Towards Quantification of Assurance for Learning-enabled Components

TL;DR

This paper proposes a probabilistic framework to quantify assurance levels of learning-enabled components in autonomous vehicles, aiding safety validation and operational hazard mitigation.

Contribution

It introduces a method to quantify dependability attributes of LECs using Gaussian process regression, with a practical example in autonomous aircraft taxiing.

Findings

Quantified assurance measures for LECs using probabilistic techniques

Applied Gaussian process regression to characterize uncertainty in perception functions

Discussed integration of LEC assurance into overall system safety cases

Abstract

Perception, localization, planning, and control, high-level functions often organized in a so-called pipeline, are amongst the core building blocks of modern autonomous (ground, air, and underwater) vehicle architectures. These functions are increasingly being implemented using learning-enabled components (LECs), i.e., (software) components leveraging knowledge acquisition and learning processes such as deep learning. Providing quantified component-level assurance as part of a wider (dynamic) assurance case can be useful in supporting both pre-operational approval of LECs (e.g., by regulators), and runtime hazard mitigation, e.g., using assurance-based failover configurations. This paper develops a notion of assurance for LECs based on i) identifying the relevant dependability attributes, and ii) quantifying those attributes and the associated uncertainty, using probabilistic techniques. We give a practical grounding for our work using an example from the aviation domain: an autonomous taxiing capability for an unmanned aircraft system (UAS), focusing on the application of LECs as sensors in the perception function. We identify the applicable quantitative measures of assurance, and characterize the associated uncertainty using a non-parametric Bayesian approach, namely Gaussian process regression. We additionally discuss the relevance and contribution of LEC assurance to system-level assurance, the generalizability of our approach, and the associated challenges.