This study investigates the integration of model-based system engineering (MBSE) into ISO 26262 processes, focusing on the idea of independence in safety-critical automotive systems. This idea is borrowed from other domains, like DO-178C for aviation, and extended with back-to-back testing. Practices and tools commonly used in MSBE will be examined, and their place in the verification and validation process will be shown. The role of independence at various safety integrity levels will be examined. Finally, a case study will be presented to show how this can be achieved with existing tools and processes.

The automotive industry is undergoing rapid transformation with the introduction of new vehicle architectures and software-defined vehicles, alongside advanced processing platforms. This shift creates a wealth of innovative data-driven opportunities. In this presentation, Dr Xiao will explore real-time HD semantic map solutions designed to enhance parking experiences and enable Level 4 autonomous parking systems. The solutions use low-cost sensors – surround-view cameras – to create sharable parking lot maps. These maps, stored in the cloud, provide real-time updates on parking spot availability and type (EV, handicapped, etc). Dr Xiao will explain how these advancements lead to smarter, more efficient parking solutions.

Explore the future of autonomous transit with our autonomous rapid transit (ART) system, as we explore its real-world applications in enhancing transportation services for airports and public transit. We will share several ART operations utilizing full-size buses and ADA-compliant vehicles, alongside an innovative ART airport people mover project that integrates electric buses and a vehicle management platform. We will discuss the implementation process and lessons learned in adopting these solutions. Join us and uncover how ART offers faster deployment and reduced total costs while meeting safety requirements, making it a game-changer for the autonomous transit market.

It seems that on a weekly basis we see another accident or incident involving the apparent failure of an AV or ADAS. Regardless of the frequency of these incidents, they are used as fodder by the media to frighten the public, earning more clicks and add revenue. We've seen AVs jamming up streets, hitting cyclists, dragging pedestrians and a recent tragedy where a Ford MachE ( supposedly with Blue Cruise engaged) struck a stopped vehicle on a highway, resulting in a fatality. I will discuss my opinions as to why such incidents happen and propose technical solutions to reduce or eliminate these issues in the future. Solutions can take the form of better or increased sensors on vehicles or more robust localization and communication systems. There are also many investments that can be made around infrastructure, which could greatly improve the safety and efficiency of ADAS and AV systems. I will discuss a few of these technical approaches (including V2V and V2X) as well as who should be paying for them.

As ADAS technology proliferates in passenger vehicles, there is a pressing need to understand how aftermarket modifications may affect the functionality of these systems. To address these challenges, SEMA stays at the forefront of research and testing, particularly with rapidly evolving vehicle technologies such as ADAS and autonomous features. In this presentation, SEMA will share the results of its groundbreaking research projects that tested the effects of various aftermarket modifications (suspension lifts) on the ADAS functionalities in a Chevrolet Silverado and Ford F150, including lane departure warnings/lane-keeping assist, forward collision warnings/automatic emergency braking, blind-spot detection and rear cross-traffic alerts.

Four lines of defense to a safer vehicle: process – build what you specify (automotive SPICE); functional safety – ISO 26262:2018; safety of the intended function – ISO 21448; cybersecurity ISO 21434.

As the automotive industry advances toward higher levels of vehicle autonomy and vehicle-to-everything (V2X) communication, cloud-based services will play a larger role. While the ISO 26262 standard sets functional safety requirements for software running inside the vehicle, cloud-based applications must adhere to the same requirements. Swift Navigation’s Skylark Precise Positioning Service is a cloud-based GNSS corrections service running on AWS that provides vehicles with high-accuracy location data for precise navigation, ADAS and autonomy and V2X communication. Skylark recently achieved ISO 26262 certification, elevating the role of GNSS in the automotive sensor suite and setting a design pattern for the development of cloud-based applications used for safety-critical use cases. Learn more about the service architecture and cloud infrastructure used to ensure compliance with safety standards while leveraging the unique benefits of the cloud.

This session will present a vision for how connectivity technologies can meaningfully support advanced driver assistance systems (ADAS) worldwide. The 5GAA roadmap for advanced driving includes both wide area and local broadcast communications and shares a vision for how they can augment ADAS solutions. Attendees will learn the immediate and near-term benefits of vehicles equipped with 5G modems and gain insight into the regulatory and standards headwinds to overcome.

Battelle is assisting the Federal Highway Administration (FHWA) with research to develop realistic and easily changeable mock roadway features (e.g. curbs, pavement markings, barriers, vegetation) to rapidly create and take down diverse scenarios for testing automated driving systems (ADS). These realistic, lightweight, portable (mock) roadway features will enable proving grounds and other facilities to increase their testing adaptability and agility without having to invest in expensive infrastructure upgrades. We will present several concepts under development – including foam curbs, removable pavement marking and lightweight concrete barriers – and the methods used to develop and test them (e.g. sensor signatures, likeliness and durability testing).

The presentation will show how, through automating the use of formal methods via abstract interpretation among other techniques, enterprises can alleviate the tester burden, reduce iterations generated by penetration, fuzzing and unit testing, and allow developers to focus on high-value tasks. This unique approach, which combines static and dynamic analysis, was recommended by NIST (NIST.IT.8151) and the White House's ONCD, and has the additional powerful advantage that it yields no false negatives. This means a guaranteed absence of undefined behaviors like buffer overflows. We will further demonstrate how developers can comprehensively verify software properties and produce critical-bug-free code, ensuring memory safety.

