This presentation provides an overview of the ongoing activities of the European Commission in the field of assisted and automated driving. It will explain the regulatory framework, describe the current status and highlight current challenges and future work.

Removing the human driver fundamentally changes what we actually mean by acceptable safety. A simplistic 'safer than human driver' positive risk balance approach must be augmented with additional considerations regarding risk transfer, negligent driving behavior, standards conformance, absence of unreasonable fine-grain risk, ethics and equity concerns. Current standards frameworks and accompanying definitions are likely to be inadequate to ensure safety due to implicit assumptions that are violated when the human driver is removed. A framework relates risk to acceptable safety in a way that is applicable to all autonomous systems.

What the audience will learn

• Why positive risk balance will not give socially acceptable safety
• Examples of safety issues in the news beyond positive risk balance
• How we need to define acceptable safety for at-scale deployments

The hype surrounding autonomous vehicle development has seen a decline in recent years, as the industry has come to realize that mass production of full self-driving technology remains distant. However, productization of autonomous vehicle components, like ADAS Level 2, is advancing steadily within the latest multirange electric vehicles. This presentation brings a business strategy perspective to a tech audience, fostering interdisciplinary discussions on current market entry barriers in productizing autonomous vehicle technology and exploring strategies to accelerate the technology’s commercialization.

What the audience will learn

• Key market entry challenges for autonomous vehicle and ADAS software
• Strategies to overcome regulatory and commercial barriers in AV tech
• Insights on accelerating the commercialization of autonomous technologies
• The importance of interdisciplinary collaboration for future mobility
• Business-driven approaches to integrate AV tech in electric vehicles

The concept of Operational Design Domain is generally accepted to be an essential part of development, testing and approval of Autonomous Driving Systems but still a new concept without real best practice. We show how the idea comes true by contributing to standardizing a human- and machine-readable technical description format, building a proper taxonomy taking requirements of relevant stakeholders into account as well as implementing software to develop and manage complex ODD definitions.

A global team of 52 participants from 21 companies is developing ASAM OpenMATERIAL, a standard for 3D model and material properties to ensure simulation consistency. Releasing in March 2025, it defines physical properties (refraction, roughness) and structural hierarchy, supporting dynamic elements like wheels. Integrated with ASAM’s OpenX ecosystem, it promotes interoperability for movement, positioning and layouts, enabling reusable assets and enhancing sensor-specific simulations (e.g. lidar). The scope includes virtual traffic models but excludes environmental conditions, targeting robust, consistent simulations across automotive applications.

What the audience will learn

• ASAM OpenMATERIAL standardizes material properties and 3D model structures for accurate, consistent simulations
• ASAM OpenMATERIAL integrates with ASAM OpenX standards, supporting interoperability in simulation setups
• Standardized data improves sensor-specific simulations for lidar, radar and perception testing
• Practical applications and scope, focusing on virtual traffic models, excluding environmental factors like weather effects

This presentation explores the indispensable role of periodical technical inspections (PTIs) in maintaining the safety, reliability and compliance of vehicles equipped with advanced driver assistance systems (ADAS) and autonomous technologies. As these systems revolutionize transportation, regular inspections are essential to ensure their continued effectiveness and public trust.

What the audience will learn

• How PTIs ensure safety and reliability in ADAS and autonomous vehicles
• Understand how PTIs ensure compliance with safety and legal standards, reducing risks and building trust in ADAS and autonomous vehicle technologies
• Discover how PTIs prevent system failures, reduce repair costs and enhance performance through proactive maintenance of ADAS and autonomous vehicles
• Learn how PTIs build trust in advanced technologies and drive innovation by supporting data-driven improvements in ADAS and autonomous systems

Many companies in the ADS landscape see the complexity of regulations and standards as a major hurdle to efficiently create value in B2C and B2B contexts. While the ADS systems themselves are becoming more and more intelligent, the safety certification staff’s toolset does not leverage the power of connected information graphs and AI-enabled automation for creation and processing. This talk will introduce the major building blocks required to achieve digital continuous ADS safety certification and will give insights from many years of applied research to explain what the digital ADS safety certification ecosystem of the future could look like. Specifically, the relationship between approval and liability context, risk-based safety cases, the safety engineering work products as well as post-deployment safety monitoring will be analyzed in the context of digitalization needs and potential.

AI-driven systems introduce dynamic learning, adaptability and continuous updates, posing significant challenges to traditional homologation methods. The objective of this paper is to analyze the existing homologation methodologies, such as the New Assessment/Test Methodology (NATM), and examine how various institutions, including UNECE, JRC and SAE, address AI's incorporation into ADS certification. The discussion focuses on identifying gaps in current frameworks, evaluating the harmonization of principles like transparency, robustness and ethical accountability, and proposing a roadmap for future integration. Ultimately, the paper aims to highlight how harmonized approaches can ensure both innovation and safety in AI-enabled ADS.

