Plan, Activity, and Intent Recognition

Plan, Activity, and Intent Recognition

Theory and Practice

1st Edition - February 24, 2014
  • Editors: Gita Sukthankar, Christopher Geib, Hung Bui, David Pynadath, Robert Goldman
  • eBook ISBN: 9780124017108
  • Paperback ISBN: 9780123985323

Purchase options

Purchase options
DRM-free (EPub, PDF, Mobi)
Available
Sales tax will be calculated at check-out

Institutional Subscription

Free Global Shipping
No minimum order

Description

Plan recognition, activity recognition, and intent recognition together combine and unify techniques from user modeling, machine vision, intelligent user interfaces, human/computer interaction, autonomous and multi-agent systems, natural language understanding, and machine learning. Plan, Activity, and Intent Recognition explains the crucial role of these techniques in a wide variety of applications including: personal agent assistants computer and network security opponent modeling in games and simulation systems coordination in robots and software agents web e-commerce and collaborative filtering dialog modeling video surveillance smart homes In this book, follow the history of this research area and witness exciting new developments in the field made possible by improved sensors, increased computational power, and new application areas.

Key Features

  • Combines basic theory on algorithms for plan/activity recognition along with results from recent workshops and seminars
  • Explains how to interpret and recognize plans and activities from sensor data
  • Provides valuable background knowledge and assembles key concepts into one guide for researchers or students studying these disciplines

Readership

Academic researchers and industrial researchers in specific application areas such as user interface design and video surveillance systems

Table of Contents

  • About the Editors

    Contributors

    Preface

    Introduction

    1: Plan and Goal Recognition

    1: Hierarchical Goal Recognition

    1.1 Introduction

    1.2 Previous Work

    1.3 Data for Plan Recognition

    1.4 Metrics for Plan Recognition

    1.5 Hierarchical Goal Recognition

    1.6 System Evaluation

    1.7 Conclusion

    2: Weighted Abduction for Discourse Processing Based on Integer Linear Programming

    2.1 Introduction

    2.2 Related Work

    2.3 Weighted Abduction

    2.4 ILP-based Weighted Abduction

    2.5 Weighted Abduction for Plan Recognition

    2.6 Weighted Abduction for Discourse Processing

    2.7 Evaluation on Recognizing Textual Entailment

    2.8 Conclusion

    3: Plan Recognition Using Statistical–Relational Models

    3.1 Introduction

    3.2 Background

    3.3 Adapting Bayesian Logic Programs

    3.4 Adapting Markov Logic

    3.5 Experimental Evaluation

    3.6 Future Work

    3.7 Conclusion

    4: Keyhole Adversarial Plan Recognition for Recognition of Suspicious and Anomalous Behavior

    4.1 Introduction

    4.2 Background: Adversarial Plan Recognition

    4.3 An Efficient Hybrid System for Adversarial Plan Recognition

    4.4 Experiments to Detect Anomalous and Suspicious Behavior

    4.5 Future Directions and Final Remarks

    2: Activity Discovery and Recognition

    5: Stream Sequence Mining for Human Activity Discovery

    5.1 Introduction

    5.2 Related Work

    5.3 Proposed Model

    5.4 Experiments

    5.5 Conclusion

    6: Learning Latent Activities from Social Signals with Hierarchical Dirichlet Processes

    6.1 Introduction

    6.2 Related Work

    6.3 Bayesian Nonparametric Approach to Inferring Latent Activities

    6.4 Experiments

    6.5 Conclusion

    3: Modeling Human Cognition

    7: Modeling Human Plan Recognition Using Bayesian Theory of Mind

    7.1 Introduction

    7.2 Computational Framework

    7.3 Comparing the Model to Human Judgments

    7.4 Discussion

    7.5 Conclusion

    8: Decision-Theoretic Planning in Multiagent Settings with Application to Behavioral Modeling

    8.1 Introduction

    8.2 The Interactive POMDP Framework

    8.3 Modeling Deep, Strategic Reasoning by Humans Using I-POMDPs

    8.4 Discussion

    8.5 Conclusion

    4: Multiagent Systems

    9: Multiagent Plan Recognition from Partially Observed Team Traces

    9.1 Introduction

    9.2 Preliminaries

    9.3 Multiagent Plan Recognition with Plan Library

    9.4 Multiagent Plan Recognition with Action Models

    9.5 Experiment

    9.6 Related Work

    9.7 Conclusion

    10: Role-Based Ad Hoc Teamwork

    10.1 Introduction

    10.2 Related Work

    10.3 Problem Definition

    10.4 Importance of Role Recognition

    10.5 Models for Choosing a Role

    10.6 Model Evaluation

    10.7 Conclusion and Future Work

    5: Applications

    11: Probabilistic Plan Recognition for Proactive Assistant Agents

    11.1 Introduction

    11.2 Proactive Assistant Agent

    11.3 Probabilistic Plan Recognition

    11.4 Plan Recognition within a Proactive Assistant System

    11.5 Applications

    11.6 Conclusion

    12: Recognizing Player Goals in Open-Ended Digital Games with Markov Logic Networks

