Write a Blog >>
MODELS 2021
Sun 10 - Sat 16 October 2021
Wed 13 Oct 2021 10:20 - 10:40 at Room 1 - Certification and Assurance I Chair(s): Tao Yue

Increasingly, safety-critical systems include artificial intelligence and machine learning components (i.e., Learning-Enabled Components (LECs)). However, when behavior is learned in a training environment that fails to fully capture real-world phenomena, the response of an LEC to untrained phenomena is uncertain, and therefore cannot be assured as safe. Automated methods are needed for self-assessment and adaptation to decide when learned behavior can be trusted. This work introduces a model-driven approach to manage self-adaptation of a Learning-Enabled System (LES) to account for run-time contexts for which the learned behavior of LECs cannot be trusted. The resulting framework enables an LES to monitor and evaluate goal models at run time to determine whether or not LECs can be expected to meet functional objectives. Using this framework enables stakeholders to have more confidence that LECs are used only in contexts comparable to those validated at design time.

Wed 13 Oct

Displayed time zone: Osaka, Sapporo, Tokyo change

10:00 - 11:00
Certification and Assurance ITechnical Papers at Room 1
Chair(s): Tao Yue Simula Research Laboratory
10:00
20m
Full-paper
A Lean Approach to Building Valid Model-Based Safety ArgumentsFT
Technical Papers
Torin Viger , Logan Murphy , Alessio Di Sandro , Ramy Shahin University of Toronto, Marsha Chechik University of Toronto
10:20
20m
Full-paper
MoDALAS: Model-Driven Assurance for Learning-Enabled Autonomous SystemsFT
Technical Papers
10:40
20m
Talk
Graphical Composite Modeling and Simulation for Multi-aircraft Collision AvoidanceJ1ST
Technical Papers