What the audience will learn

• AI use cases and current trends
• A harmonized roadmap for AI in ADS homologation
• Key challenges in AI homologation
• Current Frameworks and their applications

The synergy between the evolving automotive landscape and advances in cloud computing, virtualization and AI has not only improved current technologies but also sparked transformative shifts. A solution is sought to tackle current challenges, including enabling testing in complex development environments, managing multiple variants/releases and addressing hardware bottlenecks. Elektrobit’s Test Grid platform solution is designed to meet the growing demand for seamless, platform-agnostic scalability in real and virtual test environments. It unifies all test assets, supports homogeneous invocations, enables effortless integration during early development stages and ensures hot-pluggability with existing CI/CD ecosystems.

What the audience will learn

• Adaptation of tooling to support real and virtual environments
• Achieving platform agnosticism
• Seamless integration into CI/CD ecosystem

The journey from groundbreaking research to scalable development in advanced driver assistance systems (ADAS) is a complex yet crucial endeavor. It involves transforming innovative ideas and findings into practical, real-world solutions that enhance road safety and efficiency. Achieving this requires synergistic collaboration between academia, industry stakeholders and regulatory authorities. By fostering a culture of shared knowledge, aligning objectives across sectors and investing in comprehensive testing and validation processes, we can ensure that cutting-edge ADAS technologies are seamlessly integrated into vehicles. This approach not only accelerates the adoption of advanced ADAS features but also sets the stage

What the audience will learn

• Software-defined vehicle layer model
• Current development status in ADAS/AD
• Where research and development need to work together more closely
• What the future of development and research could look like

We will discuss a suite of cutting-edge technologies that demonstrate our commitment to advancing autonomous and connected vehicle ecosystems, specifically tailored for the Indian and global markets. The software-defined autonomous vehicle provides a flexible and scalable foundation for integrating various vehicle functionalities. This software-centric approach allows for continuous SOTA and FOTA upgrades, enabling vehicles to adapt to new technologies and regulations without requiring hardware changes. Autonomous driving stacks are optimized for diverse road conditions and include advanced sensor fusion, real-time data processing and machine learning algorithms that enhance vehicle safety and performance.

What the audience will learn

• Software-defined autonomous vehicle features
• Autonomous driving stack – sensor fusion, perception, path planning and control
• Features update from the cloud

The concept of a software-defined vehicle (SDV) has become a hot topic across the automotive industry as automakers look for ways to address the complex software needs for functions like ADAS and autonomous driving. Many automakers and industry organizations have turned to open source software for SDV development, which has also led to an increase in contributions back to open source projects and the need for Open Source Program Offices to streamline and organize open source activities. Dan Cauchy, Executive Director of AGL, will discuss the current state of SDVs and the work being done by automakers and Tier 1s as part of the AGL SDV Expert Group. He’ll also provide insight into the driving trends behind SDVs and enabling technologies including virtualization, containers, and the cloud. Additionally, he’ll share updates from the recently launched AGL Open Source Program Office (OSPO) Expert Group, led by Toyota to help other automakers set up OSPOs, exchange information, and develop best practices

In the current work we propose a method to apply generative AI GAN methodology on a hardware-aware NN for lidar data. In order to improve the network semantic segmentation performance, we introduce a GAN network into the segmentation. The adversarial training encourages the model to generalize better by simulating a diverse range of conditions, improving its robustness in real-world applications. This increases the performance with regard to classical real and simulated data based training approaches. Once the NN is trained, we also apply several compression techniques to optimally reduce the latency of the NN for real-time processing of dense point clouds.

What the audience will learn

• Lidar
• Embedded NN for dense point clouds
• Generative adversarial networks

The AutoSeg Vision Foundation model is an artificial intelligence framework powering camera-based scene understanding for autonomous driving, developed by the Autoware Foundation. AutoSeg’s custom neural network architecture processes images and computes multiple perception outputs including semantic segmentation, 3D scene estimation, end-to-end path prediction and lane detection – forming the building blocks of autonomous driving. Combining AutoSeg with Autoware’s OpenADKit -offers a modular, scalable and cross-platform AI system which can be trained in the cloud, deployed on the edge and updated over-the-air as part of a holistic data pipeline, enabling autonomous cars to learn as they drive.

What the audience will learn

• Neural network architecture of the AutoSeg Vision Foundation Model
• How AutoSeg performs in real-world driving scenarios
• OpenADKit framework
• AutoSeg and OpenADKit full AI pipeline
• Autoware’s future vision for autonomous driving

Building a fully trainable AD stack is a promising approach to efficiently build and scale an AD system. Transformer neural networks using tokenization of diverse information into a common representation and attention mechanisms to efficiently combine data in time and space foster understandable and flexible end-to-end architectures. An enabler to follow the fast-evolving research in end-to-end is a toolchain allowing quick application of such architectures from training over simulation into closed-loop real-world vehicles. The presentation gives an overview of the toolchain and presents insights gained from tests in simulation and closed-loop applications in the real world.

