu and Tektronix test solution

The Future of Automotive Testing Conference

This day of high-level content will explore various topics and provide an engaging opportunity to learn from and connect with industry peers. Situated among the exhibits, it will have a relaxing atmosphere, and visitors will be able to dip in and out at their leisure. A highlight will be ATTI’s on-stage interview with Jon Quigley, who worked for Volvo for many years and now runs his own company, Value Transformation. With his broad experience and portfolio of contacts, he’s a very good person to know. He loves sharing his thoughts, too, hence his new gig as ATTI’s regular columnist.

Read Quigley’s latest column on p36 of the September issue.

Also during the conference, Venkat Adusumalli, software engineering manager at Stellantis, will reveal how Stellantis is using AI to accelerate E/E system testing and validation workflows. Click here for a pre-show interview with him.

Innovation Showcase

The free-to-attend Innovation Showcase also provides an interactive platform for learning about new technologies. Speakers will welcome questions and discussion after their presentations, making it a great way to explore ideas together. Like the conference, it will take place within the main hall, so it will be very easy to listen in while wandering through the exhibits, or to come and go throughout the day.

Technology debuts

The industry is moving quickly and it can be a challenge to keep up. Every year there is an abundance of new technologies on display. Some are incremental improvements to existing products, others are entirely new. It’s always surprising how companies find ways around bottlenecks. Often, these developments emerge from ongoing conversations between supplier and customer, ultimately benefiting multiple companies.

Read ATTI‘s comprehensive expo preview in the September issue.

Face-to-face discussions  

It sounds obvious, but the most fruitful conversations are usually the ones that happen in person – it’s how journalists find the best stories. Year after year, exhibitors and visitors report having forged unexpected collaborations at the show, in the form of technology tie-ups or service partnerships.

Detroit’s revival 

A lot of money has been plowed into Detroit in recent years, as evidenced by the stunning renovation of Michigan Central Station, which is well worth a visit. Much of the investment has been in the tech sector. Eleven years ago – when the station was still derelict – ATTI took a tour of some of the labs at GM and what was then the FCA headquarters (see The right wave length, November 2014, Seasonal highlights, September 2015, and Powerbase, March 2015). The facilities were impressive then and are even more so now, thanks to several years of investment in innovation leading to Detroit’s resurgence as an automotive powerhouse.

Visit the Automotive Testing Expo North America website to secure your FREE pass, which will give you access to the expo, the Future of Automotive Testing Conference and the Innovation Showcase

Designed for high-performance data acquisition in compact, space-constrained environments, the ADQ3-USB brings the full capabilities of the ADQ3 platform into a standalone USB 3.2 form factor, offering up to 10GSPS (Gigasamples-per-second) sampling rate and 2GB/s sustained data transfer to a host PC.

High-speed digitizers are a critical component in analytical and sensing systems, such as lidar and automated test equipment. The demand for faster data acquisition in these fields is driven by higher resolution, faster imaging speeds and more granular real-time analysis. These generate gigabytes of data per second, demanding efficient real-time processing and high-speed data transfer. To preserve signal integrity, especially in compact and noise-sensitive environments, it is often essential to place the digitizer close to the detector within the system enclosure.

Compact design and performance

The ADQ3-USB is housed in a fanless enclosure that supports side-by-side mounting of two units in a standard 1U 19in rack. This design enables users to place the digitizer close to the detector, minimizing cable length and reducing signal reflections, optimizing analog performance in high-speed applications.

It supports continuous data streaming at up to 2 GB/s via USB 3.2, with onboard FPGA capabilities for real-time signal processing, and can handle large volumes of raw data up to 20 GB/s. By eliminating the need for PCIe slots, the ADQ3-USB enables fast and simple integration with mini-PCs and laptops, making it suitable for mobile setups, embedded systems and OEM applications.

Firmware and FPGA options

The ADQ3-USB supports multiple firmware packages tailored to specific application needs, such as FWDAQ for standard data acquisition, FWATD for waveform averaging, FWPD for pulse detection and  DEVDAQ for custom FPGA development.

The open FPGA architecture enables users to implement application-specific algorithms directly on the digitizer, reducing the need for post-processing and enabling real-time decision-making.

OEM integration and model variants

Teledyne SP Devices positions the ADQ3-USB for OEM integration, with ISO-certified production, global support and tailored engineering services for hardware and firmware modifications.

