Explainable Human-AI Interaction

A Planning Perspective
Erscheinungsjahr 2022
ISBN: 978-1-63639-289-9
Verlag: Morgan & Claypool Publishers

Buch, Englisch, 184 Seiten, Paperback, Format (B × H): 152 mm x 229 mm

Reihe: Synthesis Lectures on Artificial Intelligence and Machine Learning

Discusses how an AI agent can use mental models to either conform to human expectations or change those expectations through explanatory communication. While the focus of the book is on cooperative scenarios, it also covers how the same mental models can be used for obfuscation and deception.

Autoren/Hrsg.

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Wissensbasierte Systeme, Expertensysteme

Inhaltsverzeichnis

- Preface
- Acknowledgments
- Introduction
- Measures of Interpretability
- Explicable Behavior Generation
- Legible Behavior
- Explanation as Model Reconciliation
- Acquiring Mental Models for Explanations
- Balancing Communication and Behavior
- Explaining in the Presence of Vocabulary Mismatch
- Obfuscatory Behavior and Deceptive Communication
- Applications
- Conclusion
- Bibliography
- Authors' Biographies
- Index

Über Autor(innen)

Sarath Sreedharan is a Ph.D. student at Arizona State University working with Prof. Subbarao Kambhampati. His primary research interests lie in the area of human-aware and explainable AI, with a focus on sequential-decision making problems. Sarath's research has been featured in various premier research conferences, including IJCAI, AAAI, AAMAS, ICAPS, ICRA, and IROS, as well as journals like AIJ. He was also the recipient of Outstanding Program Committee Member Award at AAAI-2020. Anagha Kulkarni is an AI Research Scientist at Invitae. Before that, she received her Ph.D. in Computer Science from Arizona State University. Her Ph.D. thesis was in the area of human-aware AI and automated planning. Anagha's research has featured in various premier conferences like AAAI, IJCAI, ICAPS, AAMAS, ICRA, and IROS. Subbarao Kambhampati is a professor in the School of Computing & AI at Arizona State University. Kambhampati studies fundamental problems in planning and decision making, motivated in particular by the challenges of human-aware AI systems. He is a fellow of Association for the Advancement of Artificial Intelligence (AAAI), American Association for the Advancement of Science, and Association for Computing Machinery and was an NSF Young Investigator. He was the president of the AAAI, trustee of International Joint Conference on Artificial Intelligence (IJCAI), and a founding board member of Partnership on AI. Kambhampati's research as well as his views on the progress and societal impacts of AI have been featured in multiple national and international media outlets.