What the audience will learn

• An overview of the end-to-end state of the art
• Why transformer neural networks have a huge impact on end-to-end
• An example of a toolchain fostering rapid end-to-end experiments
• Challenged and blocking points getting end-to-end architectures into a vehicle
• Insights into first closed-loop experiments with a closed-loop end-to-end AD stack

AI tools are increasingly being used in cyberattacks and defense mechanisms. This is shifting the paradigm of cyber defense by training the LLMs to simulate attack scenarios based on the industry and organization context. This includes the use of business data from the OEMs and Tier 1 suppliers to train the AI modules. Application testers can use generative AI to simulate sophisticated cyber attacks; emulate the exploitation of code configuration issues for preventative security; impersonate the system user by querying mechanisms for human interaction; or simply add context to threat technique identifiers within the Mitre Att&ck framework.

What the audience will learn

• The concept of AI and LLM in security testing
• Use cases
• Kill chain analsysis

From ChatGPT to generative world models for autonomous driving (AD), data for AI model training must be high performance, flexible and scalable. Data helps AI models identify and extract meaningful features from input data. The quality and depth of training data significantly affects the success of AI models. Training data provides examples and relevant information for AI models to learn from. This presentation will discuss AI-powered computing for AV development, data-driven development, and ways to accelerate AV development.

What the audience will learn

• Data for AI model training must be high performance, flexible, and scalable
• Quality and depth of training data significantly impact the success of AI models
• Data helps AI models identify and extract meaningful features from input data

The presentation will focus primarily on the evolution of AD stack from RL algos to diffusion models, and its impacts on robotics and, if data collection is not a challenge, then into autonomous driving.

What the audience will learn

• Google and Alphabet
• ML to AI in ADAS
• Recent advances in computing
• LLMs in motion control
• Outlook

This presentation will explore the role of SOTIF (Safety of the Intended Functionality) in ensuring continuous safety in autonomous trucking. Plus will share its strategy for ensuring the safe deployment of autonomous trucks across different scenarios and environments.

What the audience will learn

• Understanding the importance of SOTIF in autonomous trucking
• How Plus integrates SOTIF principles into its system development
• Key challenges and lessons learned from real-world safety testing

End-to-end AI (e2e AI) is drawing attention in the automotive industry, yet questions remain about its safety and practical application in Level 2+ to Level 3/4 driving systems. In this presentation, hear directly from Wayve, the pioneer of e2e AI, on how it is putting this transformative approach into practice. Learn how Wayve is addressing safety concerns without relying on traditional rules-based methods and why e2e AI excels at solving edge-case scenarios. Discover how this innovative approach is unlocking the path to safer, scalable and adaptable autonomous driving systems.

What the audience will learn

• How Wayve’s e2e AI approach addresses safety
• How Wayve’s approach does not rely on traditional rules-based methods
• Why Wayve’s AI is uniquely capable of solving edge-case scenarios
• Why this is a critical challenge for autonomous driving technology
• How Wayve’s AI is scaling systems ready for real-world deployment

Unlike traditional modularized autonomous driving based on high-definition maps, the end-to-end model DeepRoute IO introduced by DeepRoute.ai doesn't need high-definition maps and has been rapidly adopted by auto makers for series production. It's more human-like, and can handle complex scenarios while ensuring safety. In just four months, over 30,000 vehicles integrated with IO have been released for consumers to enjoy the convenience of smart driving. The presentation will share the paradigm shift brought by the end-to-end model and technology evolution behind it.

What the audience will learn

• Autonomous driving technology evolution in the past decade
• Why end-to-end model is better, what it's capable of
• Commercialization path for end-to-end autonomous driving

The presentation will cover vehicle automation and system ergonomics screening, automation of driving and co-action issues, and situation awareness and back-in-the loop issues.

The distinction between L2++ and L3 advanced driving systems is often blurred and overlooked. However, L3 systems introduce additional requirements for system safety, robustness and software architecture, posing significant challenges for many OEMs. Porsche Engineering's Guardian leverages years of experience in L3 safety and systems validation. This software component is designed to facilitate the transition from L2++ to L3, providing a robust, safe and standards-compliant solution. The Guardian's modularity allows for seamless integration into your existing system and serves as a high-level component that guarantees the safety of L3 trajectory planning.

What the audience will learn

• Challenges in the transition from L2 to L3 from a safety perspective
• State-of-the-art software architecture to guarantee the validation of your L3 system
• Flexible software component that facilitates the transition between L2 and L3

The purpose of this presentation is to highlight the current regulatory context for assisted and automated systems with regard to the driving task. The aim is to explain how the various regulatory bodies work together, and to present the principles of validation, throught the different pillars : safety audit, testing or simulation.

