The agreement reflects the growing role of high-fidelity simulation in motorsport engineering, as testing restrictions, cost pressures and program complexity increase across the industry.

Dynisma CEO Graeme Cook said, “Dallara’s engineering philosophy places huge value on understanding vehicle behavior and driver perception, and we are proud to support that approach as technical partner. The DMG‑360XY platform is designed to be trusted as a primary engineering tool, and this multi-simulator agreement reflects a shared commitment to realism, correlation and long-term technical excellence.”

As part of the partnership, Dallara will deploy two DMG-360XY simulators across its European and US operations. The first system is scheduled for installation at Dallara’s global headquarters in Varano de’ Melegari, Italy, during Q4 2026, with a second simulator planned for delivery to its Indianapolis facility in Q1 2027.

The DMG 360XY is Dynisma’s most advanced motion system, used by Formula 1, GT and endurance racing organizations. It combines ultra-low latency (under 5ms) with high-bandwidth response exceeding 100Hz, unlimited 360° yaw rotation and 5m of XY travel, delivering sustained motion cues without washouts or motion recentering.

By adopting identical simulator platforms across its Italian and US engineering facilities, Dallara will establish a consistent simulation environment supporting correlation, collaborative development and repeatable results across vehicle programs, driver work and longer-term research.

Andrea Pontremoli, CEO and general manager, Dallara, said, “High fidelity simulation is a strategic asset for our group. Establishing identical, top-of-the-range motion platforms in Italy and the USA supports continuity across our engineering programs and strengthens confidence in how virtual development informs real-world performance.”

Luca Bergianti, director of vehicle dynamics and performance at Dallara, said, “At Dallara, virtual development is becoming central to how we engineer our vehicles. The vehicle model now acts as the key integrator of all disciplines, allowing us to validate technical choices in a virtual environment before producing physical components.

“Advanced simulators embed virtual tools into the engineering process, helping us improve performance, uncover opportunities and anticipate issues early on. Dallara’s choice of Dynisma as a partner reflects this shared vision, as we push high-fidelity simulation, realism and development efficiency to the next level.”

As well as supporting internal development, the simulator platforms will form part of Dallara’s wider engineering infrastructure, covering long-term vehicle development, research and selected collaborative programmes.

Related news, ORECA selects Siemens’ Simcenter to support motorsport development programs

The company has adopted the Siemens’ Simcenter STAR-CCM+ and Simcenter Optistruct, part of the Siemens Xcelerator portfolio, to support its high-performance motorsport programs, including its Le Mans 24 Hours hypercar program with Ford Motor Company.

ORECA is using the STAR-CCM+ software for CFD workflows and multi-physics simulations combining aerodynamic, thermal and brake-related effects, alongside Optistruct for optimizing carbon fiber composite layups to balance stiffness and weight in performance-critical components. The tools form part of ORECA’s broader adoption of simulation technology across its motorsport development programs.

“ORECA was looking for a simulation environment that could support accelerated and more streamlined workflows from design through simulation while enabling new types of multiphysics analysis,” said Jean-Philippe Pelaprat, head of aerodynamics at ORECA Group. “Siemens’ simulation software gives our engineering teams the flexibility to run more advanced simulations and optimize composite structures in a highly demanding motorsport environment.”

“Our collaboration with ORECA shows how Siemens Xcelerator empowers engineering organizations to push the limits of performance through simulation-driven engineering,” said Sam Mahalingam, executive vice-president of simulation, HPC and AI, Siemens Digital Industries Software. “By bringing advanced CFD and composite optimization together within a digital twin environment, we’re giving customers the tools to explore bold new design approaches and drive innovation in some of the most demanding, competitive engineering programs in the world.”

Related news, Göpel Electronic introduces universal control solution for single and endurance tests of vehicle components and interiors

The day started with a panel discussion on Euro 7. It’s a topic that has come in and out of the spotlight, and which ATTI has reported on several times over the past few years.

Next up was ATTI’s fireside chat with Dr Ahmed Ebada, an avid contributor to the magazine, on digital twins and AI. Asked what he hopes people will be thinking about – or doing differently – after they leave the discussion, he said, “I hope attendees leave with a more practical view of AI and digital twins. Rather than asking, ‘How can we deploy more AI?’ I would like them to ask, ‘How can we build trustworthy systems that continuously learn, validate and improve outcomes?’

