Assessing increasingly sophisticated advanced driver assistance systems and autonomous driving technologies requires manufacturers and testing organizations to analyze large volumes of camera, sensor and vehicle data. During on-road testing, engineers have traditionally reviewed footage, identified road signs and conditions, compared them with dashboard data and assessed the vehicle’s response. This manual process is difficult to scale without increasing engineering resources.

IVEX was developed to address this challenge using computer vision, AI and cloud-based data processing to automate aspects of on-road vehicle safety testing. The platform can interpret the vehicle’s surroundings, including speed limits and road signs, read information displayed to the driver and compare these data sources. The analysis can then assess whether the vehicle recognized relevant road information and responded according to the applicable safety protocol.

The company uses a human-in-the-loop model, enabling engineers to review its output and retain control over the final assessment. The technology can reduce engineering time spent analyzing data by more than 95%; in one example, it processed 400 hours of multi-sensor driving data using eight hours of engineering time.

“Vehicle safety testing generates enormous amounts of data, but much of its analysis still depends on repetitive manual work,” said Mario Torres, co-founder and CEO of IVEX. “AI and rigorous mathematical algorithms allows us to make the testing process significantly faster and more scalable while keeping engineers in control and ensuring that every result remains traceable to the original data. With this funding, we can deepen the capabilities of our platform and bring IVEX technology to North America and Asia.”

IVEX’s long-term goal is to develop an AI-powered platform for automotive safety testing, with different safety protocols, testing requirements and vehicle functions operating as applications. The company says its underlying models will improve as the platform processes data from additional vehicles and driving environments, supporting the development of further safety-testing applications.

Related news, Keysight and University of York partner on AI safety validation for SDVs

Keysight Technologies and the Centre for Assuring Autonomy (CfAA) at the University of York (UK) have announced a research collaboration to advance the safe deployment of artificial intelligence (AI) in software-defined vehicles (SDVs). The collaboration will focus on developing practical methods to validate AI systems and generate the evidence needed to demonstrate their safety and reliability. The work is designed to enable auto makers and suppliers to meet emerging industry requirements while reducing development risk and accelerating the deployment of AI-enabled automotive systems.

Keysight and the CfAA say that together they will help bridge the gap between AI safety research and practical engineering by advancing methodologies for structured AI safety cases and building justified confidence in the safety of AI-enabled automotive systems.

The research will focus on creating evidence-driven approaches to support the implementation of ISO/PAS 8800 requirements, exploring measurable safety-scoring methodologies grounded in academic research and industry standards, and designing practical frameworks for generating auditable AI safety evidence. The resulting methodologies are intended to support the process of building AI safety cases, improve confidence in AI validation, and help engineering teams demonstrate justified AI safety more efficiently throughout the product lifecycle.

By combining the university’s academic expertise with Keysight’s AI validation techniques, the collaboration seeks to advance methodologies applicable to automotive AI development.

Simon Burton, chair in systems safety at the University of York, said, “The automotive industry is at a pivotal point where AI technologies are becoming increasingly integral to vehicle functionality. Ensuring these systems can be evaluated using robust, evidence-based approaches is essential. This is where the CfAA is ideally placed to support Keysight. We have produced several freely accessible frameworks and guidance already being used by industry safety professionals in the transport sector. This collaboration is another way we are supporting the advancement of practice methods that help translate AI safety principles into engineering practices that can be applied in safety-critical environments.”

Lukas Klose, head of the automotive AI Solution Center at Keysight, added, “Automotive organizations need practical and scalable ways to build confidence in AI-enabled systems. By combining leading research in safety assurance with Keysight’s holistic AI Validation Framework, we aim to develop methodologies that help engineering teams generate structured evidence for AI safety cases and support the deployment of trustworthy AI technologies in conformance with international standards such as ISO/PAS 8800.”

The research is expected to inform future development of Keysight’s AI Software Integrity Builder, strengthening support for AI safety arguments, evidence generation and validation aligned with automotive industry expectations.

In related news, SeoulTech develops AI framework to assess vision-system robustness

More than 250 solution providers are expected on the show floor, with exhibits spanning vehicle testing and validation, ADAS and autonomous vehicle development, NVH measurement and analysis, emissions and powertrain testing, simulation and virtual development tools, and data acquisition and test automation. As part of Vehicle Tech Week North America, visitors also gain access to two additional events, Intelligent Vehicle Expo and Automotive Design & In-Cabin Expo, broadening the range of opportunities for cross-disciplinary conversations across the vehicle development lifecycle.

