Automotive development is evolving as software-defined vehicle programs introduce faster feature cycles and more complex system interactions while meeting strict requirements for safety, reliability and long-term maintainability. Gen AI is now part of engineering workflows. It can help increase development speed, but its non-deterministic behavior, lack of physics awareness and limited traceability make it difficult to apply directly to safety-critical systems. These characteristics make verification, certification and traceability challenging when outputs generated by Gen AI are introduced without constraints.

Model-based design addresses these issues through deterministic execution, executable specifications and physics-based simulation. MathWorks is bringing these strengths together by integrating Gen AI assistance directly into model-based design tooling, enabling engineers to benefit from accelerated workflows while preserving the rigor required for long-term reliability and certification of automotive software.

Simulation as the foundation of trust

Simulation is the foundation of trust in engineering workflows assisted by Gen AI. It provides a controlled environment where system behavior can be verified early and repeatedly. Model‑based design enables closed‑loop simulation within continuous development pipelines, enabling Gen AI‑assisted artifacts to be validated continuously in virtual environments long before software reaches hardware. Closed-loop simulation uncovers defects that emerge only from real‑time interaction between software, hardware and physical dynamics, such as instability, timing issues, saturation and integration errors. Unlike regular software tests that validate code logic in isolation, simulation validates system behavior against requirements under realistic operating conditions, catching safety‑ and performance‑critical issues much earlier.

In leading organizations, ‘shift left’ is not a one-time activity; virtual verification is embedded directly into continuous integration/continuous development (CI/CD) pipelines. Every change triggers automated builds and simulation runs, exercising models against representative scenarios and acceptance criteria. Verification becomes continuous, not episodic.

Scalable development for evolving E/E architectures

Automotive E/E architectures are transitioning from ECU-centric networks to zonal and centralized computing platforms. Software is no longer bound to specific hardware configurations but must now operate reliably across heterogeneous compute targets while remaining portable and scalable, from small controllers to high-performance vehicle computers.

Model-based design supports this requirement by separating system behavior and software intent from hardware implementation. Engineers develop executable models that serve as stable sources of truth. The models can generate production-ready code for a wide range of processors and operating systems, including platforms incorporating AI inference engines and hardware accelerators such as GPUs, DSPs and NPUs. This approach enables the development and validation of AI-enabled functions (e.g. virtual sensors) at the system level, reduces the need to reengineer algorithms for each target, and improves efficiency and consistency across platforms.

Improving collaboration through model-based design

Engineering organizations must transform their collaboration models to keep pace with increased complexity. Integrating simulation, virtualization and automated verification directly into CI/CD workflows supports rapid iteration across software, AI models and hardware acceleration strategies. This model-centric approach helps organizations operate more quickly while preserving robustness, safety and long-term maintainability in the era of software-defined and AI-driven vehicles.

Integrating AI into deterministic engineering workflows

AI is most effective in automotive development when embedded within a deterministic modeling framework. Within model-based design tools, GenAI-generated content is automatically tied to established interfaces, data definitions and architectural constraints. Model Context Protocol (MCP) capabilities empower engineers with AI assistance while preserving the rigor, repeatability and certification readiness.

Long-term maintainability and certification readiness require deterministic behavior, transparent audit trails and verification evidence that accumulates throughout the lifecycle. Model-based design naturally supports these goals by linking requirements, models, test suites and generated code. Continuous simulation produces verification data throughout development rather than only at the end of a program. When artifacts generated by Gen AI follow the same workflows, they inherit this structure. This ensures that productivity gains do not come at the cost of safety, quality or compliance, and that Gen AI can be adopted at scale.

Conclusion

Gen AI and model-based design offer a structured path to accelerate automotive software development while maintaining trust, safety and engineering rigor. Model-based design provides determinism, physics-based validation and traceability. Gen AI adds efficiency and supports faster iteration when integrated within these boundaries.

This combination enables earlier insight into system behavior and deployment across diverse hardware architectures. The model-centric approach ensures consistent collaboration across engineering teams, and promotes reuse and consistency across global programs. Gen AI-enabled model-based design provides a scalable and reliable foundation for developing robust and certifiable automotive systems.