Detecting lost cargo on highways poses a critical and stringent challenge for Level 3 Autonomous Driving Systems (ADS), especially considering UN 157 (ALKS) requirements. This presentation will examine how functional safety and SOTIF considerations further complicate this task. We'll explore how to derive realistic acceptance criteria based on real-world accident data and translate them into concrete perception validation targets. The analysis will then map various collision avoidance maneuvers to their corresponding perception needs. Finally, we will evaluate the suitability of different sensor technologies to effectively meet these identified perception requirements for robust lost cargo detection.

After the hype of autonomous driving, the automotive industry has understood that higher-level autonomy increasingly requires the involvement of AI-based solutions. Nevertheless, current brute-force AI solutions need a tremendous amount of data and are computationally expensive, which leads to the long-tail problem in self-driving and thus the questionable reliability and profitability of AV business. On the other hand, automotive mass-production needs to enhance driver safety and its own sustainability, and to have new products with new technology to attract end users. Younger generations are obsessed with high-tech and want to see more increased autonomy in their vehicles, so many Tier 1s and OEMs are paying great attention to autonomous parking, smart summon, auto-reverse and highway pilot. With the recent technological advancements in automotive SoC, computer vision and robotics, realizing these advanced functions at a great scale is feasible, and thus L2+ is considered a very good intermediate step to leverage the autonomy level.

Shared autonomous services are transforming urban mobility, offering solutions to urbanization and climate challenges. For software and vehicle providers, addressing the specific needs of public transportation operators is key to creating impactful products. This presentation outlines the essential elements for developing autonomous public transportation services, drawing from the ALIKE project in Hamburg. Topics include designing accessible vehicles, navigating regulatory approval, creating user-centered digital booking experiences, increasing public acceptance and building efficient operational and software processes. Gain insights into the unique challenges and opportunities in integrating autonomous technology into public transportation systems to meet operator and passenger needs.

What the audience will learn

• Experiences from project ALIKE with partners Moia, VW and Holon
• The digital user experience in an autonomous public transportation service
• Software needs for managing an autonomous fleet
• Vehicle requirements for accessibility
• Insights from public acceptance studies

Autonomous driving will be key for the future of public transportation services. This session will highlight the potential of autonomous vehicles, focusing on the pioneering project KIRA (German for ‘AI-based regular operation of autonomous on-demand transport’), Germany's first Level 4 autonomous public transportation pilot. The project aims to integrate self-driving vehicles into the public transportation network in the Rhine-Main area. Currently, six vehicles operate autonomously in Darmstadt and the district of Offenbach, addressing driver shortages and contributing to the mobility transition. Based on KIRA, the presentation will provide valuable insights into technological and regulatory challenges while enhancing public transportation services.

What the audience will learn

• Main learnings within the KIRA project, technological and operational challenges, regulatory frameworks and strategies for enhancing user acceptance
• Insights into technological advancements and regulatory challenges faced during the implementation of the KIRA project
• Overview of the current state and future potential of autonomous driving technology in public transportation
• Approaches to scaling autonomous driving in Germany

FEV.io GmbH participates in the HiDrive project and has developed and tested AD highway driving function with V2V support for on-ramping areas. The setup of the toolchain, the development process and the engineering framework will be introduced within the presentation. During the preparation of this function, a simulation environment and a systems engineering approach were used to improve the development with automated test case derivation and vehicle tests on the proving ground. All of these elements helped to improve the development time and helped to make the results of this part of the project a success.

What the audience will learn

• Efficient systems engineering with automatic derivation of test cases from SysML models
• AD function testing on several levels from MIL to vehicle
• V2V support for complex driving scenarios
• Vehicle testing for complex driving scenarios of autonomous driving functions
• Automatic OpenDRIVE and OpenSCENARIO file creation from SysML models

The DLR eV German Aerospace Center's Institute of Vehicle Concepts presents the architecture and challenges of the automated vehicle concept U-Shift. The presentation will provide an insight into the fully equipped sensor setup, autonomous stack architecture and safety concepts. Further, it will dive into the key challenges and the center's solutions for developing a modular vehicle with an automatic capsule changing system that does not feature any driver seat. This includes topics about sensor layouts for lidar, radar and camera, collective perception built on V2X, special driving cases like capsule docking and how to get a permit for BuGa23.

What the audience will learn

• U-Shift – on-the-road modular vehicle
• Sensor setup of lidar, radar and camera
• Safety concepts
• Collective perception

The presentation will outline the project's history and experiences from Level 2 until Level 3: how to innovate and align with restrictions; creation of an ecosystem; setting up a L4 project and go live.

What the audience will learn

• Real use cases versus technology
• Technology evaluation
• What to avoid

This presentation explores the transformative potential of large language models (LLMs) in shaping the next generation of advanced driver assistance systems and automated vehicle technologies. It will provide an overview of research conducted at the Centre for Accident Research and Road Safety – Queensland (CARRS-Q), focusing on the innovative integration of LLMs across diverse domains. These include applications in cooperative intelligent transportation systems (C-ITS), augmented reality interfaces, digital twin technology and tailored solutions for rural and remote environments. The presentation will highlight how these advancements can enhance road safety and inform future developments in ITS.