“Whether we are discussing automated testing, digital twins, SDVs or autonomous systems, the key opportunity lies in connecting data, simulation, AI and real-world operations into a continuous feedback loop.

“Ultimately, I hope the audience recognizes that competitive advantage will not come from having the most AI models, but from building the most reliable and scalable AI-driven decision systems.”

Audience member Tatiana Sokolova, a professional truck driver, said she is especially interested in how AI, digital twins and intelligent testing technologies can better reflect real-world road conditions and professional driving experience. While the exhibition’s audience doesn’t typically include drivers, she was excited to add a practical, real-world angle to the discussions.

She commented, “I am especially interested in how real-world operational feedback from professional drivers can support testing, validation and safety discussions – for example, by helping to identify edge cases, unusual traffic situations, foreseeable misuse and boundary situations that may be difficult to capture only in simulations or standard test scenarios.”

The morning continued with presentations, and began this afternoon with another panel at 1:35pm, Safe by design, secure by default – navigating SOTIF, functional safety and cybersecurity in modern automotive testing, and more presentation and panels.

One of ATTI’s afternoon highlights is the presentation from Matthias Baert, CEO and co-founder of Marple, and Alessandro Pino, vehicle dynamics controls manager, Bugatti-Rimac – A modern lakehouse architecture for automotive testing – scheduled to take place at 2:25pm. Speaking ahead of the presentation Pino said, “Engineering teams often believe meaningful analysis requires local scripts, while server-based platforms are seen as tools for finance or business users. In reality, modern, server-based technologies are ideally suited to engineering workflows, enabling collaboration, scalability and faster insight generation.”

A panel discussion at 3:10pm will be led by ATTI on Euro NCAP 2026, which introduces the largest increase in test scenarios since the assessment program was launched is due to take place. Euro NCAP 2026: What the new safety framework means for the automotive testing community will cover key questions including how the changes are expected to affect testing and how long OEMs expect this transition to take, how tuning and verification activities will fit within overall development activities, virtual and physical analysis integration, and what Euro NCAP is doing to ensure its program isn’t disruptive to OEMs.

One of ATTI’s panelists, Emma Deutsch, director of customer-oriented engineering, test operations and DP office at Nissan Technology Centre Europe, who spoke to ATTI onstage last year, said, “I’m looking forward to discussing how we can work more collaboratively on vehicle safety. I hope that we can give the audience an insight into how these changes effect how vehicle design and development is being radically changed – and how this affects customers.”

The ATTI Forum will conclude with another panel followed by the awards.

Awards 
Meet in the Atrium from 4:30pm (ceremony at 5:15pm) for drinks and to celebrate industry achievements across 13 categories and three sets of awards: the Automotive Testing Technology International Awards, the new Vehicle Tech Week Trailblazer Awards and the ADAS & Autonomous Vehicle International Awards.

Automotive Testing Expo, part of Vehicle Tech Week Europe 2026, is open 9am to 3pm tomorrow, June 25

Read Dr Ebada’s column in the March 2026 edition

The 9,460ft2  site at Book End merges Nio’s former UK facilities at Begbroke Science Park and Bicester Motion into a single unit, comprising a dedicated CAE workspace and vehicle laboratory. The R&D center will support closer collaboration across the UK team and provide a more spacious and efficient base for future vehicle development work as the Chinese auto maker marks 10 years of R&D in the UK.

Danilo Teobaldi, principal chief engineer, Nio, said, “Bringing our virtual and physical UK engineering teams together in Witney will accelerate the development of innovations that improve the user experience. With new facilities, we can ensure Nio’s UK-based team continues to pioneer in areas such as class-leading Euro NCAP results for all three group brands, along with smart chassis system solutions for our global platforms.”

Ten years of innovation

In 2016, Nio established its global R&D center for performance and advanced concept engineering in Oxfordshire. Over the past decade, the operation has supported its global vehicle development programs, from the EP9 electric supercar launched in 2016, through to the Nio ET9, its smart executive flagship EV. Its engineers in the UK have also worked on the development of Nio’s third brand, Firefly, and its first compact EV.

Hui Zhang, vice president, Nio Europe, said, “For a decade, our Oxfordshire team has been an integral part of Nio’s global R&D network, contributing to multiple vehicle programs and engineering innovations across our global portfolio. As we celebrate this milestone, we thank the team for its dedication, expertise and contribution to Nio’s development over the past 10 years. The opening of our new Witney R&D center reflects our long-term commitment to the UK, Europe and international collaboration in advancing smart electric mobility.”