In the September 2024 edition of ATTI, Secondmind’s chief product officer, Morgan Jenkins, discusses the power and limitations of AI

In related news, Agentic AI transforms McLaren Automotive’s entire engineering process

The agenda covered simulation, data management, diagnostics and test automation, with discussions underscoring interoperability, simulation credibility and data‑centric development. These themes emerged across sessions on ASAM standards OpenDrive, OpenScenario, OSI, ODS, SOVD, XIL, OTX, CMP, and digital‑twin integration through the Asset Administration Shell (AAS).

Cross-standard harmonization and the need to align toolchains across domains, suppliers and development stages remain priorities, with speakers citing inconsistent interpretations of ASAM specifications as a cause of fragmentation. Updates included co‑simulation workflows, higher‑fidelity OpenX modeling, interoperable data management, modular measurement architectures, digital‑twin concepts, ODD taxonomies and simulation‑quality assessment.

Regional updates and roadmap

Updates from ASAM’s ambassadors in China, Korea, Japan and the USA were shared by CATARC technical director Bolin Zhou, IVH CEO Daeoh Kang and ASAM Japan representative Yoshiaki Shoi. Priorities included co-simulation and merging standards in China; sensor simulation and ASAM SOVD in Japan; and study groups in South Korea supporting global application of standards, such as ASAM OpenDrive.

BMW IT specialist Michael Schwarzbach outlined the 2026 Technical Steering Committee roadmap, highlighting ODD-based testing, collaboration improvements, harmonized standards and a common ontology.

OpenX updates

ASAM technology managers Ahmed Sadek and Yash Shah (below) presented ASAM OpenX updates. Previous OpenX models defined traffic participants independently, creating toolchain inconsistencies. New concepts for ASAM’s simulation standards include combining ASAM OpenDrive with the Quantifying Simulation Quality (QSQ) initiative, and ASAM OSI adding high-fidelity sensor simulation support, such as spectral irradiance and radar waveforms. “No standard is developed in a silo,” Shah said. “We think feature-based, then collect standards experts for harmonization.”

Simulation integration

Clemens Linnhoff, founder and CTO at Persival, demonstrated co-simulation between Scenario Player and Sensor Model, with all assets linked in ASAM OpenScenario as a single source of truth.

ASAM ODS, MDF, CMP and digital twins

Technica Engineering technical fellow and head of media relations Lars Völker outlined Capture Module Protocol (ASAM CMP) improvements. “Before 2022, in‑vehicle DAQ was vendor‑specific and non‑modular. CMP 1.0 introduced modular DAQ and support for heterogeneous technologies. New use cases support raw Ethernet and define message transport across the vehicle system. Scaling HIL and test setups enables an elastic measurement infrastructure.”

Using slides from the Industrial Digital Twin Association (IDTA), Stefan Romainczyk, senior product manager at Peak Solution, said, “Today’s digital twins are proprietary and one lifecycle element, whereas future twins have a complete lifecycle with efficient scaling. With ASAM ODS, AAS can create a comprehensive data profile for digital twins – standardized interoperability improves predictive maintenance, time and cost.”

SDV diagnostics updates

Following the launch of ASAM SOVD 1.2 in February with 29 global OEMs and suppliers, Vector Informatik manager Tobias Weidmann presented at the seminar the latest activities in the development of the standard. ISO 17978-4 Remote Access covers how to access vehicle information via authorization and defining the access path; possibilities include functional communication, new access methods to log information via a streaming interface, and large file handling via third-party service providers.

ODD taxonomy and AV deployment

Andreas Richter (below), engineering program manager – Operational Design Domains, Volkswagen Commercial Vehicles, outlined ASAM OpenODD implementation within MOIA America, VW’s autonomous‑mobility affiliate, formerly known as ADMT. VW Commercial Vehicles is the first group brand to introduce SAE Level 4 autonomous driving using the ID Buzz platform with integrated third‑party automated‑driving systems. Testing is underway in Hamburg and Munich in Germany, Oslo in Norway, and in Austin, Texas.

