Accepted papers

Thematic Session 1:  AI Safety

Deep Neural Network Uncertainty Estimation with Stochastic Inputs for Robust Aerial Navigation Policies

Fabio Arnez, Huascar Espinoza, Ansgar Radermacher and François Terrier

No Free Lunch: Overcoming Reward Gaming in AI Safety Gridworlds

Mariya Tsvarkaleva and Louise Dennis

Effect of label noise on robustness of deep neural network object detectors

Bishwo Adhikari, Jukka Peltomäki, Saeed Bakhshi Germi, Esa Rahtu and Heikki Huttunen

Human-in-the-Loop Learning Methods Toward Safe DL-based Autonomous Systems: A Review

Prajit T Rajendran, Huascar Espinoza, Agnes Delaborde and Chokri Mraidha

Thematic Session 2: Automated Driving Safety

An Integrated Approach to a Safety Argumentation for AI-based Perception Functions in Automated Driving 

Michael Mock, Stephan Scholz, Frederik Blank, Fabian Hüger, Andreas Rohatschek, Loren Schwarz and Thomas Stauner

Experimental Conformance Evaluation on UBER ATG Safety Case Framework with ANSL/UL 4600

Kenji Taguchi and Fuyuki Ishikawa

Learning From AV Safety: Hope and Humility Shape Policy and Progress

Marjory Blumenthal

Thematic Session 3: Assurances for Autonomous Systems

Levels of Autonomy & Safety Assurance for AI-based Clinical Decision Systems 

Paul Festor, Ibrahim Habil, Yan Jia, Anthony Gordon, A. Aldo Faisal and Matthieu Komorowski

Certification Game for the Operational Safety Analysis of AI-based CPS

Imane Lamrani, Ayan Banerjee and Sandeep Gupta

A New Approach to Better Consensus Building and Agreement Implementation for Trustworthy AI Systems 

Yukiko Yanagisawa and Yasuhiko Yokote

Short Talks

Towards a Common Testing Terminology for Software Engineering and Artificial Intelligence Experts

Lisa Joeckel, Thomas Bauer, Marc Hauer, Michael Klaes and Janek Gross

IEEE P7009 Standard on Fail-Safe Design of Autonomous and Semi-Autonomous Systems 

Ken Wallace