Blog

As AVs transition from research labs to public roads, ensuring the reliability of safety-critical functionalities, such as emergency braking, becomes paramount. These systems must operate with uncompromising quality and consistency, regardless of the complexity or number of other vehicle functions running in parallel. This presentation explores strategies to maintain the integrity of safety-critical systems whileRead more

As autonomous vehicles progress toward widespread deployment, ensuring their safety is paramount. a comprehensive approach to system safety, focusing on methods to identify, assess, and mitigate risks across the entire autonomous driving technology stack considers rigorous safety protocols at every stage of development and deployment, from safety-critical sensor fusion to fail-safe mechanisms and real-time decision-making. TheRead more

The perception and classification of moving objects are crucial for autonomous vehicles performing collision avoidance in dynamic environments. LiDARs and cameras tremendously enhance scene understanding but do not provide direct motion information and face limitations under adverse weather. Radar sensors work under these conditions, including rain, fog, and snow, and provide Doppler velocities, delivering direct informationRead more

This talk examines the core architectural choices in autonomous driving: modular, model-based ADAS versus end-to-end deep learning. Modular systems offer interpretability and compatibility with safety standards like ISO 26262, while end-to-end approaches promise greater adaptability through data-driven learning. However, the latter challenges current validation and certification frameworks. We explore technical trade-offs, real-world deployment implications, andRead more

Verification and validation processes play a vital role in ensuring the safety and reliability of automated driving. Scenario-based testing has emerged as an effective method for identifying critical scenarios that challenge the capabilities of automated driving systems. This presentation aims to explore how to leverage the potential of Generative AI for traffic scenario generation. TheRead more

Ensuring the safety of AI in safety-critical systems is essential for the deployment of automated driving technology. While AI has demonstrated its potential to surpass classical approaches in handling complexity and enabling higher levels of autonomy, the necessary safety assurance frameworks remain underdeveloped. This presentation will provide a forward-looking perspective on the interdependencies between AIRead more

Imagine a self-driving car navigating a busy city street. It detects pedestrians, reacts to sudden obstacles, and ensures passenger safety – all in milliseconds. But behind the scenes, hidden from view, lies an invisible force that makes it all possible: the C and C++ compilers and libraries that transform complex ADAS software into machine-executable code.Read more

This presentation explores the development of autonomous vehicle architecture, focusing on the core modules of perception, decision-making, and actuation. These modules are essential for environmental data collection, decision-making, and execution of driving actions, which form the foundation of autonomous vehicles. With increasing demands on autonomous systems, the need for greater computing capacity and the integrationRead more

This talk provides an in-depth analysis of the SOTIF standard and the ISO PAS 8800, elucidating their roles in guaranteeing the safe integration of AI into AVs. It highlights the potential risks of non-compliance associated with inadequately regulated autonomous driving technologies. Furthermore, methodologies for assessing the safety of autonomous systems are explained, including risk analysis,Read more

The growing complexity of automotive embedded systems has led to an increasingly critical need for safe and secure software. Traditionally, safety and cybersecurity verifications are conducted separately, resulting in duplicated or tripled V-cycle efforts. This talk explores how formal methods empower C/C++ and Rust developers to proactively address specific categories of vulnerabilities and bugs inRead more