Towards Risk Modeling for Collaborative AI

TL;DR

This paper proposes a risk modeling framework for Collaborative AI systems that incorporates goals, risk events, and domain indicators, using runtime evidence to ensure safety and compliance, exemplified in an Industry 4.0 scenario.

Contribution

It introduces a novel risk modeling approach specifically designed for Collaborative AI systems with machine learning components, integrating runtime evidence for safety assurance.

Findings

Risk model effectively identifies hazards in Collaborative AI.

Runtime evidence enhances safety assurance processes.

Application demonstrated in Industry 4.0 robotic collaboration.

Abstract

Collaborative AI systems aim at working together with humans in a shared space to achieve a common goal. This setting imposes potentially hazardous circumstances due to contacts that could harm human beings. Thus, building such systems with strong assurances of compliance with requirements domain specific standards and regulations is of greatest importance. Challenges associated with the achievement of this goal become even more severe when such systems rely on machine learning components rather than such as top-down rule-based AI. In this paper, we introduce a risk modeling approach tailored to Collaborative AI systems. The risk model includes goals, risk events and domain specific indicators that potentially expose humans to hazards. The risk model is then leveraged to drive assurance methods that feed in turn the risk model through insights extracted from run-time evidence. Our envisioned approach is described by means of a running example in the domain of Industry 4.0, where a robotic arm endowed with a visual perception component, implemented with machine learning, collaborates with a human operator for a production-relevant task.