AVL and QinetiQ have signed an MoU to collaborate on the use of model-based system engineering (MBSE) and digital twin solutions to develop and bring into operation new defence and commercial vehicles.

The partnership will see the delivery of new digital and real-world testing and evaluation services at QinetiQ’s Hurn Proving Ground in the New Forest in the UK, with AVL providing advanced vehicle modeling and simulation services as well as a digital twin of the Hurn facility.

Defense platforms and mobility programs require an integrated capability that unites physics-based modeling, digital twin and virtual and field testing across diverse operating environments, the companies said.

Continue reading AVL and QinetiQ partner on digital twin of UK vehicle test facility at ADAS & Autonomous Vehicle International.

A new AI-based framework called AdvWT, developed by Seoul National University of Science and Technology (SeoulTech), has been used to demonstrate how naturally occurring damage to traffic signs can cause DNN-based vision systems to misclassify them. Testing the model across multiple AI architectures showed attack transferability and physical-world robustness, with researchers stating that training models with AdvWT-generated damaged signs could help identify vulnerabilities and improve AI generalisation to real-world damage.

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.

Continue reading SeoulTech develops AI framework to assess vision-system robustness at ADAS & Autonomous Vehicle International.

Five AI, part of Bosch Mobility, has announced plans to develop simulation technology aimed at helping automotive manufacturers and suppliers develop autonomous vehicles more safely, quickly and cost-effectively.

Backed by UK government funding through the CAM Pathfinder program, this new technology combines Gaussian scene reconstruction and generative AI techniques to create highly realistic digital representations of real-world environments. The company has been creating and using simulation software for automotive manufacturers since 2015.

Gaussian scene reconstruction converts images captured from the real world into photorealistic 3D environments that can be rendered efficiently in a simulation. It allows developers to recreate roads, junctions and other driving environments with a level of realism that is otherwise difficult to achieve at scale.

Continue reading Gaussian scene reconstruction and AI to be used to accelerate AV simulation at ADAS & Autonomous Vehicle International.

Hyundai Motor Group has named Junghyun Kwon as its new executive vice president and head of the Autonomous Driving Development Center. According to the company, Kwon will be pivotal in advancing Hyundai’s autonomous driving capabilities. He will report to Minwoo Park, president and head of the advanced vehicle platform division.

Kwon is an autonomous driving AI expert who has worked at leading global tech companies. He oversaw autonomous driving software development and commercialization at Nvidia. Most recently, Kwon led intelligent robot development at Samsung Electronics.

Drawing on his deep expertise in autonomous vehicle perception software, deep learning, machine learning and computer vision technologies, Kwon will lead the group’s autonomous driving technology development from conception through product commercialization.

Continue reading Junghyun Kwon appointed executive VP and head of the Autonomous Driving Development Center at Hyundai at ADAS & Autonomous Vehicle International.

UK software specialist rFpro has added Solectrix‘s SXIVE (Simplified eXtensive Image and Video Engine) image-processing technology to its AV Elevate platform, enabling engineers to design, model and optimise the entire camera pipeline in simulation. By facilitating development before physical prototypes are available, the solution allows sensor optimization and training dataset production to shift earlier in the development cycle, significantly reducing costs.

The integration will support the tuning of image signal processing (ISP) and camera parameters against edge cases, the training of perception models with SXIVE-processed synthetic data and testing complete vision pipelines under highly variable conditions.

The update brings Solectrix’s software-based ISP into rFpro’s camera model, enabling engineers to optimize key processing steps directly in simulation, such as debayering, color correction, tone mapping, denoising, lens distortion and lens shading correction.

Continue reading rFpro and Solectrix offer solution for the rapid development of camera systems at ADAS & Autonomous Vehicle International.

Deontic will present ‘Simulation-First Validation: Turning Autonomy Requirements into Regulator-Ready Scenarios at Scale’ at the free-to-attend conference taking place at this year’s Intelligent Vehicle Expo North America (October 27-29, 2026), in Novi, Michigan. The Intelligent Vehicle Conference will discuss the technical solutions needed to secure public purchasing, ensure passenger safety and drive continuous lifecycle value. AAVI recently caught up with Deontic’s co-founder and CEO, Stephen Lernout, to find out more.
How can your company help with ADAS and autonomous driving development?

Deontic is a Belgian AI company building a validation intelligence layer for ADAS and autonomous driving development.

Continue reading EXPO INTERVIEW: Deontic discusses simulation-first validation at ADAS & Autonomous Vehicle International.

The Abu Dhabi Autonomous Racing League, A2RL, has announced its international racing debut will take place on September 5, 2026, in Imola, Italy, with up to five fully autonomous race cars based on the Dallara Super Formula SF23.

Organized by ASPIRE, the grand challenges arm of Abu Dhabi’s Advanced Technology Research Council, A2RL has evolved from a bold public testbed for AI under extreme race conditions into a competitive racing series.

Reigning A2RL champion TUM (Germany) will compete alongside Unimore Racing (Italy) and PoliMOVE (Italy) at the iconic racetrack in Imola, having qualified through their performances during the 2025 season.

Continue reading Autonomous racing series A2RL to make international debut at Imola at ADAS & Autonomous Vehicle International.

Under Euro NCAP’s 2026 protocols, the weighting of driver and occupant monitoring systems on a vehicle’s safety rating has significantly increased, and advanced driver distraction warning (ADDW) will become mandatory for all new vehicles from July 2026 under the EU’s General Safety Regulation. The challenge for OEMs and their suppliers is that these systems must work reliably across a vast range of real-world conditions and testing them physically is slow, expensive and limited in scope.

To address this, rFpro has launched the AV Elevate In Cabin add-on package, which 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.

Continue reading rFpro launches AV Elevate In Cabin driver and occupant monitoring simulation tool at ADAS & Autonomous Vehicle International.

Helm.ai has launched next-generation foundation models, GenSim-3 and VidGen-3, which it says are the first to achieve native full-HD (1,920 x 1,080) resolution across a full six-camera, 360° surround-view suite. By rendering a 12MP fully synchronized synthetic canvas per timestep, Helm.ai reportedly delivers five times higher pixel density than current state-of-the-art benchmarks for generative world models.

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).

Continue reading Next-generation Helm.ai models deliver full-HD 360° synthetic driving environments at ADAS & Autonomous Vehicle International.

Simulation software specialist rFpro has launched an engineering-grade digital twin of Japan’s Hakone Turnpike. The 15km toll road, which climbs through the forested mountains of Kanagawa Prefecture, is widely used by Japanese vehicle manufacturers for vehicle dynamics development. The model is commercially available and has already been adopted by a major Japanese OEM.

“Vehicle manufacturers are being asked to bring new models to market faster, at lower cost and with more variants than ever, and the only way to do that is to move more of their development work into simulation,” said Catherine Wood, head of content at rFpro.

Continue reading rFpro develops Japanese test route digital twin for virtual vehicle development at ADAS & Autonomous Vehicle International.