What the audience will learn

• Use of LLM in conjunction with ADAS
• Future research in LLM/ADAS/AV
• How OEMs can join forces with academia to improve safety

Testing car safety functions is a challenging job. The lab setup is an efficient way to test different safety functions: we can perform repeated tests with the same scenario and road. The cost of testing is economical and reduces the test time. Car safety functions like AEB (autonomous emergency braking) and PI (pilot assist) can be tested in the lab. This presentation explains how we have performed in-lab safety function tests. This speeds up the homologation process for car safety functions.

What the audience will learn

• How homologation tests can be done in lab
• Testing car ADAS functions in lab using emulated solutions
• Demo of AEB and PI in the lab environment
• How lab tests can speed up the car safety functions homologation process

A comprehensive test strategy using sensor data is required to ensure the proper operation of computer vision-based perception and sensor fusion algorithms. This presentation highlights hardware-based data reprocessing as an essential method for validating perception. Major adaptation of recorded sensor data is needed during reprocessing to meet frequent software and hardware updates, board network changes and requirements like E2E security protection along the development process. The presentation also explains how to validate the proper function of replay systems, which can have a tremendous impact on test quality and development costs. Finally, a brief outlook on AI-supported testing is presented.

What the audience will learn

• When to pick hardware-based data reprocessing and why it should be made an integral part of the strategy for testing perception and data fusion ECUs
• The major advantages of adapting recorded data during reprocessing and why this can be a challenging task
• Challenges of using sensor interfaces in reprocessing testing and how to solve them
• How to prove the proper function of a data reprocessing system to further increase test quality
• How GenAI-based methods can help to reduce the costs of reprocessing real sensor data

Our presentation introduces a state-of-the-art closed-loop hardware-in-the-loop (HIL) simulation framework designed specifically for testing automotive embedded systems with real hardware. The focus of our project is the front video camera system from Bosch GmbH’s advanced driver assistance systems product line. We present design, tools, architecture, methods and proof of concept, while highlighting the management challenges encountered. Our research with the project no. 2019-1.1.1-PIACI-KFI-2019-00129 has been implemented with the support of the Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund.

What the audience will learn

• Bosch ECU testing environment and tools
• Development goals and strategy for closed-loop simulation
• HIL infrastructure and challenges in data injection to video ECUs
• Sub-model design and development for 3D rendering, vehicle dynamics and CAN simulation
• Introduction of a proof of concept for implementation of closed-loop system for testing automotive embedded systems with real hardware

NHTSA FMVSS 127 will become mandatory for SOP 2029 vehicles. US NCAP declared the new tests and probably EURO NCAP will follow. This means RFQs for improved AEB systems need to be published in 2025, latest 2026. The thermal camera industry is offering now cameras with reduced (but enough) performance to pass the tests at an indicative price tag of US$100 per camera. Focusing on lowering the imager resolution is one thing, but many other elements must be considered. The presentation will elaborate on these elements.

What the audience will learn

• The relevance of tehrmal cameras for NHTSA FMVSS 127
• The challange and key factors to note when embracing a thermal camera
• Ways to reduce BOM

The new UNECE Regulation No. 171 on driver control assistance systems (DCAS) established new minimum safety requirements for vehicle systems that assist drivers in longitudinal and lateral vehicle motion control. This presentation will analyze key elements of the DCAS regulation, in particular highlighting the innovative multi-pillar assessment approach to system design, physical testing and virtual testing. It will use this to discuss the anticipated evolution of the certification process and explain the future approach for type approval of automated driving systems (ADS).

What the audience will learn

• Understand the background that has led to the adoption of DCAS regulation
• The core elements of the multi-pillar approach to the DCAS regulation
• The transition to more comprehensive evaluations for the ADS regulation
• Understand ADS type approval in the UK in the context of the legal framework introduced by the Automated Vehicles Act 2024

Most studies in road safety show that more than 90% of fatal crashes are caused by human driver factors. The most common causes include risky driving behaviors, alertness and impaired driving. Based on data collected through existing vehicle sensors, the Safety-Coach identifies risks through four indicators directly related to the main human driver-related accident causation factors: speed, safety distance, vigilance and risky driving behavior. Each indicator is computed in real time, according to the risks identified by the vehicle's sensors, and displayed to the driver. To improve the driver's behavior, pertinent advice related to taken risks is proposed.

