🤖 AI Summary
This study addresses the challenges posed by hidden and complex AI-related technical debt in AI-intensive cyber-physical systems (AI-CPS), which is significantly more difficult to identify and manage than in traditional systems. Through empirical analysis of AI ecosystems and code repositories, developer interviews, and static code analysis, this work systematically characterizes AI-CPS-specific forms of technical debt for the first time. It proposes targeted mechanisms for detection and remediation and introduces an innovative agent-driven automated tool to enable continuous monitoring and governance of AI technical debt. The resulting framework advances a systematic understanding of technical debt in AI-CPS and demonstrates the feasibility and effectiveness of the proposed tool in real-world scenarios.
📝 Abstract
Artificial Intelligence (AI) components are increasingly pervasive in several software systems, including Cyber-Physical Systems (CPSs). AI-CPS are used in several domains, including autonomous vehicles, industry, home automation, robotics, and healthcare. Being composed of hardware, AI components, and conventional modules, AI-CPS can exhibit technical debt (TD) that is peculiar and potentially more challenging than that of conventional systems. This thesis aims to characterize AI-CPS TD and propose approaches for its identification and repair. In a first phase, we characterize AI-CPS TD by analyzing AI ecosystems and AI-CPS repositories, as well as interviewing developers. Based on the acquired knowledge, we define approaches to identify and mitigate such TD. Finally, we plan to develop and validate an automated tool that supports agentic AI solutions to monitor, govern, and repay AI-CPS TD.