Jason Sullivan, group portfolio director for Vehicle Tech Week, commented, “North America remains one of the most important regions in the world for automotive engineering and technology development. Launching Vehicle Tech Week North America in Novi places the event at the heart of a deeply established automotive region, while creating a platform that speaks directly to where the industry is heading next.”

The Future of Automotive Testing Conference 

Now in its third year and free to attend, The Future of Automotive Testing Conference expands to a full three-day program in 2026 and brings together perspectives from OEMs, suppliers, testing laboratories, research institutions and regulatory bodies to discuss where testing is headed next.

Sessions are grouped around three themes: advanced testing technologies, including data-driven testing, the shift-left approach, AI-enabled workflows and digital twins; testing advanced technologies, covering next-generation powertrains, ADAS, software-defined vehicles and V2X; and future issues and solutions, taking in regulation, standards, certification and homologation as well as broader market pressures shaping the industry.

More than 25 speakers are confirmed so far, with names still being added. Confirmed contributors include Philip Koopman, faculty emeritus at Carnegie Mellon University; Marius Dupuis, CEO of ASAM eV; Christian Thiele, director of global ground vehicle standards at SAE International; and engineers from Stellantis, Ford, General Motors, Tesla, Zoox, Torc Robotics AI and BorgWarner, among others.

Marc LeDuc, VTW senior conference producer for North America, added, “Vehicle Tech Week North America features three integrated conferences built around the realities of modern vehicle development. Each conference track gives depth within a specialist discipline, but the real value comes from connecting those disciplines. Engineers working on software-defined vehicles, validation, propulsion systems, in-cabin experience or simulation are increasingly solving shared problems, and this integrated programming is designed to bring those conversations together.”

On the show floor

With more than 250 solution providers confirmed, the exhibition floor is shaping up to be one of the most comprehensive editions yet.

Data acquisition will be a strong theme this year. Dewetron (booth T1620) will showcase modular measurement systems for power analysis, NVH, vehicle dynamics and durability testing, with compact hardware for in-vehicle measurement and Oxygen software for test-bench analysis.

Force Control (booth T922) will showcase its Positorq dynamometer load brakes, which use oil-shear technology to eliminate cogging, chatter and stick-slip in low-speed, high-torque testing. The brakes enable accurate data capture down to 0rpm with virtually no wear, supporting lifecycle, shock-load, emissions and performance testing.

Also on the floor, Dewesoft (booth T1510) will showcase its DAQ ecosystem for durability, NVH, combustion analysis, EV testing and ADAS validation, which has modular hardware and real-time software supporting CAN, CAN FD, XCP, FlexRay and EtherCAT.

Explore the full exhibitor list here.

Vehicle Tech Week North America 

This year’s expo marks the debut of Vehicle Tech Week North America, which brings three specialist conferences under one roof: The Future of Automotive Testing Conference, Intelligent Vehicle Conference and Automotive Design & In-Cabin Conference. Attendees can attend sessions in their discipline while also dipping into adjacent industry topics.  

Free expo passes for Automotive Testing Expo North America, which include access to the exhibition and the full conference program, are available now at testingexpo-usa.com.

The thermal demands placed on heavy-duty, locomotive and off-highway equipment are becoming harder to solve through conventional, sequential radiator design. AI-powered simulation gives Dolphin the ability to explore far more combinations of core, fin, tube and airflow design – helping engineers find better-performing designs in significantly less time, while balancing thermal performance, pressure drop, weight, durability, packaging and manufacturability.

Dolphin will expand its use of SimScale’s AI and advanced digital simulation tools across its heavy-duty, locomotive truck and bus, and off-highway and industrial ranges in the coming months, using the technology to run computational fluid dynamics and thermal simulations, including shell-and-tube and plate heat exchanger configurations, to optimize thermal efficiency.

Its adoption of the technology deepens Dolphin’s investment in digital-first engineering, enabling its technical team to test and refine thermal and fluid performance earlier and faster in the design cycle, ahead of physical prototyping.

“Our engineering team has always owned every stage of design and validation in-house,” said Nooruddin Jetpurwala, founder, chairman and CEO, Dolphin Global. “Bringing SimScale’s physics and engineering AI and advanced simulation capability into that process enhances our operational efficiency and time optimization. We can now test more configurations, identify issues earlier, and bring validated designs to market faster, without compromising the standards our customers depend on.”