The center will facilitate CAE, computational fluid dynamics (CFD), simulation, safety, Euro NCAP safety assessments, durability, handling and noise, vibration and harshness (NVH) developments. It will also serve as Nio Europe’s focal point for artificial intelligence regulation and representation within the International Organisation of Motor Vehicle Manufacturers’ (OICA) AI Cluster through the SMMT. Additionally, the team will contribute to EU policy and regulatory engagement through UNECE working groups and industry consultations.

Mike Hawes, SMMT chief executive, commented, “This investment highlights the UK’s enduring strength as a center of automotive collaboration and engineering excellence. Nio’s decision to consolidate its R&D activity here in a new, state of the art facility also reflects the depth of British talent and expertise in next-generation vehicle technologies.

“It is a timely reminder that amid fierce global competition for investment, the UK can continue to attract and grow high-value innovation, supporting jobs, skills and the transition to zero-emission mobility.”

Related news, Real-world EV test names Xpeng X9 top performer

To address this, rFpro has launched the AV Elevate In Cabin add-on package that enables automotive OEMs, Tier 1s and sensor developers to tune, train and test driver and occupant monitoring systems in simulation to improve the speed and consistency of in-cabin testing.

“Euro NCAP’s 2026 scoring changes make in-cabin monitoring one of the most consequential areas of vehicle safety development,” said Matt Daley, technical director at rFpro. “When you combine that with ADDW becoming mandatory, it is clear that the demand to develop and validate these systems faster and earlier in the program will only grow. We have taken our proven exterior simulation solution and applied the same techniques to the interior. AV Elevate In Cabin is a physically accurate, engineering-grade  simulation environment enabling thousands of tests to be conducted before anything physical has even been built.”

AV Elevate In Cabin addresses three core areas of in-cabin simulation: the fidelity of the virtual cabin environment, the control of occupant behavior within it and the physical accuracy of sensor perception.

Interior fidelity

rFpro has improved the fidelity of its vehicle interior models by adding sub-structures that are invisible to the human eye and to cameras but are detected by radar. The metal framework within seats, for example, is now modeled to ensure radar-based sensing systems encounter realistic returns.

The object library has been expanded to include items commonly found inside vehicles, including rucksacks, laptops, child seats, pets and other personal belongings. Skin simulation has also been improved, with higher-detail facial models to support systems that assess driver state from facial features.

Controlling the virtual environment 

A high-density bone rig within rFpro’s human models enables fine control of facial and limb movements, supporting simulation of the macro and micro expressions that driver monitoring systems must detect. This includes ‘owl movement’, where the driver turns their head, and ‘lizard movement’, where only the eyes shift away from the road.

“We have even considered details like opening and closing vehicle windows,” said Daley. “That is not something you need to think about for external sensor simulation, but it fundamentally changes how light and radar energy travel through the cabin. If you are developing an in-cabin system that needs to work reliably in the real world, these are the kinds of variables you have to account for.”

Sensor modeling

Most in-cabin systems use a mixture of radar sensors, visible light cameras and IR cameras, that see using their own IR energy source. rFpro’s new IR camera sensor integration accurately models the energy emitted by the camera and how it interacts with every cabin surface.

Specific IR reflectivity and radar properties have been assigned to all interior materials, including the driver’s skin, seats and windows. These material characteristics have been correlated with laboratory measurements conducted under the Sim4CamSens research program, with the National Physical Laboratory and Compound Semiconductor Applications Catapult involved in the testing. Skin reflectivity, for example, has been characterized down to the difference between a nose, chin and cheek to improve the realism of IR camera data.

“Looking further ahead, understanding who is in the cabin and what they are doing is essential for autonomous vehicle operations, not just for safety, but for the passenger experience,” said Daley. “If you know where occupants are, you can optimize everything from airbag deployment to noise-cancelling audio. We are looking to partner with sensor developers and OEMs to help drive the direction of this capability further.”

Related news, Gazoo Racing unveils GRMN Corolla

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

“For the BMW Group, the use of industrial data is a key factor in translating artificial intelligence into value creation,” said Dr Franz Decker, CIO and senior vice president of the BMW Group. “By combining our engineering datasets with Mistral AI’s model training capabilities, we are building specialized AI which supports complex development tasks.”