    12.1 Introduction

    12.2 Related Work

    12.3 Observation Corpus

    12.4 Markov Logic Networks

    12.5 Goal Recognition with Markov Logic Networks

    12.6 Evaluation

    12.7 Discussion

    12.8 Conclusion and Future Work

    13: Using Opponent Modeling to Adapt Team Play in American Football

    13.1 Introduction

    13.2 Related Work

    13.3 Rush Football

    13.4 Play Recognition Using Support Vector Machines

    13.5 Team Coordination

    13.6 Offline UCT for Learning Football Plays

    13.7 Online UCT for Multiagent Action Selection

    13.8 Conclusion

    14: Intent Recognition for Human–Robot Interaction

    14.1 Introduction

    14.2 Previous Work in Intent Recognition

    14.3 Intent Recognition in Human–Robot Interaction

    14.4 HMM-Based Intent Recognition

    14.5 Contextual Modeling and Intent Recognition

    14.6 Experiments on Physical Robots

    14.7 Discussion

    14.8 Conclusion

    Author Index

    Subject Index

Product details

  • No. of pages: 424
  • Language: English
  • Copyright: © Morgan Kaufmann 2014
  • Published: February 24, 2014
  • Imprint: Morgan Kaufmann
  • eBook ISBN: 9780124017108
  • Paperback ISBN: 9780123985323

About the Editors

Gita Sukthankar

Dr. Gita Sukthankar is an Associate Professor and Charles N. Millican Faculty Fellow in the Department of Electrical Engineering and Computer Science at the University of Central Florida, and an affiliate faculty member at UCF’s Institute for Simulation and Training. She received her Ph.D. from the Robotics Institute at Carnegie Mellon, an M.S. in Robotics, and an A.B. in psychology from Princeton University. In 2009, Dr. Sukthankar was selected for an Air Force Young Investigator award, the DARPA Computer Science Study Panel, and an NSF CAREER award. Gita Sukthankar’s research focuses on multi-agent systems and computational social models.

Affiliations and Expertise

Assistant Professor, University of Central Florida

Christopher Geib

Christopher Geib is an Associate Professor in the College of Computing and Informatics at Drexel University. Before joining Drexel, Prof. Geib's career has spanned a number of academic and industrial posts including being a Research Fellow in the School of Informatics at the University of Edinburgh, a Principal Research Scientist working at Honeywell Labs, and a Post Doctoral Fellow at the University of British Columbia in the Laboratory for Computational Intelligence. He received his Ph.D. in Computer Science from the University of Pennsylvania and has worked on plan recognition and planning for over 20 years.

Affiliations and Expertise

Associate Professor, Drexel University

Hung Bui

Dr. Hung Bui is a Principal Research Scientist at the Laboratory for Natural Language Understanding, Nuance, Sunnyvale, CA. His main research interests include probabilistic reasoning, machine learning and their applications in plan and activity recognition. Before joining Nuance, he spent 9 years as a senior computer scientist at SRI International, where he led several multi-institution research teams developing probabilistic inference technologies for understanding human activities and building personal intelligent assistants. He received his Ph.D. in Computer Science in 1998 from Curtin University, Western Australia.

Affiliations and Expertise

Principal Scientist, Laboratory for Natural Language Understanding, Nuance

David Pynadath

Dr. David V. Pynadath is a Research Scientist at the University of Southern California Institute for Creative Technologies. He received his Ph.D. in Computer Science from the University of Michigan, Ann Arbor, where he studied probabilistic grammars for plan recognition. He was subsequently a Research Scientist at the USC Information Sciences Institute, and is currently a member of the Social Simulation Lab at USC ICT, where he conducts research in multiagent decision-theoretic methods for social reasoning.

Affiliations and Expertise

Research Scientist, Institute for Creative Technologies, USC

Robert Goldman

Robert P. Goldman is a Staff Scientist at SIFT, LLC, specializing in Artificial Intelligence. Dr. Goldman received his Ph.D. in Computer Science from Brown University, where he worked on the first Bayesian model for plan recognition. Prior to joining SIFT, Dr. Goldman was Assistant Professor of Computer Science at Tulane University, and then Principal Research Scientist at Honeywell Labs. Dr. Goldman's research interests involve plan recognition, the intersection between planning, control theory, and formal methods, computer security, and reasoning under uncertainty.

Affiliations and Expertise

Staff Scientist, Smart Information Flow Technologies LLC