The ADQ3-USB is compatible with a wide range of digitizer models within the ADQ3 series – the ADQ30, ADQ32, ADQ33 and ADQ35. Each model offers different sampling rates, bandwidths and channel configurations.

In related news, high-force, compact 100kN tabletop testing system from Instron targets metals and composites

Test benches have long played a critical role in research and development. In highly controlled lab environments, engineers can measure performance with extraordinary precision. They can simulate stresses, observe failures and capture data with forensic detail. However, the transition from lab to production is rarely straightforward. The requirements of real-world manufacturing – cost, durability, speed and flexibility – demand a different approach to testing. Increasingly, businesses need systems that can bridge both worlds.

This is especially true in sectors where quality and safety are non-negotiable. Aerospace manufacturers, for instance, are often required to store performance data for a decade or more. Automotive OEMs need to verify critical systems like suspension or braking, not just once but continuously, across thousands of units. Pharmaceutical companies must validate devices under strict regulatory conditions, with traceable, repeatable results. In each case, the testing solution must start as a precise tool for experimentation and evolve into something robust enough for the factory floor.

What’s emerging is a shift in mindset – from thinking of test benches as bespoke lab rigs to viewing them as integrated test systems that can be adapted, replicated and scaled. This is changing how machine builders approach design. Rather than building entirely new setups for each test scenario, there’s a move toward modular, reconfigurable architectures that can be tailored to the task, whether it’s analyzing torque in a robotic arm or checking the pressure tolerance of a safety valve.

Data driven

Data is at the heart of this shift. Capturing accurate, high-frequency data enables teams to spot anomalies, understand failure points and refine products before they reach market. However, in production environments, data acquisition faces new hurdles like electrical noise, temperature fluctuations or physical vibration. The test system has to be able to withstand all of this and still deliver clean, usable data.

One of the more significant developments in recent years has been the ability to record data at very high sampling rates – tens of thousands of data points per second – and do so reliably on the factory floor. In high-speed or high-risk applications, where a single missed signal could mean a costly failure, this can make a measurable difference to reliability.

Another important consideration is how scalable a testing solution is. A setup that works for one prototype may not be viable for high-volume production. Flexibility is key. Machine builders are increasingly looking for systems that can be easily expanded or adapted without the need to start from scratch. For example, being able to add extra inputs or change how data is logged, without ripping out and replacing entire systems, can make testing more responsive to shifting needs.

There’s also a growing awareness that the value of a test system extends beyond the testing itself. Once validated, the same configuration can often be packaged and sold as a standalone product. We’ve seen examples in industries from automotive to medical devices where a test setup built for internal use has become a marketable solution. What begins as a custom bench in R&D ends up as a repeatable, sellable machine – industrialized and ready for deployment.

This evolution is shaping how engineers think about testing, not just as a stage in development but as a strategic capability. By investing in systems that are both precise and production-ready, businesses can accelerate the path from prototype to product.

As the boundary between lab and line continues to blur, the tools and thinking around testing are adapting. The challenge now is not just how to test thoroughly, but how to do it smarter, faster and in the environments where it counts.

Read our interview with Mehdi Ferhan, Volvo Group’s senior vice president for powertrain engineering, in which we discuss legislation, sustainability and Volvo’s future vehicle development 

“The implementation of Siemens’ Teamcenter software represents a major technological shift for Tatra Trucks and will provide the company with a significant competitive advantage on the global market. Digitization will enable us to respond more efficiently to the specific requirements of each customer and faster order processing. We anticipate more flexible development, faster technological preparation of production and more timely deliveries of the required quality,” said Jakub Pončík, technical director, Tatra Trucks.

The use of Teamcenter will help Tatra Trucks achieve synchronization and effective data management, from business communication and development through vehicle production to spare parts catalogs or warranty and post-warranty service, by bringing together its PLM system for product development and management with its enterprise resource planning (ERP) system for economics and production.

These systems will become key pillars of digitalization, enabling the company to unify previously fragmented systems, simplify processes and enable faster and more efficient collaboration between departments. The implementation also includes Siemens’ Mendix low-code platform, which allows for the quick creation of applications to reach data from information systems such as ERP and customer relationship management (CRM) and connect it to the Teamcenter digital thread backbone.