Complexity and data volume in crash simulation

Each week, BMW runs thousands of virtual crash simulations, generating vast amounts of engineering data. Over time, this has resulted in a historical dataset of over one petabyte of crash simulation data that provides highly detailed insights into vehicle structures and material behavior, forming a unique foundation for training an industrial AI model.

“As Industrial AI becomes the new frontier for AI, we are proud to partner with the BMW Group” said Marjorie Janiewicz, chief revenue officer of Mistral AI. “This collaboration shows how industry specific AI models can help solve complex engineering challenges such as crash simulation.”

Large industry model as a technical foundation

To scale this approach, the BMW Group is focusing on large industry models. These are AI systems trained on industry-specific engineering and simulation data from vehicle development and safety testing. Unlike general‑purpose AI systems, LIMs embed domain‑specific knowledge directly into the AI model. This requires not only industrial data, but also deep domain expertise and technical environments that enable AI systems to learn directly from BMW’s development processes.

Related news, Next-generation Helm.ai models deliver full-HD 360° synthetic driving environments

The foundation models address what is often referred to as the industry’s data wall, where the cost and effort of collecting real-world edge-case data can slow development. Traditional generative world models typically produce video at sub-HD or VGA resolutions (around 0.4MP per camera). In contrast, Helm.ai generates full-HD (2MP) output that matches the resolution of modern production vehicle cameras, helping to reduce the sim-to-real gap in training for Level 2 and Level 4 autonomous driving systems.

Scene transfer versus fully synthetic generation

Helm.ai’s platform provides auto makers with a pipeline for data augmentation and creation.

GenSim-3 (high-fidelity scene transfer) enables development teams to restylize real-world video synchronously across six-camera, 360° surround-view setups. The model alters parameters such as weather, illumination and object appearance at full-HD (2MP) resolution. Additionally, the latest model introduces improvements in environmental texture, surface reflectivity and light behavior on complex materials.

VidGen-3 (fully synthetic generation) generates highly realistic driving sequences completely synthetically. By simulating complex environments, human-like agent behaviors and traffic logic from scratch, VidGen-3 bridges geographic and environmental data gaps at scale.

The 5X pixel density advantage

The technology’s key breakthrough is the fidelity of the multicamera generative simulation.

By producing full-HD (2MP) video, Helm.ai provides significantly more visual information than traditional generative datasets. Because modern production vehicles use high-resolution camera systems, training data is more effective when it matches that resolution. Lower-resolution synthetic data can create a domain gap when used to train full-HD perception systems. By generating data natively at 2MP per camera, Helm.ai aligns training inputs with real-world sensor output, supporting more consistent model performance in deployment.

To accommodate diverse sensor and training requirements, engineering teams can optimize for dynamic, high-speed validation with three-camera setups at 30fps, or maximize spatial context with a full six-camera, 12MP surround view at 5fps.

The virtual sensor twin

Unlike CGI-based video generation methods, Helm.ai’s models are designed to simulate hardware-like sensor output by incorporating certain physical characteristics of real camera systems. This includes reproducing effects such as sensor noise patterns, lens flares and exposure-related artifacts. This produces training data that more closely reflects real-world camera behavior, helping perception systems learn under conditions similar to those encountered in actual driving environments.

High fidelity on lower compute

While other generative world models rely on the massive computational scaling of thousands of GPUs to generate sub-HD video, the full-HD (2MP) resolution milestone was achieved using a highly optimized cluster of just a few hundred advanced GPUs.

“We are moving the industry from standard ‘AI video’ to authentic, hardware-accurate sensor emulation,” said Vladislav Voroninski, the CEO and founder of Helm.ai. “By leading with a full-HD (2MP) standard and a 12MP total aggregate capability per timestep, we have solved the resolution bottleneck that has historically limited the utility of generative AI in safety-critical systems. By optimizing our compute architecture, we are giving our partners a high-performance platform to validate their autonomous stacks using synthetic data that perfectly matches the fidelity of their actual production sensors.”

In recent news, Candera unveils “smarter and faster” CGI Studio 3.16 HMI development software

“Our customers expect a straightforward path from simulation model to microcontroller, and the new integration with Matlab and Simulink delivers exactly that,” said Brad Rex, senior director of the system solution team, user experience group at Renesas. “By working with MathWorks, we’ve removed the need to assemble toolchains and device drivers by hand so teams can simulate and validate designs earlier, iterate faster and reduce integration effort across ECU and industrial‑control projects.”

