Webinar: Functional Safety in Autonomous Driving: HARA Fundamentals and Practical Automation

#autonomous-driving #control #functional #safety #robotics #systems
Share

In the rapidly evolving landscape of autonomous and highly automated driving, functional safety serves as the bedrock of public trust and system reliability. Central to this discipline is Hazard Analysis and Risk Assessment (HARA), a rigorous framework designed to systematically identify potential malfunctions and evaluate the resulting hazardous events within diverse operational scenarios. By examining the interplay between severity, exposure, and controllability, safety engineers derive Automotive Safety Integrity Levels (ASIL) and establish the foundational safety goals required for robust system architecture.

Despite its criticality, traditional manual HARA processes are increasingly challenged by the complexity of modern vehicular systems. Conventional methods are often marred by inconsistency, significant time investment, and limited scalability, relying heavily on subjective expert judgment. To transcend these limitations, we introduce G-Assess—a pioneering automation tool engineered to augment human expertise. By generating candidate hazards and suggesting data-driven risk ratings, G-Assess enhances traceability and accelerates the safety analysis lifecycle. This synergy between automated precision and expert oversight ensures a more consistent, complete, and safety-driven design process for the next generation of mobility.



  Date and Time

  Location

  Hosts

  Registration



  • Add_To_Calendar_icon Add Event to Calendar

Loading virtual attendance info...

  • Contact Event Host
  • Starts 19 May 2026 11:00 PM UTC
  • Ends 08 June 2026 01:59 PM UTC
  • No Admission Charge


  Speakers

Dr A. Arab

Topic:

Functional Safety in Autonomous Driving: HARA Fundamentals and Practical Automation

Biography:

Dr. A. Arab directs the Agile Safe Autonomous Systems (ASAS) Lab at the City College of New York and NYU, and is co-founder and CEO of General Autonomy Inc. His research integrates control theory, AI, and formal verification for safety-critical autonomy, with contributions spanning ISO 26262-aligned validation frameworks, scalable edge-case testing, and generative AI tools for hazard identification. Recent work introduces vision-language observer architectures for real-time semantic hazard detection. He also contributes to global safety standards through UL and IEEE committees.