Human-Centered Explainable AI for Sequential Decision-Making Systems
Author(s)
Das, Devleena
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Everyday users (non-AI experts) are interacting with a growing number of AI systems that provide intelligent assistance, such as educational tutors and home robots. However, the increased computational and inferential capabilities of such AI systems often lead to differences between a user’s and an AI system’s mental models, making it difficult for users to understand AI solutions. Furthermore, AI systems are not perfect, and in real-world settings, suboptimal AI decision making, or failures are inevitable. We posit that for AI systems to provide meaningful support, these systems must be understandable to everyday users. This presents a need for human-centered explainability techniques that help increase everyday users’ understanding of complex AI systems.
This thesis examines computational methods for explaining sequential decision-making AI systems such that both end users and AI systems benefit in improved understanding and performance. Findings from psychology state that humans naturally reason about complex problems by attributing abstractions to a given task. Inspired by these insights, this thesis investigates the following hypothesis: Explanations of AI systems that are grounded in abstractions of utility factors, environmental context, subgoal information and task concepts can improve everyday user task performance as well as AI performance. To support this claim, this thesis contributes: (1) an algorithm that leverages task utility factors to explain optimal AI systems for improved user performance; (2) a framework that grounds robot decision-making in environmental context to explain robot failures to non-roboticists; (3) an algorithm that extracts environmental-context via semantic scene graphs to provide scalable explanations of robot failures; (4) an algorithm that explains suboptimal, hierarchical AI systems by extracting appropriate subgoal information to help users avoid suboptimal decisions; (5) a framework that leverages concept-based explanations in a learned joint embedding space to improve both AI learning and user performance.
Sponsor
Date
2024-03-04
Extent
Resource Type
Text
Resource Subtype
Dissertation