Richter noted that the industry is not always clear on ‘ODD’, ‘taxonomy’, ‘service area’ and ‘scenarios’. “To bring autonomous driving to life, we have to agree on the same terms,” he said, calling for ODD definitions that are unambiguously readable by humans and machines, supported by geodata analysis and enterprise‑ready tools for ODD and scenario management.

“ASAM OpenODD offers a taxonomy-agnostic, modular model to represent ODDs in different technical formats, [and] support development, storage and processing in a machine and human-readable way,” he explained. “Originally intended for scenario-based testing, ODD definition is now required in more process steps for developing, testing, approving and operating ADS. The ODD as a single point of knowledge ensures OEMs and authorities share definitions.”

VW’s internal elaborated ODD taxonomy demonstrates how modular definitions support understanding across organizations and regulators. The ODD management toolchain validates taxonomies and module definitions, supports multilingual concepts and connects to scenario‑creation and requirements‑management workflows. Using STIEF (scenario-accompanied, text-base, iterative evaluation of automated driving functions), engineers can preload scenario definitions via natural‑language inputs, while geodata analysis identifies new operational areas and generates challenging test routes.

Simulation credibility

In an ASAM QSQ update, Automotive Artificial Intelligence’s general manager Basit Khan highlighted the challenge of trusting simulation for virtual homologation.

“No standardized quality metrics exist for simulation frameworks, especially ADAS/AD sensors,” he said. “Many contributors – OEMs, suppliers, research and tool vendors – have different priorities and vocabulary. Through working groups spanning use cases, camera, lidar, radar and vehicle dynamics, our goal is to drive cross-sector innovation by building a unified standard upon proven, existing components. By harmonizing established concepts, we can create a practical framework that ensures simulation reliability without reinventing the wheel.”

Research and collaborations

Fraunhofer IOSB’s research group leader Jens Ziehn reported on how ASAM helps scale R&D results, for example where ASAM’s OpenDrive, OpenLabel and OpenScenario are used to deliver interoperability and reusable data across diverse acquisition sources in the AVEAS Brave10K project to scale automated driving in public transportation.

SAE’s Ed Straub outlined ASAM’s collaboration with SAE J3259 (ODD taxonomy), while ASCS’s Alexander Walsh emphasized the complementary role of ASCS and ASAM in simulation, AI and HPC.

Industry collaboration continues at Vehicle Tech Week Europe

Vehicle Tech Week Europe, represented by ADAS & Autonomous Vehicle International, Automotive Testing Technology International and Automotive Interiors World, served as ASAM’s media partner.

Launching this June in Stuttgart, Germany, the three-day ‘festival of engineering’ will unite the full vehicle‑technology ecosystem – from EV and battery testing to autonomous‑vehicle development, UX/HMI, materials engineering and in‑cabin innovation – creating cross‑disciplinary value at a time when the industry faces intense technological and regulatory pressure.

ASAM is an association partner of Vehicle Tech Week Europe, and Yash Shah and Andreas Richter will continue their discussions about ASAM OpenX evolution and ODDs at the event.

Learn about Vehicle Tech Week’s partnerships here.

Find out more about ASAM’s International Conference, which will take place on November 4 and 5, 2026.

Related news, EXPO REVIEW: Automotive Testing Expo Korea 2026

AVL VSM is a flexible, real-time simulation tool that enables users to model components, systems and complete vehicles. It allows them to test vehicle dynamics and performance in realistic scenarios, which is crucial for optimizing vehicle characteristics and ensuring safety. VSM enables a more integrated approach to vehicle design and optimization by allowing simultaneous consideration of various vehicle attributes and components and how they interact.

When VSM is paired with an Ansible Motion driver-in-the-loop simulator, the user can test changes to the virtual model and refine chassis dynamics, powertrain driveability, ADAS and active safety function calibration with a virtual test drive.

“By combining AVL VSM with Ansible Motion driver-in-the-loop simulators, manufacturers can move critical decisions to the front of the development cycle, dramatically reducing physical prototypes and test iterations,” said Gary Newton, AVL’s vice president of business development. “This tool combination can have an enormous impact on timeline and budget. Imagine validating 70+ track scenarios per day in multiple conditions, surfaces and drive events. The result isn’t incremental improvement, it’s months saved and millions preserved.”

