Building Trust in AI-Driven Decision Making for Cyber-Physical Systems (CPS): A Comprehensive Review

TL;DR

This paper reviews how explainable AI can improve trust in AI-driven decision-making within cyber-physical systems across various sectors, addressing transparency, security, and ethical challenges.

Contribution

It provides a comprehensive overview of trust-building strategies in AI-enabled CPS, emphasizing the role of explainable AI and ethical considerations.

Findings

Explainable AI enhances trustworthiness in CPS decisions

Transparency and accountability are crucial for trust

Addressing security and privacy challenges is essential

Abstract

Recent advancements in technology have led to the emergence of Cyber-Physical Systems (CPS), which seamlessly integrate the cyber and physical domains in various sectors such as agriculture, autonomous systems, and healthcare. This integration presents opportunities for enhanced efficiency and automation through the utilization of artificial intelligence (AI) and machine learning (ML). However, the complexity of CPS brings forth challenges related to transparency, bias, and trust in AI-enabled decision-making processes. This research explores the significance of AI and ML in enabling CPS in these domains and addresses the challenges associated with interpreting and trusting AI systems within CPS. Specifically, the role of explainable AI (XAI) in enhancing trustworthiness and reliability in AI-enabled decision-making processes is discussed. Key challenges such as transparency, security, and privacy are identified, along with the necessity of building trust through transparency, accountability, and ethical considerations.