“As equipment and vehicle thermal demands become more complex, supplier engineering teams are increasingly turning to AI and advanced simulation tools,” added David Heiny, co-founder and CEO, SimScale. “By adopting these tools, Dolphin is enabling its engineers to explore up to hundreds more design variants and move beyond conventional approaches and simple, incremental improvements to deliver the type of innovation its customers need.”

Recent news, SeoulTech develops AI framework to assess vision-system robustness

In computer vision and robotics, ensuring that AI systems remain reliable under real-world conditions is a growing challenge. Deep neural network-based vision systems are increasingly used in safety-critical applications such as autonomous driving, where misinterpreting a traffic sign could potentially lead to unsafe decisions. Everyday wear and tear can subtly alter traffic signs, raising questions about whether naturally occurring damage could also expose vulnerabilities in AI-based recognition systems.

To understand and address the problem, a research team led by associate professor Seong Tae Kim from Kyung Hee University and assistant professor Hong Joo Lee from SeoulTech developed Adversarial Wear and Tear (AdvWT), a framework that exploits natural wear and tear as an adversarial signal.

“We focused on traffic signs because they are exposed to weather and environmental damage throughout their lifetime, and their accurate recognition is essential for safety-critical applications,” explained Dr Lee. “Unlike temporary optical attacks, natural deterioration can persist until a physical object is repaired or replaced.”

To create AdvWT, the team trained a generative image-to-image translation model to learn the visual characteristics of damaged and undamaged traffic signs. The model, based on StarGAN-v2, learned a latent “damage style” representation that can reproduce diverse forms of realistic deterioration while preserving the identity and meaning of the sign.

By progressively adjusting the damage representation, they generated signs that looked naturally degraded but were more likely to be misclassified by an AI system. In a human study involving 32 participants, AdvWT-generated images received high naturalness ratings, closely matching the perceived realism of real damaged traffic signs.

The framework was evaluated against two traffic-sign datasets and tested against eight recognition architectures. Across the evaluated models and datasets, AdvWT achieved near-perfect attack success rates on lightweight CNNs such as ResNet-18 and MobileNet, while also remaining effective against transformer-based models. AdvWT also achieved the highest average transferability across most tested model combinations, suggesting that the adversarial perturbations could transfer across different model architectures.

To test the framework in a physical setting, the researchers printed clean and adversarial speed-limit signs and photographed them under different distances, viewing angles as well as indoor and outdoor conditions. The resulting images remained effective at misleading the traffic-sign classifier, showing that the adversarial effect persisted after printing and recapturing under varied physical conditions.

The researchers also demonstrated that the same bidirectional model could be used to restore naturally damaged traffic signs, suggesting potential applications beyond adversarial testing. Importantly, training models with AdvWT-generated damaged signs improved their ability to generalize to real-world damaged traffic signs, suggesting that simulated natural deterioration could be used to identify and strengthen weaknesses in vision systems.

“Building reliable AI requires more than improving average performance. It requires continuously identifying where AI systems fail, understanding why those failures occur, and using those insights to make the systems more robust,” said said Dr Kim. “Over the next five to 10 years, research in this direction could play an important role in developing AI systems that can be deployed more reliably in real-world, high-stakes domains such as healthcare and finance.”

Recent news, AI co-driver turns spoken observations into structured test data

Created specifically to meet the demands of Cross Car racing, the ZZXC extends Nova Motorsport’s mixed-surface competition portfolio alongside its existing multichampionship-winning Rallycross (RX) and Autocross (AX) products.

The development concept

Nova Motorsport drew upon the decades of competition tire knowledge within its engineering team, including experience gained through the design, development and manufacture of Avon Motorsport products for Rally, Rallycross and Autocross competition. According to the company, the result is a highly innovative tire package that offers teams a series of unique advantages.

The Nova ZZXC rear tire features a distinctive asymmetrical tread pattern. Unlike a directional design, the rear tire can be fitted on either side of the vehicle, meaning competitors only need to carry one spare rear tire rather than separate left- and right-sided products.

Nova Motorsport developed the rear tire’s outer shoulder with larger tread blocks to maximize durability under load. In contrast, a more open inner tread pattern has been created to generate greater traction. The tire design aligns with the relatively low levels of camber typically used in Cross Car chassis setups.

The rear tire has been developed to enable competitors to adjust the profile by altering the tire pressure. Lower pressures create a flatter profile ideal for dry conditions; increasing the pressure can create a more crowned profile better suited to wet and muddy surfaces. In these conditions, the aggressive open tread allows the larger blocks to engage more effectively while helping the tire evacuate mud.