Salman Safdar, Ansible Motion’s business development director, added, “Through our continuing collaborative efforts with AVL, we’re developing new ways to conduct subjective and objective evaluations of qualified concepts much earlier in the vehicle design cycle. Connecting our simulators seamlessly with a feature-rich simulation environment like AVL VSM elevates the virtual vehicle development process for manufacturers seeking to shorten development times, realize cost savings and reduce environmental impacts.”

Related news, GRAS launches new KEMAR head and torso simulator for acoustics analysis

kAIros is part of Horse Powertrain‘s wider strategy to strengthen the competitiveness of advanced manufacturing in Europe through the use of AI in development, simulation and industrial operations. By combining advanced supercomputing with cloud platforms, the company aims to provide the computing power, security and scalability needed to support these activities and enhance its long-term innovation capabilities.

AI Factory to support industrial AI applications 

At the heart of kAIros is the Horse Powertrain AI Factory, supporting AI use cases across engineering and production, including model training, simulation and digital twins, with the aim of accelerating industrial innovation and real-world deployment. A key part of the concept is the generation of training data to help continuously improve models and digital twins over time.

These capabilities enable the company to run advanced simulations and optimize operations in real time across products, factories, warehouses and logistics, with Google Gemini Enterprise used to deploy AI agents across the business, helping reduce coordination tasks that add limited value.

kAIros also supports physical AI by linking real-world operations with virtual systems in real time. This enables systems to interpret their environment, support autonomous decision-making, and interact with cobots, automated guided vehicles and smart machines. Applications include automated video-based quality inspection, faster product simulation and robotics for process optimization.

A dedicated Center of Excellence will lead the development of internal AI capabilities, bringing together cross-functional teams to build applications and scale expertise across the organization. Alongside this, the AI Factory will support scenario simulation, algorithm optimization and the development of intelligent propulsion solutions to improve efficiency and predictive performance. The initiative also aims to build long-term industrial AI capability to support advanced manufacturing in Europe.

Patrice Haettel, COO of Horse Powertrain and chief executive officer of Horse Technologies, said, “Industry advances at moments when technology doesn’t just follow change – it drives it. With kAIros, we are taking a decisive step into a new era where AI can redefine speed, cost, efficiency and sustainability.

“Our goal is to turn data into knowledge, simulations into real value, and innovation into competitive advantage. Horse Powertrain aims to be more agile and reliable because we understand that AI is not just a tool and kAIros is among the first AI factories in Europe for the automotive industry.”

Related news, GRAS launches new KEMAR head and torso simulator for acoustics analysis

Guided by a shared vision of fully automated, CI/CD-connected development environments based on open standards and modern software practices, the suppliers aim to make HIL testing truly ‘soft’ – meaning software-driven –  as well as being flexible, scalable and seamlessly deployable. This is central to supporting the evolution toward software-defined vehicle architectures.

Gianluca Vitale, software global unit manager at AVL, said, “At AVL, our software strategy continues to evolve with a clear focus on accelerating development through end-to-end solution responsibility, positioning ourselves as an open integrator that enables customers to move faster and more efficiently.”

“Together with VCarSystem, we are introducing disruptive, end-to-end approaches that radically speed up software release cycles and E/E integration, offering a new benchmark for testing efficiency and development agility,” said Qi Chen, president of VCarSystem. “Partnering with AVL marks a significant step toward reshaping the future of vehicle development in the era of software-defined vehicles.

“As the industry shifts from hardware-bound architectures to software-driven mobility platforms, validation must evolve at the speed of software. Together with AVL, we are building an open, scalable testing ecosystem that accelerates function validation, shortens development cycles and enables continuous innovation throughout the SDV lifecycle – creating long-term sustainable value for our global customers and partners.”

Related news, MissionH24 accelerates hydrogen innovation with AVL Racetech simulation technology

McLaren can now explore more of the design space, run complex tests and simulations faster, and tune every component with greater precision. The platform also reduces manual, repetitive tasks through leveraging engineering agents.

