Advance Program

Program-at-a-glance


Advance program

Opening of the fifth Automotive Reliability and Test Workshop 2020

General Chair: Yervant Zorian, Synopsys (US)
Program Chair: Paolo Bernardi, Politecnico di Torino (I)

Keynote: Oscar Ballan – Ethernovia (US)

The role of safety at component level for AD, ADAS and other dependable applications

Abstract: How the concept of safety in the broader meaning is distributed along the Automotive supply chain, in particular for Autonomous Drive and Advanced Driver Assistance System applications. Will be presented an approach based on hands-on experience for FuSa and safety engineering in general from a component vendor perspective when dealing with the Automotive and other safety related markets.

 


Technical session 1 – About adoption of Software Test Libraries

Moderator: Nilanjan Mukherjee, Mentor, A Siemens Business (US)

State of the Art Software Test Libraries (STL) and ASIL B. Truths, Myths and guidance
Priyanka Viswanathan, Antonio Priore, Peter Harrod, John Penton, Mukesh Lahori, Naresh Menon
Arm Ltd, Cambridge (UK)
Keshav Mathur
Arm Inc, Austin (USA)
Alexander Griessing
exida (DE)

Software Test Library for Artificial Intelligence-Based Applications
Davide Piumatti, Annachiara Ruospo, Andrea Floridia, Riccardo Cantoro and Ernesto Sanchez
Politecnico di Torino (IT)


Technical session 2 – Test and Reliability scenarios

Moderator: Michele Portolan, TIMA (FR)

Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles
Zahra Ghodsi and Siddharth Garg
New York University (US)
Siva Hari, Iuri Frosio, Timothy Tsai, Alejandro Troccoli, Stephen Keckler and Anima Anandkumar
Nvidia (US)

Degradation modeling and validation – bottlenecks for standard use of aging simulations in IC design
André Lange and Roland Jancke
Fraunhofer IIS/EAS (DE)


Embedded Tutorial

Moderator: Gurgen Harutyunyan, Synopsys (AR)

Are Self-Driving Cars Reliable? Evaluation of Radiation-Induced Errors in Automotive Applications
Paolo Rech
Politecnico di Torino (IT)

Abstract: The new trend in the automotive market is self-driving system. To be implemented, a self-driving platform needs to be able to analyze a huge amount of images and signals in real time. This is achieved thanks to Convolutional Neural Networks (CNNs) executed on Graphics Processing Units (GPUs). The Tesla self-driving system, for instance, is powered by NVIDIA embedded GPUs executing CNNs-based object-detection. GPUs were originally designed for multimedia applications, for which reliability is not an issue. Their architecture is then optimized to increase performances, not reliability. In the talk we will discuss the reliability of GPUs and evaluate if they are compliant with the strict ISO 26262, which is the standard that define the reliability constraints for automotive applications. The talk will focus on the reliability of object-detection algorithm and convolution neutral networks (including YOLO, Faster RCNN, and ResNet).We will understand how to identify radiation-induced errors in GPUs and distinguish between tolerable errors and critical errors. After a brief description of radiation effects at physical level we will show the real impact of neutrons in GPUs by presenting accelerated neutron beam results that correspond to more than 150,000 years of natural exposure. Our data demonstrates that most of radiation-induced errors in GPUs can be tolerated, even in safety-critical applications. We will show how to replicate the causes of critical errors through architectural-level and instruction-level fault-injection. By hardening only critical error sources, we will be able to increase the reliability of the application without unnecessary overhead.


Technical session 3 – Safety and Security solutions for Automotive SoC

Moderator: Anne Meixner, The Engineers' Daughter (US)

Built-In Self-Test for Functional Safety under Software Control in an Advanced Automotive System-on-Chip
Joe Herd and Kar-Lik Wong
Arm (UK)

In-Field Test and Repair Solution for Safety-Oriented Applications
Grigor Tshagharyan and Gurgen Harutyunyan
Synopsys (AR)
Yervant Zorian
Synopsys (US)
Yehonatan Abotbol and Shahar Dror
Mobileye (ISR)

Safe and Secure Automotive Solutions
Lee Harrison and Gajinder Panesar
Mentor (UK)
Nilanjan Mukherjee and Raghav Mehta
Mentor (US)


Invited Talks – What future for Automotive Reliability and Testing

Moderator: Yervant Zorian, Synopsys (I)

Amitava Majumdar – Xilinx (US)

Nir Maor – Qualcomm (US)

Ralf Montino – Elmos Semiconductor (DE)


Technical session 4 – Embedded Automotive Systems, Design and Debug

Moderator: Riccardo Cantoro, Politecnico di Torino

AR Navigation Using AUTOSAR
Ahmed Hussein, Ahmed N. Gomaa, Mohab H. Fath El-Bab, Rana Y. Mohamed, Sherif S. Khourshed,  and Amr Mokhtar
Alexandria University (EGY)
Keroles Khalil and Georges Antoun
Mentor (EGY)

Portable CAN Sim Analyzer (HW based on embedded linux/ SW based on QT)
Hesham Abdelaziz, Amr Fouda, Mahmoud El-Sabagh, Youssef Taha, Youssef Abdelmoniem, Haitham Mahmoud, Mostafa Abdelmegeed, Youssef Abo El Maaty, Yomna Eid and Moatasem Abdeltawab
Mentor (EGY)
Amira Hakam, Keroles Khalil and Ashraf Salem
Ain Shames University (EGY)