The Renesas RH850/U2A microcontroller – widely used in automotive ECUs – provides the deterministic performance and safety-critical features required for EV motor control, ADAS and body electronics. Engineers developing traction motor control for electric vehicles can deploy field‑oriented control and regenerative braking algorithms directly from Simulink to RH850/U2A‑based ECUs. This shortens the time from concept to vehicle‑level testing, supports smoother torque delivery during rapid transients and speeds calibration across drive cycles – without writing initialization code or custom build scripts.

Said Anuja Apte, India product marketing manager at MathWorks, “Our collaboration with Renesas strengthens the level of interoperability that engineers expect when using Matlab and Simulink. By providing a direct path from Simulink models to optimized microcontroller deployment, we help engineering teams move from design to hardware more efficiently while staying integrated with the broader toolchains they rely on. This approach reflects the MathWorks Connections program, which brings partners and customers together to accelerate innovation and reduce time-to-market within a widely adopted engineering and scientific platform.”

In related news, OmniTrust and Synopsys collaboration enables earlier security validation of embedded systems

The release extends the capabilities of Candera CGI Studio across the entire workflow from design and validation to deployment, and enables development teams to create and scale modern user interface concepts more efficiently across industries, hardware platforms and a wide range of use cases.

“With Candera CGI Studio 3.16, HMI development gets smarter and faster, combining AI-assisted tools, flexible workflows, and broad platform support,” said Roland Winkler, senior product development manager at Candera.

Improvements and updates

The Scene Composer experience has been enhanced with a new View Editor that simplifies automotive HMI workflows by allowing developers to preview scene combinations and manage transitions within a structured framework.

An Embedded Player enables seamless switching between design and runtime simulation inside Scene Composer, while a standalone Player remains available.

Multi View in the Scene Editor adds up to four synchronized views with selectable camera angles, improving inspection of complex 3D interfaces and enabling quick switching between single and multi-view modes.

Localization and documentation workflows are improved with built-in XLIFF 2.0 support. Developers can import, merge, edit and export localized text in a standard XML-based format, making CGI Studio easier to integrate into existing localization toolchains.

The new AI Docs Agent provides in-workflow support by delivering tailored answers in any language, helping users find information more quickly and reducing day-to-day friction. Each response also includes direct links to relevant Candera CGI Studio documentation, enabling users to access source material immediately.

Solution templates and advanced 3D

Another highlight of Candera CGI Studio 3.16 is the expansion of ready-to-use automotive HMI templates. The new In-Vehicle Infotainment (IVI) template includes building blocks for navigation, weather, media, phone, HVAC and digital twin scenarios. It supports both 2D and 3D use cases, with advanced visualizations and customizable application screens.

The new Instrument Cluster Solution Template integrates advanced driver assistant system functions such as adaptive cruise control (ACC), lane departure detection (LDD) and side assist alongside essential dashboard elements like speed gauge, media, telltales, time, odometer, temperature and turn-by-turn guidance. These templates help teams accelerate prototyping and shorten time to value.

The update enhances 3D capabilities with full glTF 2.0 support and features such as clear coat rendering. It also adds HDR rendering with tone mapping and automated import of image-based lighting cube maps for global illumination. Together, these improvements enable more realistic HMI visuals across automotive, industrial and embedded applications.

Engine and platform improvements

On the platform side, Candera CGI Studio 3.16 expands deployment flexibility with native rendering support for Apple iOS, enabling developers to build applications for Apple devices using Xcode and Metal.

The release also introduces Vulkan support as a modern graphics backend for 3D GPUs, improving CPU and GPU efficiency on Linux and Android platforms.

Another key addition is Software Rendering, which enables Candera CGI Studio 3.16 to run on platforms without a GPU. This enables platform-independent rendering across a wide range of targets, including ESP32-S3, ESP32-P4, Traveo II Body MCU, Raspberry Pi Pico and Linux-based systems. The renderer supports transformations, blending and visual effects while achieving up to 60 FPS depending on the platform and configuration, with low memory requirements.

Additional engine optimizations round out the release. Candera CGI Studio 3.16 now supports the new Monotype Spark Engine, designed for low memory usage and high performance. The update also includes newer versions of FreeType and HarfBuzz, delivering significant cache improvements for more efficient text rendering.

Candera CGI Studio 3.16 also streamlines behavior configuration through automatic code-size optimization using the SC plugin and CMake integration. These improvements help developers reduce memory footprint, improve performance and simplify overall project setup and configuration.

Recent news, Michelin reveals software-based tire digital twin platform