Nick Collins, CEO of McLaren Automotive, explained, “This is a genuine strategic transformation for the business. By continuously compounding and optimizing our data, our intelligence and our engineering philosophies at unimaginable speed, we can deliver product developments at pace, while protecting the DNA of our company.”

The Rescale system is trained exclusively on McLaren data and uses Nvidia AI infrastructure, AI physics models and agentic engineering libraries. It connects McLaren’s CAE, systems engineering and design into a unified AI data fabric that continuously learns and optimizes, while adhering to McLaren’s quality standards and performance characteristics. 

“Our foundational platform allows McLaren to leverage the latest agentic engineering technologies powered by Nvidia AI infrastructure, providing a compounding source of competitive advantage for engineers in critical areas of product development, such as carbon materials, structural dynamics, durability and ultimately the programmatic scaling of engineering excellence across every discipline, to deliver world-class products faster,” said Joris Poort, founder and CEO of Rescale.

Tim Costa, VP and GM, computational engineering at Nvidia, said, “The future of automotive engineering is being rewritten by agentic AI and advanced simulation, turning decades of design heritage into a live, generative engine that accelerates every stage of the vehicle lifecycle. By integrating Rescale’s unified control layer with Nvidia’s open models for agentic AI and accelerated physics, McLaren is compressing years of traditional simulation into hours of real-time design exploration.”

Adding to its worldwide R&D network, Nexen Tire has established a new European base at UTAC Ivalo to refine winter and all-weather products. Having been a customer for over two decades, the tire maker is no stranger to the winter testing grounds – and engineers now have their very own area on which to experiment. Construction began in April 2025, with the Purple Snow Ivalo Center, as it has been named, opening in December.

The European market accounts for more than 40% of the company’s total revenue, and with major European countries including Germany, Italy, Czech Republic and Sweden now requiring the use of certified winter tires with the 3PMSF marking during winter, this new asset is vital for Nexen. As part of its multi-pronged approach to strengthening winter tire development, it has also opened a laboratory to study the surface characteristics of roads in cold weather.

“We had been talking to car manufacturers for several years, saying that we needed this kind of facility, and finally the company agreed to it,” says Brad Kim, CTO of Nexen’s R&D Center in Korea.

The Purple Snow Ivalo Center features snow handling tracks with varying gradients and curves, including a 1,400 x 600m ride and handling circuit with an 18 m difference between the lowest and highest points; a track for testing the durability of studded tires; and a large straight of 700 x 40m. Upon completion, surface variation across all tracks was just 3cm – a result of which both Nexen and UTAC are incredibly proud.

Having this permanent base is a game-changer for Nexen, boosting testing capacity and the accuracy of results. Previously, with limited time to complete all tests, there was no room for flexibility, and if analyses needed to be repeated for correlation, it simply wasn’t possible. “If we were suspicious of the test results, but only scheduled to have the facility for a certain period of time, then there could be a long queue to test again,” explains Kim. “Now we can repeat a test as many times as we want until we are confident of the reliability [of the results].”

Out with the old, in with the new

Last August, the Korean auto industry’s first highly dynamic motion simulator began operating at Nexen’s tech center in Seoul, which will work in tandem with the Lapland base. This close connection between virtual and physical testing has become essential. Performance predictions can now be immediately cross-validated through on-snow driving tests, reducing the disparity between the real and digital worlds.

It’s no surprise that Kim’s team places a strong emphasis on virtual evaluation, aiming ultimately to need only one physical tire per program for validation. The Ansible Motion driving simulator is the starting point for transforming the company’s entire development process, which, Kim candidly told ATTI, is still largely done the traditional way. “We do virtual tire development pretty much the conventional way. We are currently judging whether we can integrate virtual testing methods into our conventional foundation phases.”

Kim describes this approach: “We build a tire and then test it. If we are not satisfied, we go back, adjust the compound or the construction, and then do more vehicle tests. Everything is well-established for virtual tire development, because we have many projects, so we just continue with the conventional approach.”

With one engineer often working on multiple projects at the same time – one product line may have as many as 140 sizes, and last year Nexen developed 600 additional sizes in the replacement market – it’s easy to see why the company has invested so substantially in new testing infrastructure. “In terms of productivity, I think we are top-notch – one engineer could be working on 10-20 different projects,” Kim proudly states.

