Explainable Planning for Hybrid Systems

TL;DR

This paper explores explainable AI planning for hybrid systems, addressing the challenge of generating understandable explanations in complex, safety-critical autonomous applications.

Contribution

It provides a comprehensive study on explainable AI planning specifically tailored for hybrid systems that model real-world problems.

Findings

Addresses the need for explainability in AI planning for safety-critical domains

Focuses on hybrid systems that combine discrete and continuous dynamics

Highlights the importance of transparent decision-making in autonomous systems

Abstract

The recent advancement in artificial intelligence (AI) technologies facilitates a paradigm shift toward automation. Autonomous systems are fully or partially replacing manually crafted ones. At the core of these systems is automated planning. With the advent of powerful planners, automated planning is now applied to many complex and safety-critical domains, including smart energy grids, self-driving cars, warehouse automation, urban and air traffic control, search and rescue operations, surveillance, robotics, and healthcare. There is a growing need to generate explanations of AI-based systems, which is one of the major challenges the planning community faces today. The thesis presents a comprehensive study on explainable artificial intelligence planning (XAIP) for hybrid systems that capture a representation of real-world problems closely.