En savoir plus
Plan recognition, activity recognition, and goal recognition all involve making inferences about other actors based on observations of their interactions with the environment and other agents. This synergistic area of research combines, unites, and makes use of techniques and research from a wide range of areas including user modeling, machine vision, automated planning, intelligent user interfaces, human-computer interaction, autonomous and multi-agent systems, natural language understanding, and machine learning. It plays a crucial role in a wide variety of applications including assistive technology, software assistants, computer and network security, human-robot collaboration, natural language processing, video games, and many more.
This wide range of applications and disciplines has produced a wealth of ideas, models, tools, and results in the recognition literature. However, it has also contributed to fragmentation in the field, with researchers publishing relevant results in a wide spectrum of journals and conferences.
This book seeks to address this fragmentation by providing a high-level introduction and historical overview of the plan and goal recognition literature. It provides a description of the core elements that comprise these recognition problems and practical advice for modeling them. In particular, we define and distinguish the different recognition tasks. We formalize the major approaches to modeling these problems using a single motivating example. Finally, we describe a number of state-of-the-art systems and their extensions, future challenges, and some potential applications.
Table des matières
Preface.- Acknowledgments.- Introduction.- Defining a Recognition Problem.- Implicit vs. Explicit Representation of Knowledge.- Improving a Recognizer.- Future Directions.- Bibliography.- Authors' Biographies.
A propos de l'auteur
Reuth Mirsky is a postdoctoral fellow at the Computer Science department in the University of Texas at Austin, under the mentorship of Prof. Peter Stone. Reuth received her Ph.D. from the Department of Software and Information Systems Engineering at Ben Gurion University, under the supervision of Prof. Kobi Gal. Her Ph.D. thesis was on plan recognition in exploratory environments. Reuth¿s research focuses on improving existing AI with human-inspired design, and her algorithms have been applied in various tasks for education, clinical treatment, and finance. Reuth¿s contributions were published by leading AI and HRI conferences and journals. Her longterm research vision is to enable better collaborations in mixed human-and-artificial agents settings.Sarah Keren is a postdoctoral fellow at Harvard University, where she is affiliated with the Center for Research on Computation and Society (CRCS). Her mentors are Prof. Barbara Grosz and Prof. David Parkes. Before coming to Harvard, Sarah completed her Ph.D. at the Faculty of Industrial Engineering and Management of the Technion¿Israel Institute of Technology, where she was advised by Prof. Avigdor Gal and Dr. Erez Karpas. Sarah¿s research focuses on manipulating and redesigning environments for optimizing their utility. In particular, her Ph.D. work established the task of Goal Recognition Design, where environments are manipulated to maximize the ability to recognize the goals of agents acting within them. Sarah¿s work has appeared in three leading artificial intelligence conferences (AAAI, ICAPS, and IJCAI). She has received various excellence awards, including an honorable mention for best paper at ICAPS 2014 as well as the Eric and Wendy Schmidt Postdoctoral Award for Women in Mathematical and Computing Sciences.Christopher Geib is a Principal Researcher at SIFT LLC and an internationally recognized researcher in probabilistic plan recognition and planning. He received his Ph.D. in Computer Science from the University of Pennsylvania in 1995. Prior to joining SIFT, he had an extensive career both in academia as an Associate Professor at Drexel University and a Research Fellow at the University of Edinburgh, and in industry as a Principal Research Scientist at Honeywell. He has published more than 50 scholarly publications. His interests include probabilistic plan recognition and planning under uncertainty based on formal grammars and interaction between human and synthetic agents using actions and language. He has been the principal architect of multiple plan recognition systems over the last 20+ years.