What the audience will learn

• New safety system dedicated to the improvement of driver's behavior
• Driving risk analyzed in real time
• Dedicated advice proposed for the driver-related risk taken
• Safety system proposing educational role toward more safe driving

This presentation will explore the presenter's experience with hardware integration in autonomous vehicle development aiming for scalabilty, focusing on the Common Architecture and Shared Technology (CAST) framework. It will discuss the unique challenges posed by long lead times for brackets and wiring harnesses in a rapidly evolving development environment and share challenges experienced during the integration process, such as handling the lack of requirements due to new technology, ensuring seamless, scalable integration of hardware components, stable interfaces and particularities of sensor and computing components.

What the audience will learn

• Scalable hardware integration in autonomous vehicles
• Insights into the CAST framework
• Managing long lead times for critical components in a software-centric environment
• Addressing new aspects in automotive hardware development due to autonomous transportation

If we want to estimate safety gains with simulation, how can we do this properly? There are choices in scoping, shaping and configuring a safety study with simulation. And how to model the current situation? V4Safety has set up a framework for prospective safety assessment using simulation. It provides instructions to make studies more transparent and comparable. Built on ISO 21934, it provides methods for baseline and an extensive overview of human models for simulation of human behavior in everyday and critical situations. The framework covers safety measures in policy, infrastructure and technology, demonstrated in nine vehicle-VRU use cases.

What the audience will learn

• What are the key steps in the V4Safety framework for prospective safety assessment with simulation?
• How to choose and elaborate a baseline approach?
• What are the key results from the V4Safety use cases with vulnerable road users?

Safety assessment has become one of the major interests in most developing countries to reduce road accidents and minimize traffic congestion. This has increased the need for conducting safety testing for autonomous vehicles (AVs) before actual deployment in real-world environments. In Malaysia, a guideline has been established for public road trials of AVs. However, these documents do not focus on a testing framework to evaluate the safety and security of AVs based on Malaysian driving scenarios. Therefore, a safety assessment framework has been developed that consists of five stages to evaluate the overall performance of AVs before deployment in real-world environments.

What the audience will learn

• Current trend for autonomous vehicle development in Southeast Asia countries
• Challenges for deployment of autonomous vehicle in developing countries
• Safety assessment framework for autonomous vehicles
• Integration of international standards for standard development
• Application of digital twin for safety testing

High-quality data collection and selection are the cornerstones of ADAS and autonomous driving development. This presentation explores key prerequisites for successful test drives on public roads, focusing on ensuring data completeness, consistency and relevance. Topics include reference sensor calibration, field-of-view simulation and real-time diagnostics. Additionally, the presenter will discuss strategies for selecting relevant data during collection and after ingesting with pre-selection algorithms to optimize storage and processing. Attendees will gain practical insights to overcome technical challenges and streamline the data pipeline for cost-sensitive system performance.

What the audience will learn

• Techniques for ensuring data completeness and consistency during test drives
• Best practices for reference sensor calibration and integration
• Strategies for real-time diagnostics and time synchronization
• Approaches to selecting relevant data during collection and after ingesting for pre-selection
• Solutions for fleet-wide data handling and post-drive analysis

Autonomous driving implementation continues its shift to use AI technologies. These technologies require new capabilities for the development and validation of the AV software. The presentation introduces key challenges and presents solutions for a data-driven autonomy development toolchain. The solutions enable both training and V&V, using real-world data, synthetic scenarios and abstraction to enable large-scale, productive development and V&V.

Future mobility solution development requires a high volume of data to be analyzed for both quality and quantity. ZF Group and Xylon are providing off-the-self solutions. Quantitative data analysis of ADAS/AD systems require precise and reliable annotations. ZF Annotate is a state-of-the-art AI-powered ADAS/AD perception validation solution that saves time and costs. ZF Visual is an ADAS/AD data analysis software with a strong focus on visualizations. It provides engineers with deep data insights throughout the complete development cycle. The Xylon logiRECORDER can fulfill the challenging demand of collecting high bandwidth data while showing live data at the same time.

What the audience will learn

• How ZF Group ensures a safer and smarter driving experience
• Benefits of state-of-the-art AI-powered ADAS/AD perception validation
• How engineers get deep data insights and quickly assess performance
• How ZF Group software solutions allow OEMs to close the validation
• How Xylon dataloggers support comprehensive ZF software tools

Increasing levels of driving automation in more complex ODDs demand effective ways to continuously develop and verify software across millions of virtual miles and thousands of driving scenarios. As a result, scalable MLOps and DevOps have become the engineering foundations underpinning those at the leading edge of AD technology. In this presentation, Arm and AWS join forces to discuss how cloud-to-car environmental parity can enable better testing coverage and faster time-to-market across the industry. Based on a practical SOAFEE-based case study, the presenters will explore the impact of adding the image signal processor (ISP) model into the virtual perception pipeline, and how a similar methodology can benefit OEMs, Tier 1 suppliers and AD software vendors.

