Facilitating Change Implementation for Continuous ML-Safety Assurance

09/23/2022

∙

We propose a method for deploying a safety-critical machine-learning component into continuously evolving environments where an increased degree of automation in the engineering process is desired. We associate semantic tags with the safety case argumentation and turn each piece of evidence into a quantitative metric or a logic formula. With proper tool support, the impact can be characterized by a query over the safety argumentation tree to highlight evidence turning invalid. The concept is exemplified using a vision-based emergency braking system of an autonomous guided vehicle for factory automation.

READ FULL TEXT

Facilitating Change Implementation for Continuous ML-Safety Assurance

Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)

Reliability Assessment and Safety Arguments for Machine Learning Components in Assuring Learning-Enabled Autonomous Systems

Envisioning a Safety Island to Enable HPC Devices in Safety-Critical Domains

Creating a Safety Assurance Case for an ML Satellite-Based Wildfire Detection and Alert System

Integrating Testing and Operation-related Quantitative Evidences in Assurance Cases to Argue Safety of Data-Driven AI/ML Components

A Method towards the Systematic Architecting of Functionally Safe Automated Driving – Leveraging Diagnostic Specifications for FSC design

A Review of the Operational Use of UAS in Public Safety Emergency Incidents

Facilitating Change Implementation for Continuous ML-Safety Assurance

Related Research

Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)

Reliability Assessment and Safety Arguments for Machine Learning Components in Assuring Learning-Enabled Autonomous Systems

Envisioning a Safety Island to Enable HPC Devices in Safety-Critical Domains

Creating a Safety Assurance Case for an ML Satellite-Based Wildfire Detection and Alert System

Integrating Testing and Operation-related Quantitative Evidences in Assurance Cases to Argue Safety of Data-Driven AI/ML Components

A Method towards the Systematic Architecting of Functionally Safe Automated Driving – Leveraging Diagnostic Specifications for FSC design

A Review of the Operational Use of UAS in Public Safety Emergency Incidents