Toward a hybrid causal framework for autonomous vehicle safety analysis

Abstract

Autonomous Vehicles (AVs), also known as self-driving cars, are a potentially transformative technology, but developing and demonstrating AV safety remains an open question. AVs offer some unique challenges that stretch the limits of traditional safety engineering practices. Most current safety standards and methodologies in the AV industry were not originally intended for application to autonomous vehicles, and they have significant limitations and shortcomings. In this article, we analyze the literature to first build an argument that a new safety framework is needed for AVs. We then use the identified limitations of current methodologies as a basis to formulate a set of fundamental requirements that must be met by any proposed AV safety framework. We propose a new AV safety framework based on the Hybrid Causal Logic (HCL) methodology, which combines Event Sequence Diagrams (ESDs), Fault Tree Analysis (FTA), and Bayesian Networks (BNs). The HCL framework is developed at a conceptual level and then evaluated versus the identified fundamental requirements. To further illustrate how the framework may meet the requirements, a simple example of an AV perception system scenario is developed using the HCL framework and evaluated. The results demonstrate that the HCL framework provides an integrated approach that has the potential to satisfy more completely the fundamental requirements than the current methodologies.

Hybrid Causal Logic Model for Estimating the Probability of an Icebreaker–Ship Collision in an Ice Channel During an Escort Operation Along the Northeast Passage

“…successfully been applied to ship collision (Pedersen, 2021;Wang et al, 2020), ship foundering (Zhang et al, 2018a,b), autonomous vehicle (Thomas and Groth, 2021), offshore platform (Røed et al, 2009;Wang et al, 2011), and nuclear power plant (Diaconeasa, 2017) risks. It includes an event sequence diagram (ESD), FT, and BN (Fig.…”

Editorial for the special issue on the International Workshop on Autonomous System Safety (IWASS)

“…Thomas and Groth 7 transfer the risk modeling framework hybrid causal logic to autonomous vehicles in order to satisfy their identified fundamental requirements. The hybrid causal logic model uses event sequence diagrams, fault trees, and Bayesian belief networks to model the interactions of failures.…”

Safety Assurance of Autonomous Systems using Machine Learning: An Industrial Case Study and Lessons Learnt

“…In (Thomas & Groth, 20211) Bayesian networks (BNs) are used for the safety analysis of autonomous systems which also allows the integration of functional safety and SOTIF analysis. It provides a framework which incorporates an operational scenario-driven approach with a combination of fault tree and BN.…”

“…Hence, techniques such Bayesian Networks might be used to describe the probability of occurrence of a deficiency. There are already scientific publications in this direction (Thomas & Groth, 20211). However, the quantification of deficiencies and the extension of the CFDT methodology with respect to quantification must be investigated in detail in the future.…”