What the audience will learn

• The pros and cons of different virtual ECU abstraction levels
• The advantages of cloud-to-car environmental parity for software development and verification
• Why images tuned for human vision may not yield best results for compute vision
• The importance of integrating a virtual model of the ISP into both AI training and testing stages

The presentation gives current insights into efficient data acquisition for ADAS and autonomous driving ECUs and how this benefits from a modular approach, enabling these setups to be reused for the next generation. It focuses on hardware and software mechanisms to tap out data during a test drive or on HIL benches. It also covers the decoupling of ECU internals with breakout boards, PCI Express as an alternative to ethernet when transferring data, and the advantages of decentralized setups. An architecture with an interface to simplify the integration of chip vendor or – in general – specific libraries, for example, bus simulation for diverse test scenarios. These design principles support precise and efficient data collection in increasingly complex systems.

What the audience will learn

• Advantages of both distributed and centralized logging
• PCI Express as a measurement interface for domain controllers
• Standards for ethernet as ASAM CMP and MDF4
• Software integration approach into a logger for vendor-specific software blocks

This presentation will provide insights into how AI is transforming the landscape of AD/ADAS and autonomy development. It will discuss emerging industry trends, such as the rising complexity of L2+, L3, and L4 ADAS systems and the growth of E2E ML-based architectures that necessitate new tooling solutions. It will highlight key AI technologies, including LLMs, neural reconstruction, sensor diffusion and world models, and illustrate how these can be leveraged to create innovative AI-powered interfaces and simulators that promise to be both scalable and closed loop. The benefits that these AI-driven advancements can bring to OEMs and suppliers will also be discussed.

What the audience will learn

• Recent trends in AD/ADAS that require novel AI solutions
• Relevant emerging AI technologies
• New opportunities for AI-powered interfaces
• New opportunities for AI-powered simulators
• Benefits to OEMs and suppliers

Driving simulators often struggle to accurately simulate vulnerable road users (VRUs) in safety-critical scenarios. We present a framework integrating immersive virtual reality and human motion capture with the CARLA driving simulator. This setup allows simulations where real human agents act as VRUs interacting with an AI-equipped ego car featuring advanced ADAS functions. It enables testing and validation of new ADAS features with real pedestrian behaviors, providing valuable data on VRU reactions in dynamic traffic environments. This approach enhances the realism of VRU simulations and supports the development and evaluation of safer, more effective ADAS technologies for real-world applications.

What the audience will learn

• An overview of SOTA driving simulators and their limitations, covering the behavior of vulnerable road users in dynamic traffic environments
• The capabilities of the framework that integrates the CARLA simulator with the VR Meta Quest Pro headset, involving real human agents as pedestrians
• The application domains and the use cases of the proposed VR+CARLA simulation framework

Interior sensing is transforming ADAS by providing critical real-time insights into driver attention, occupant behavior and in-cabin environments. Traditionally, ADAS has relied on external sensors like lidar, radar and cameras to monitor road conditions. However, the integration of interior sensing – such as driver monitoring cameras (DMC), interior radars and sensor fusion – is enhancing decision-making for ADAS in several ways. Driver state monitoring (DSM) helps ADAS assess drowsiness, distraction and cognitive load, enabling adaptive interventions. Occupant monitoring detects seatbelt use, passenger presence and postures to optimize airbag deployment and crash response. Sensor fusion enables context awareness.

What the audience will learn

• What insights driver state monitoring and occupant monitoring can provide
• How interior sensing will enhance decision-making in ADAS

Data visualization for an automotive presentation: the key is to abstract complex information into easily understandable graphics that convey insights quickly. The presentation offers a breakdown of how to approach data visualization in the context of the automotive industry, focusing on key areas such as production, sales, quality control and innovation.

What the audience will learn

• Usage inside autonomous driving
• Why data visualization matters for automotive design
• What to look for in data visualization tools
• Examples of data visualization
• Best practices for data visualization in automotive design

This presentation will cover the recent progress in in-cabin sensing, which goes beyond traditional driver monitoring systems, showing how it enables advanced occupant safety, comfort and health. Considering EU-NCAP's recent introduction of safety rating parameters, we will showcase relevant features, including occupant detection, localization, type classification and seatbelt use, in conjunction with real-time contactless vitals and face recognition promoting holistic passenger well-being and personalization on the go. This presentation will cover in-cabin use cases that enhance the consumer experience, required sensors like camera and radar, software elements and deployment channels that allow car manufacturers additional monetization opportunities by leveraging the hardware used for regulatory compliance.

What the audience will learn

• Enhanced occupant safety: understand recent progress in in-cabin sensing features and get insights into the near-term future
• Leverage AI and ML: learn how AI and ML can enhance the capabilities of in-cabin sensors beyond classical approaches
• Comfort and health monitoring: get insights into how real-time contactless vitals and face recognition reinforce holistic well-being and personalization
• Consumer delight and monetization: find out how to monetize already available (required) hardware while enhancing user experience
• Regulatory compliance: learn how to futureproof in-cabin architecture design in light of evolving regulatory compliance requirements

Agile methodologies are increasingly important in the automotive industry due to the market's evolving needs and challenges, such as the rise of software-driven innovation and shorter development cycles. Applying Agile methodologies to large-scale automotive projects requires tailoring practices to accommodate the complexities of automotive environments. OEMs can build an Agile approach by adopting a Scaled Agile framework for automotive, organizing teams around system architecture, aligning with automotive development cycles, handling compliance and safety standards, and integrating DevOps and continuous delivery. Agile methodologies enable OEMs to stay competitive and adapt to rapid technological advancements to meet ADAS market demands.