As Level 3 ADAS functions continue to dominate vehicle roadmaps in the short term, testing these ADAS functions adequately is a continuing challenge for the automotive ecosystem. In this session, Rohde & Schwarz will introduce two new test methods for ADAS testing: the optimized, cost-effective on-vehicle radar test and combining V2X with the sensor HIL test for pre-road test reliability tests. The session will share initial project/demo descriptions, key learnings and potential application areas for these new test methods.

Validation of automated driving functions, especially for SAE L3, has become a challenging aspect of new vehicle development. Large quantities of tests have to be performed in different environments. Complex SIL and HIL setups and highly scalable cloud simulations are necessary to cover the required testing. In ISO 21448 (SOTIF), sampling is a central component and focuses on targeted parameterization and variation of scenarios. In this presentation, the audience will learn about the SOTIF standard and its effect on vehicle development. We will also present a scalable, virtual toolchain solution for automation, parameterization and efficient, targeted analysis of the test.

Explore the critical role of perception simulation in developing safe and reliable autonomous vehicles. This keynote offers an in-depth look at aiMotive's aiSim and its capabilities in simulating real-world sensor data to train and validate perception systems. Learn how aiSim empowers engineers to create highly realistic and challenging scenarios for perception algorithms, ensuring they are prepared for complex road environments. Discover the impact of perception simulation on accelerating the development of AI-driven perception in self-driving technology.

Estimating connected and automated vehicles' (CAVs) energy impacts is challenging due to the non-linear dependence between CAVs' interactions with the environment and the scarcity of real-world data. To overcome these limitations, an 'anything-in-the-loop' (XIL) workflow has been developed. The XIL workflow integrates various CAV controllers into real powertrain components or vehicles in a safe, controlled and highly repeatable experimental environment, enabling a thorough validation and analysis of functionalities, dynamic performance and energy impacts. The presentation provides an overview of the workflow tasks and highlights achievements in energy conservation and insights into validating a multivehicle simulation leveraging experimental results.

An essential methodology that every ADAS/AD project must leverage is hardware-in-the-loop testing (HIL). While traditional HIL testing is more accurate than SIL, it runs orders of magnitude more slowly than cycle-for-cycle software-in-the-loop testing. Complexity, cost and deployment challenges limit scalability. In this session, Ambarella, in cooperation with Dell, will introduce a new methodology that delivers a low-cost, scalable server-based HIL rig simulation architecture that matches or exceeds the speed and accuracy of traditional HIL rigs for AI model verification with the flexibility of on-premises and/or remote deployment.

Ontario Tech University/Automotive Centre of Excellence's core research facility will share the journey of the precipitation characterization and testing functionality of ADAS for soiling due to weather impacting the vehicle sensors and detecting targets. Ontario Tech and ACE are leading the way in developing new, advanced development routines and testing methodologies for real-world weather conditions. The world-class Climatic Aerodynamic Wind Tunnel and other environmental chambers provide testing in rain/snow/ice/fog in varying temperatures and humidity. ACE provides calibrated rain/snow/ice/fog precipitation characterization that accurately and repeatably reproduces real-world performance of lidar, radar, cameras and other optical sensors in full vehicle operation.

The safety of autonomous systems is one of the challenges addressed by the CVH project at IRT SystemX through simulation. One of its aims concerns perception, considering physically realistic simulation of sensors, from a hardware point of view on one hand, and modeling of the environment on the other hand. In the case of radars, the applied methodology comprises four main topics: building the virtual sensor, modeling virtual targets, describing simulation scenarios and characterizing the phenomenological model of perturbations. This paper discusses modeling virtual targets, in order to demonstrate the relevance of our methodology through quantified results.

Both these AD approaches utilize sensors, hardware, processors, cameras, etc, but their integration and computing power requirements are different. The presentation will examine where the concepts diverge and determine if there is a direct path from one to the other. Another essential factor to consider is how the vehicle perceives the immediate environment. Different mapping options – HD Maps versus mapless – will be presented and compared.

Analysis of the current state of development of autonomous vehicle technologies requires a critical analysis of the requirements and key elements of autonomous driving systems, in particular visualization systems. The report focuses on emerging trends in lidar sensor technologies to improve the performance of autonomous vehicles. New trends include new optical sensors with improved performance, fast response principles of lidar sensors, optical laser beam distribution systems – particularly diffractive optics, and a new method of obtaining information in a visual camera format with distance information (possibly in color), which allows users to analyze information based on artificial intelligence on a chip and others.

The presentation will cover challenges with traditional lidar calibration, advantages of targetless calibration, use cases and applications and Deepen AI's targetless calibration.

Expand your operational design domain (ODD) and cover new geographical regions by fine-tuning large language models (LLM) and augmenting autonomous driving scenarios with abstract knowledge of standards, regulations and laws.

The presentation will provide an introduction to in-vehicle network (IVN) security, including TSN standards and industry adoption, security architectures and multilevel security validation.