“Some things you can estimate or judge on a single tire, like rolling resistance or spring constant. But what we need is to equip these tires on a specific vehicle, and we’re not there yet,” he adds. “We’re pushing in that direction; that’s why we installed the driving simulator. It’s about subjective feeling; it’s very difficult to objectively judge whether this tire fits this vehicle.”

It’s early days in Nexen Tire’s simulator journey, but the team is cracking on with getting up to speed and commissioning the system. “We’re in the middle of the conditioning stage, but at the same time we have started to do some tests with the machine. Our drivers should feel as if they are really driving, so we are tweaking the mechanics together with our simulator supplier. If there’s a way of tweaking parameters in the software, then we can do it.”

Another facet of the company’s digital analysis is the continued development of AI. Engineers have created a unique artificial intelligence tool, which they say has revolutionized analysis. For example, developers can input multiple parameters and have it predict rolling resistance. “The speed improvement is incredible. For a typical simulation, it could take about one day to give you the result; AI can take five minutes to get the same result, so it’s like a competition between simulation and AI.”

Working together, AI and simulation can be used to predict a tire’s footprint, for example.

Softly does it

Kim emphasizes that Nexen Tire does not limit its pool of suppliers and encourages proposals from potential new partners. It works with many of the major suppliers – Synthos, KKPC, LG Chem, Arlanxeo – as well some Japanese synthetic polymer suppliers.

He reveals that tire maker is currently “testing new concepts of compounds that remain flexible in low temperatures, with good handling and braking performance,” adding that it is also assessing novel construction concepts, especially in the replacement tire arena.

Middle man

Step by step, Nexen is performing correlation activities to refine the driving simulator, learning along the way. The engineers are clearly enjoying playing with their shiny new toy, but they’re not afraid to admit that they’re still getting to grips with it. “We need to learn from it. We know how to use it, but still the whole industry is in a learning phase,” comments vehicle dynamics expert Yannic Grassmuck.

In the replacement market, the sim could save a fortune, since changing a mold mid-project is not cost-effective. This is especially true in the winter tire segment, where molds are expensive and take longer to produce due to the sipes.

One of Grassmuck’s primary responsibilities is to translate OEM feedback for the engineers. Feedback is recorded in writing and then shared with the relevant team. Occasionally, joint tests are conducted with both Nexen and the OEM’s drivers, “which is very important because every OEM has small differences in the maneuvers that they drive, and the drivers need to be aligned on the expectations,” Grassmuck says.

According to Grassmuck, it’s common for an auto maker to allow three attempts at a virtual prototype, followed by only one or two real test loops.

The sticking point on every digital program remains the same as always: obtaining a vehicle model from the OEM. Companies have become more willing to provide these over the past year or two, says Grassmuck, but “it’s difficult. Some are willing to, some can officially provide [the model] but the internal process takes too long and it’s not very productive, so they give other options; there’s a workaround, let’s say.”

Who knows, maybe in the future Nexen Tire’s experts could have a smaller simulator in Europe, adds Grassmuck, but for now, they’re not getting ahead of themselves. It is a major financial investment, and they first need to maximize the potential of the simulator in Korea.

More on UTAC’s facilities in the November 2025 edition of ATTI

Read more about Nexen’s AI tire performance prediction tool

Nexen first announced it was to install a driving simulator in 2024. Find the full story on the TTI website here

Signal Plot is a free, downloadable extension for CanKing 7.4.0 or later that allows engineers to track multiple signals simultaneously, zoom into events, compare values using cursors and switch between live and pause modes. The extension provides engineering-unit graphing directly within the CanKing workspace, making it particularly useful for HIL bench bring-up and on-site debugging.

“Our goal with Kvaser CanKing has always been to give engineers the clarity they need with as little friction as possible. Signal Plot does exactly this; turning raw CAN and LIN data into clear, meaningful visuals in real time. It’s a simple yet powerful upgrade that delivers an immediate boost in understanding and efficiency,” said Martin Sventén, CEO of Kvaser.

The update is designed to provide engineers with faster, more intuitive insights into system behavior, making real-time monitoring and debugging of automotive networks simpler and more efficient.