What the audience will learn

• Why Agile methodologies are becoming crucial in the automotive industry and the benefits of deploying them in ADAS projects
• How to apply Agile methodologies effectively in complex large-scale-automotive projects that involve software, hardware and mechanical teams
• Agile helps enable scalability for next-gen technologies and ADAS vehicles by adopting iterative approaches and reducing time-to-market
• Enhancing customer-centricity by prioritizing user feedback and rapid iterations; this fast responsiveness is essential for features like over-the-air
• Agile emphasizes early and continuous testing to reduce defects and to ensure liability, complying with functional safety (ISO 26262)

This presentation explores the critical role of traffic rule compliance assessment in the approval and authorisation of automated driving systems. By utilising roadside infrastructure within real-world testbeds, this approach facilitates the capture of key data to compare the driving behavior of operators under assessment with other road users in the same location and time. The discussion includes practical examples of compliance assessment and reporting, providing insights into how these evaluations inform regulatory decisions and strengthen public trust in AV technology. Ultimately, this assessment validates driving competency and ensures adherence to safety and traffic regulations.

What the audience will learn

• Traffic Rule Compliance Assessment in approval and authorisation
• Comparison of driving behaviour between operators
• Compliance assessment and reporting examples

To guarantee the precise validation of sensor models in harsh weather conditions, AVL has developed a weather chamber (1.700 qm) where rain and fog combined with various light conditions can artificially be generated. The weather hall allows the execution of complex, dynamic scenarios like Euro NCAP, AEB and VRU at different rain intensities, fog visibility ranges and light conditions. These scenarios can be simulated one by one in the digital twin of the weather hall including the respective weather influence. Thus good alignment of the sensor model in the simulation with the results of the real measurements can be achieved.

What the audience will learn

• Impoving the robustness of ADAS/AD sensors
• Validation of ADAS/AD sensor models for enabling virtual homologation
• Extending the ODD limits and the availability of ADAS sensors

AnteMotion revolutionizes ADAS and autonomous vehicle development with an automated toolchain that transforms HD maps into OpenDrive files and procedurally generates high-fidelity 3D simulation environments. These environments are optimized for real-time performance, supporting advanced simulation scenarios while reducing time and costs. Seamlessly compatible with industry standards like USD and Unreal Engine 5.3, AnteMotion ensures robust and immersive virtual testing for perception stack development and DIL. By addressing the scalability challenges of manual methods, AnteMotion accelerates innovation in automotive technologies. Discover how our solutions empower developers to meet the growing demands of ADAS and AV systems with unparalleled efficiency and precision.

What the audience will learn

• Automating HD maps into OpenDrive for seamless simulations
• Generating high-fidelity, real-time 3D environments automatically in open standards
• Integrating simulation environments via USD or Unreal Engine
• Overcoming challenges in manual simulation content creation for ADAS/AV development

China is currently leading in vehicle automation. Most of the Chinese OEMs have so-called Level 2++ systems on the market that largely automate driving but still require a driver supervising safe system operation. These 'navigation on autopilot' systems under normal driving conditions take over all driving tasks until a pre-set destination is reached. Drivers can enjoy hands-free driving and only need to keep their eyes on the road. Everything else is handled by the system. Using ECARX's navigation on Autopilot system as an example, this presentation describes the latest developments in the field.

What the audience will learn

• The latest developments in the Chinese ADAS market
• Ways to bridge the gap between driver assistance and autonomous driving
• Different directions of ADAS development in China and the rest of the world
• Why China is faster

The development of automated driving systems requires reliable, interoperable map data for navigation, ADAS and other safety features. Overture offers an open data platform that provides high-quality base map data for driver-facing and machine-readable applications. By establishing interoperability for automotive data layers such as traffic, hazards and parking information, Overture enables OEMs and suppliers to build unique map products that enhance user experiences and unlock new revenue streams. This presentation explores how Overture addresses challenges in mapmaking and standardization, empowering the automotive ecosystem to leverage vehicle-generated data, improve map quality and drive scalable solutions for advancing automated driving.

What the audience will learn

• How collaborative mapping addresses challenges in automated driving data integration
• The role of interoperability in enhancing geospatial solutions for OEMs and suppliers
• Insights into vehicle-generated data utilization for reliable and scalable innovation
• Practical strategies for leveraging open map data in navigation and ADAS
• How open data standards enable collaboration across the automotive ecosystem