“The decision to implement solutions from Siemens Xcelerator at Tatra Trucks demonstrates its key role in optimizing the company’s digital processes. Teamcenter enables the effective use of digital twins and artificial intelligence to innovate products and manufacturing processes, helping to ensure long-term competitiveness. We are glad that Tatra Trucks has chosen our solution and we look forward to our journey together,” said René Zahradník, managing director for Czech Republic, Siemens Digital Industries Software.

The software solution integrates all key PLM processes into a single database. Teamcenter manages all customer requirements, which will be managed in real time through program and project management, including process quality across the entire company. All changes and requests will be recorded and managed within Teamcenter change management. The PLM system enables the creation and management of complete bills of materials and helps Tatra Trucks to more efficiently develop innovative products; improve information sharing between production, service and maintenance; achieve its sustainability goals of carbon footprint reduction; and meet regulatory requirements.

In related news, Siemens Digital Industries Software announced it is introducing new versions of its Teamcenter X software so that organizations of all sizes can access SaaS Product Lifecycle Management (PLM). Click here to read the full story

It builds on its precursor Marple Cloud, with the ability to read databases – rather than ‘drag and drop’ files – and thus caters to larger teams or infrastructures than its precursor. 

MarpleDB, another development, is a high-performance database designed to store and query time-series data, and complements Marple Insights by vertically integrating into the cloud tool, with the ability to be the database should a transition from a file model to a database model occur. 

The automotive industry is seeing a huge leap forward regarding data, which is moving from local files to a database model, meaning an increasing demand for large, smart cloud data storage. However, a disconnect between IT and engineering is often an issue seen in the industry. 

Most visualization and analysis tools are for business intelligence, requiring an engineer to download the data to jump into a local script, or there is no database process adopted in the first place. This reduces productivity as the data is not in a database, accessible to everyone, in real time. MarpleDB and Marple Insights are designed to address these issues. 

For example, MarpleDB can be the first stage in the data pipeline, ingesting real-time data efficiently. Marple Insights can be used to make a project where many different visualizations (maps, FFTs, time-series, scatter plots) and KPIs (histograms, formatted labels, tables) are presented to each team member independent of their location. 

This data can be further enriched with Marple’s tooling, such as custom math channels, data overlays, live-data support and other industry-specific items such as distance-based plotting for motorsport users. 

Marple has been introduced to a number of large motorsport teams, and has been employed at the IMSA 24 at Daytona, among other races. 

In related news, Automotive Testing Technology International magazine will be hosting a free-to-attend interactive panel session at Automotive Testing Expo Europe 2025 in Stuttgart, Germany, in May to provide a roadmap for not just surviving but thriving amid the headwinds of potential international trade tariffs and challenging net zero timelines. Click here to read the full story.

The collaboration will connect Altair’s RapidMiner, a tool for data preparation, AI development, orchestration and automation, with the Databricks Data Intelligence Platform to amplify data science and machine learning capabilities. This will enable customers to access and analyze data housed in Databricks, without data duplication, while applying Altair’s suite of tools to drive decision-making, build AI automation and modernize data operations.

Altair’s AI capabilities include low-code AutoML to sophisticated MLOps, agent frameworks and high-speed visualization.

“We are thrilled to partner with Databricks to empower our customers to stay ahead of the competition by achieving faster, smarter and more efficient outcomes,” said Sam Mahalingam, chief technology officer at Altair. “Through this collaboration, we are helping customers not just to analyze their data but to truly activate it, transforming fragmented data into intelligent systems that can learn, reason and act. Together, Altair and Databricks are redefining the future of data science and analytics.”

“We’ve been impressed by Altair’s innovative approach to data preparation and machine learning,” said Databricks’ director of strategic technology partners, Ariel Amster. “Our partnership will leverage the benefits of Altair RapidMiner and the Databricks Data Intelligence Platform to help customers explore, analyze and take action on data at scale.”

Altair RapidMiner also offers native support for SAS language execution, one of only two platforms in the world with this capability, aiding customers in preserving and extending the value of their existing analytics investments while modernizing their workflows.

Knowledge graphs and data fabrics

The collaboration also utilizes Altair RapidMiner’s massively parallel processing (MPP) knowledge graph technology, purpose-built to support knowledge graph creation, data fabrics and ontology modeling at enterprise scale.

By integrating with Databricks, customers can access the Altair RapidMiner knowledge graph engine to connect, contextualize and activate all types of data: structured, unstructured and streaming.

In related news, the data analysis software jBEAM Lab from Kistler recently updated to offer functions that enable more efficient analyses. Click here to read the full story.