For the front tires, Nova Motorsport retained the directional characteristics familiar to Cross Car competitors while developing a distinctive new tread. An arrow-shaped central block combines with larger blocks on either side, providing better management of the wear and loading generated during aggressive steering and cornering.

Philip Carder, product category manager at Nova Motorsport, said, “From the outset, we were determined to create a genuine Cross Car tire that would provide a new level of performance, rather than adapt a product developed for another discipline.”

Successful benchmark test

Nova Motorsport conducted a comprehensive track evaluation of the Nova ZZXC at Circuit Parc de la Serra in Mollerussa, Spain, with David Méat, three-time FIA European Cross Car Champion, at the wheel.

The test program evaluated the tire across a wide range of performance criteria, including start-line traction, acceleration, braking, steering response, cornering behavior and durability. The Nova ZZXC was also benchmarked directly against established competitor products.

“Testing on such a demanding circuit and in extreme conditions gave the Nova ZZXC nowhere to hide,” said Méat. “The traction off the start was particularly strong, and that gave me a lot of confidence through the corners and into the braking areas. There was plenty of lateral grip when the tire was loaded up, and the overall performance was very encouraging for the first test of a completely new product.” Further validation was provided by champion driver Olivier Barré at Circuit Nicolas Klein in Is-sur-Tille, France.

The Nova ZZXC was presented in Lohéac, France, in August 2026, during Round 6 of the eight-round Rallycross France championship.

In related news, Hoosier launches road-legal TrackAttack Pro tire with motorsport DNA

The LMDh prototype first carried out an initial low-speed run at the Paul Ricard Circuit’s Driving Center, before continuing its test program at Le Castellet Airport and then at the Paul Ricard Circuit, right next to ORECA’s Technocentre where the car was designed and developed.

Dan Sayers, WEC Hypercar program manager at Ford Racing said, “Reaching Paul Ricard and getting the car through its shakedown and three full days of running is exactly the milestone we set out to hit. Everything we did in the buildup – the dyno work in Dearborn, the fire-up in France, the countless hours in the sim – was about making sure that when we rolled out onto track, we were ready to be plug and play. There’s a long list of milestones still ahead of us before Q1 2027, but these past couple of weeks has given the team a lot of confidence and strong foundations to build on.”

From design to track

The prototype – the result of close collaboration between Ford Racing and ORECA –  was jointly developed by teams who have been working for several months at ORECA’s Technocentre to prepare for its return to competition in 2027.

Hugues de Chaunac, president of the ORECA Group, commented, “Seeing this Hypercar take to the track for the first time is a powerful moment for all the teams involved in this project. After several months of close collaboration with Ford Racing, these first real-world outings mark an important step in the car’s development. At ORECA, we are proud to contribute to the return of a brand as iconic as Ford to the highest level of Endurance racing, and we are eager to continue this journey with them through to their competitive debut in 2027.”

All six Ford Racing Hypercar drivers attended the test during the week. Logan Sargeant, Matt Campbell, Tom Blomqvist and Mike Rockenfeller took turns behind the wheel, while British drivers Sebastian Priaulx and Nick Yelloly were also on site to gather feedback and prepare for the next phase of testing.

Mark Rushbrook, global director of Ford Racing, said, “This is only the first step of a long and demanding development road, but the fact that all six of our drivers were on hand, working together and pushing this program forward, tells you everything about the spirit we’re building at Ford Racing.”

This first phase of testing marks an essential step in the development of the Ford Hypercar before starting a more intensive test program, in preparation for its homologation under LMDh technical regulations.

Ford Racing Hypercar driver Matt Campbell said, “I’ve been here for the whole test and from my side, it’s gone smoothly. I’ve seen fans online raving about how awesome the sound is, but from inside the cockpit, it’s on another level – it’s absolutely deafening! I’m genuinely excited for what’s ahead with this car. We know there’s a long road in front of us, but this has been a really positive start.”

The Ford Hypercar will continue its development program through several test sessions at European circuits through the end of 2026, before heading to the USA to continue its preparation. Ford Racing will make its return to the highest level of Endurance racing in 2027 with a two-car entry in the top category of the FIA World Endurance Championship (WEC).

Recent news, Aston Martin Valkyrie undergoes technical development test at Silverstone

The IATF 16949 certification covers E-Con Systems’ automotive camera portfolio across four camera types: forward-facing cameras, rear-view cameras, surround-view cameras and driver monitoring cameras, spanning the core vision systems used in mobility applications. E-Con Systems’ automotive cameras are also validated on leading platforms like Nvidia Jetson, supporting a proven path from prototyping through production.

