Identifying the Hazard Boundary of ML-Enabled Autonomous Systems Using Cooperative Coevolutionary Search

Sepehr Sharifi, Donghwan Shin, Lionel C. Briand, Nathan Aschbacher

Research output: Contribution to journalArticlepeer-review

Abstract

In Machine Learning (ML)-enabled autonomous systems (MLASs), it is essential to identify the hazard boundary of ML Components (MLCs) in the MLAS under analysis. Given that such boundary captures the conditions in terms of MLC behavior and system context that can lead to hazards, it can then be used to, for example, build a safety monitor that can take any predefined fallback mechanisms at runtime when reaching the hazard boundary. However, determining such hazard boundary for an ML component is challenging. This is due to the problem space combining system contexts (i.e., scenarios) and MLC behaviors (i.e., inputs and outputs) being far too large for exhaustive exploration and even to handle using conventional metaheuristics, such as genetic algorithms. Additionally, the high computational cost of simulations required to determine any MLAS safety violations makes the problem even more challenging. Furthermore, it is unrealistic to consider a region in the problem space deterministically safe or unsafe due to the uncontrollable parameters in simulations and the non-linear behaviors of ML models (e.g., deep neural networks) in the MLAS under analysis. To address the challenges, we propose MLCSHE (ML Component Safety Hazard Envelope), a novel method based on a Cooperative Co-Evolutionary Algorithm (CCEA), which aims to tackle a high-dimensional problem by decomposing it into two lower-dimensional search subproblems. Moreover, we take a probabilistic view of safe and unsafe regions and define a novel fitness function to measure the distance from the probabilistic hazard boundary and thus drive the search effectively. We evaluate the effectiveness and efficiency of MLCSHE on a complex Autonomous Vehicle (AV) case study. Our evaluation results show that MLCSHE is significantly more effective and efficient compared to a standard genetic algorithm and random search.

Original languageEnglish
Article number3327575
Pages (from-to)5120-5138
Number of pages19
JournalIEEE Transactions on Software Engineering
Volume49
Issue number12
DOIs
Publication statusPublished - 1 Dec 2023
Externally publishedYes

Keywords

  • cooperative co-evolutionary search
  • hazard boundary
  • ML-enabled autonomous system
  • system safety monitoring

Fingerprint

Dive into the research topics of 'Identifying the Hazard Boundary of ML-Enabled Autonomous Systems Using Cooperative Coevolutionary Search'. Together they form a unique fingerprint.

Cite this