Programme.
​8:30-9:00
Registration and welcome to WAISE 2019, Organisation Committee
Keynote
​9:00-10:00
Safety Assurance of Autonomous Systems – bridging the gap between research and industry, Prof. Mario Trapp
​10:00-10:10
Poster Pitching (3 *3 minutes)
Three Reasons Why: Framing the Challenges of Assuring AI, Xinwei Fang and Nikita Johnson
Tackling Uncertainty in Safety Assurance for Machine Learning: Continuous Argument Engineering with Attributed Tests, Yutaka Matsuno, Fuyuki Ishikawa and Susumu Tokumoto
The Moral Machine: Is It Moral?, Alexandre Moreira Nascimento, Lucio Vismari, Anna Carolina Muller Queiroz, Paulo Cugnasca, Joao Camargo and Jorge Rady
10:10-10:40
Cofee break - Poster Sessions
Session 1: Standardisation and Certification
10:40-11:20
A Safety Standard Approach for Fully Autonomous Vehicles, Philip Koopman, Uma Ferrell, Frank Fratrik and Michael Wagner
A Self-Certifiable Architecture for Critical Systems Powered by Probabilistic Logic Artificial Intelligence, Jacques Robin, Raul Mazo, Henrique Madeira, Raul Barbosa, Daniel Diaz and Salvador Abreu
Session 2: Assuring AI-based Systems
​11:20-12:30
Open Questions in Testing of Learned Computer Vision Functions for Automated Driving, Matthias Woehrle, Christoph Gladisch and Christian Heinzemann
An Abstraction-Refinement Approach to Formal Verification of Tree Ensembles, John Törnblom and Simin Nadjm-Tehrani
Improving ML Safety with Partial Specifications, Rick Salay and Krzysztof Czarnecki
12:30-13:30
Lunch - Poster Sessions
Keynote
A Body of Knowledge for Assuring Robotics and Autonomous Systems, Dr Richard Hawkins
13:30-14:30
Session 3: Uncertainty in AI-based Systems
14:30-15:30
Uncertainty Wrappers for Data-driven Models - Increase the Transparency of AI/ML-based Models through Enrichment with Dependable Situation-aware Uncertainty Estimates, Michael Klaes and Lena Sembach
Bayesian Uncertainty Quantification with Synthetic Data, Buu Phan, Samin Khan, Rick Salay and Krzysztof Czarnecki
Confidence Arguments for Evidence of Performance in Machine Learning, Simon Burton, Lydia Gauerhof, Bibhuti Bhusan Sethy, Ibrahim Habli and Richard Hawkins
15:30-16:00
Coffee break - Poster Sessions
Session 4: Safety of Autonomous Systems
16:00-16:40
RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of
Deep Reinforcement Learning Policies, Vahid Behzadan and William Hsu
Adaptive Deployment of Safety Monitors for Autonomous Systems, Nico Hochgeschwender
16:40-17:30
Key Challenges and Research Opportunities for Assuring AI-Based Systems
Plenary Discussion
17:30-17:45
Wrap-up - Best Paper Award