IATF 16949 certification reflects improvements across E-Con Systems’ quality management processes, including risk-based thinking throughout the product lifecycle, product and manufacturing risk mitigation, and structured controls for safety-critical characteristics. The certification also covers customer-specific requirements, error prevention, design-for-manufacturability, APQP and PPAP processes and enhanced quality management across the supply chain.

“As autonomous vehicles and intelligent machines increasingly depend on vision to perceive and respond to the world around them, the quality and reliability of every camera we design and manufacture become mission-critical,” said Ashok Babu, president at e-con Systems.

“The IATF 16949 certification reflects years of discipline built into how we design, develop, and manufacture our vision systems – giving automotive customers a design-responsible partner who identifies and addresses risk early in the product lifecycle, not after it reaches the field.

“We are now extending that rigor from quality to safety: we are actively developing ISO 26262 functional-safety-compliant cameras for automotive and mobility applications. Together, IATF 16949 and ISO 26262 reflect a single commitment – automotive-grade quality in how we build, and functional safety engineered in by design.”

Recent news, AI helps Hyundai unlock decades of crash test data

Yokohama Rubber developed this new system to expand the practical environment of its proprietary HAICoLab AI utilization framework, which was established in October 2020. The company has previously developed AI systems that predict a rubber compound’s physical properties and tire characteristics, generate new rubber compounds, and support mold design, and is increasingly using data to create material and tire designs.

The technical knowledge (domain knowledge) that developers need to make decisions during the tire development process can be found in a vast array of technical documents, including regulatory documents, procedure manuals, technical reports and case studies. Until now, creating a system that can quickly search this vast collection of data and provide information appropriate to development objectives and circumstances has been a challenge.

Yokohama Rubber development staff use this new system to input questions tailored to the development’s objectives and situation, and the generative AI searches internal technical documents for the most relevant information and provides responses based on that content.

The development staff have also created a mechanism by which an AI agent grasps the intent of questions and enhances the accuracy of its response by autonomously repeating the process of planning searches, retrieving information and evaluating the results. Additionally, with the system displaying links to the original documents that serve as the basis for responses, development staff can verify the basis and appropriateness of those responses and use them in interpretation and decision-making. This has added a new mechanism that uses domain knowledge accumulated by AI in technical documents, thereby expanding the tire development environment based on HAICoLab.

Along with the development of these AI systems, Yokohama Rubber is training DX staff to use HAICoLab.

In related news, Hoosier launches road-legal TrackAttack Pro tire with motorsport DNA

“We set out to redefine tire design by asking ourselves, ‘What if we infused our racing expertise into an extreme-performance summer tire?’” said Joerg Burfien, CEO and president of Hoosier Racing Tire. “This was new territory for us. We leveraged Hoosier’s advanced motorsport technology to push the boundaries of what a road-legal performance tire can achieve. Our objective was to deliver exceptional track capability without compromising everyday usability.”

“The TrackAttack Pro truly embodies the spirit of motorsport,” added Martin Heckers, head of Hoosier Racing Tire Europe. “It’s designed for drivers who want to travel to the circuit, maximize their track time, and drive home on the same tires. We believe customers across Europe will quickly become fans of this exciting addition to our product line-up because it delivers the rare combination of motorsport-inspired performance, street legality and everyday usability in a single tire.”

Incorporating H-DNA technology, the TrackAttack Pro pushes boundaries and defies limits. H-DNA was forged from a legacy of unrivaled racing excellence and relentless performance.

“One simple question posed by Joerg Burfien (CEO and president of Hoosier Racing Tire) fundamentally changed our thinking about the relationship between road and racing tires,” said Nic Moncher, head of marketing, Hoosier Racing Tire. “Our goal was to combine Hoosier’s racing pedigree with real-world usability as we grow the TrackAttack family. By leveraging our motorsport DNA, the TrackAttack Pro enables enthusiasts to enjoy outstanding performance both on the road and at the circuit using the same set of tires. By combining the ultimate track day weapon with extreme street performance, we’re delivering a tire designed to help drivers conquer every drive.”

The TrackAttack Pro spans 45 sizes covering wheel diameters from 15 to 21 inches.

Look out for the next issue of Automotive Testing Technology International, which will feature an interview with Hoosier’s head of R&D, Mike Edison.