The extension is the first built on Kvaser’s CanKing Extensions SDK, which was launched last year, to enable users to create web-based GUI extensions such as dashboards, gauges and custom interpreters without modifying the core application. The SDK leverages React and is compatible with both Windows and Linux systems.

CanKing 7.4.0 also adds support for LIN message logging and replay using MDF4.x files. Improved MDF4.x compatibility ensures that LIN data frames are correctly recognised, enabling the Message Logger and Message Replay nodes to function seamlessly across both CAN and LIN traffic.

CanKing 7.4.0 was unveiled at at Embedded World 2026 in Nuremberg, Germany.

Related news, Kia focuses on NVH reduction in EV2 development

The DMG-X is a driver-in-the-loop (DIL) simulator developed for automotive OEM testing and development programs. The system is designed to support high-fidelity simulation for applications including ride comfort evaluation, and noise, vibration and harshness (NVH) testing.

According to Dynisma, the simulator delivers motion bandwidth exceeding 100Hz across all six degrees of freedom with latency of 3-4ms. The platform also provides vertical excursions of up to 400mm and supports payloads of up to 750kg, enabling testing with full-scale vehicle prototypes.

These capabilities allow the simulator to replicate real-world driving conditions with high accuracy, supporting development work throughout the automotive lifecycle from early concept phases through to series production.

The Advanced Driving Simulation Center is intended to support studies that bridge theoretical vehicle modeling with human driver perception in simulated environments. It will use the DMG-X for research and development projects with international automotive manufacturers.

Research conducted at the center will focus on areas including vehicle dynamics, ride comfort, NVH behavior, human-machine interface (HMI), advanced driver assistance systems (ADAS) and autonomous driving technologies.

Graeme Cook, the CEO of Dynisma, said, ” This installation demonstrates the increasing recognition of high-fidelity simulation as an essential tool for automotive development, and creates an ideal environment to showcase the transformational benefits our DMG-X technology delivers – significantly reducing development time, costs and environmental impact while accelerating innovation across every key area of vehicle development.

“Early-stage DIL simulations help engineers make informed decisions on aspects like suspension and body architecture, reducing the need for heavy NVH-damping materials, ultimately lowering vehicle weight.”

“The Advanced Driving Simulation Center allows us to conduct vehicle studies with results that precisely match the physical conditions of the real world,” added Arno Eichberger, head of the institute for automotive engineering, who is responsible for the scientific operation of the testing facility. “The new simulator closes the gap between theoretical vehicle modeling and the real human perception of our test drivers.”

The DMG-X installation at Graz University of Technology provides a highly responsive interface between the vehicle model and the driver. Integrated virtual reality systems enable immersive simulation of a wide range of driving and traffic scenarios, while extremely low latency supports a realistic driving experience and helps reduce motion sickness for test drivers.

Founded in 2022 by AI industry veterans Alan Patterson and Darren Garvey, BeyondMath has developed the world’s largest foundational physics model, which is capable of simulating complex physical phenomena, from aerodynamics to thermal management.

In automotive engineering specifically – where BeyondMath works with an F1 team – the platform supports real-time testing of thousands of design combinations to identify optimisations in aerodynamics and thermal management.

The funding will be used to scale up the commercial deployment of BeyondMath’s generative physics technology and increase its research capacity.

Alan Patterson, CEO of BeyondMath, said, “Engineering teams require ever-faster, more flexible simulation, but do not have the technology to deliver on these demands. Generative physics introduces a fundamentally new approach to engineering, unlocking innovation across fields ranging from aerospace and automotive to data-center design. We now have the capital and investor support to accelerate our research roadmap and scale commercial adoption. This could be the ChatGPT moment for physics.”

Edward Inns, principal at Cambridge Innovation Capital, added, “BeyondMath is tackling one of the hardest and most valuable problems in engineering. By combining first-principles physics with modern AI, the team has built a platform that can redefine how complex systems are designed across multiple industries. We look forward to supporting Alan, Darren and the team as they continue to scale.”

Related news, VI-Grade installs first HyperDock in North America at Multimatic facility