Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Data mining for social robotics : toward autonomously social robots
Mohammad Y., Nishida T., Springer International Publishing, New York, NY, 2016. 328 pp. Type: Book (978-3-319252-30-8)
Date Reviewed: Mar 24 2017

This comprehensive work focuses on human-robot interaction (HRI) using data mining and time series analysis. There are two major objects in this vast field: autonomy and sociality. The author provides a concrete introduction to the theoretical preparations and demonstrates major works in this field, including their fruitful achievements during the past decade.

The book is well divided into two parts (after chapter 1, which is the general introduction). The first part, chapters 2 to 5, is a comprehensive preparation of the theoretical background, primarily time series data analysis, which is the major data format in latter parts. Chapter 2 introduces the foundation of time series data. Chapter 3 covers change point discovery (CPD) on time series. The goal of CPD is to discover in a given time series a list of locations with changes of dynamics and shapes. This chapter provides the basis for multiple later chapters. Chapter 4 covers motif discovery, which is to discover recurrent patterns. Chapter 5 discusses causality analysis, including causality cycles and common causes. The knowledge in Part 1 is fundamental and widely used in later chapters. In addition, the authors carefully controlled the depth of each chapter for optimal comprehension by readers.

The second part is the core of this book, representing the authors’ efforts to realize a computational framework to achieve autonomous sociality. Chapter 6 is an opening to social robots; two major research directions are introduced. Chapter 7 covers research results of imitation learning in robotics, including main aspects of imitation and major challenges. Chapter 8 provides a theoretical foundation before introducing the two major architectures to achieve autonomous sociality: the embedded interactive control architecture (EICA) and the fluid imitation engine (FIE). The EICA, introduced in chapter 9, is the major architecture the authors propose. Chapter 10 provides the details of the behavior architecture of EICA, while chapter 11 introduces the three-stage development approach to learning imitation and processes that can be used to generate interaction protocols to be run by EICA. Fluid imitation is introduced in detail in chapter 12. It is an interesting category of imitation, similar to how infants imitate, which doesn’t require pre-segmented demonstrations to acquire a model of the behaviors they perceive. It also introduces the authors’ efforts in realizing FIE to augment traditional learning from demonstration. Chapter 13 reviews several algorithms for learning from demonstration (LfD), ranging from inverse optimal control to symbolic modeling. Chapter 14 concludes the book.

In general, this book includes rich knowledge in social robot study using data mining tools. The first part of the book is a good introduction to time series analysis, which can be applied to many other disciplines. The second part is even more interesting, covering the major challenges involving imitation and the autonomy of robots interacting with humans. Most important is the connection built between data mining tools for time series and the social robot study. It’s a nice book for graduate students and practitioners to dive deeper into HRI. Personally, this book led me to rethink the learning processes and interaction manners of humans, which is a rather interesting journey.

Reviewer:  Feng Yu Review #: CR145143 (1706-0345)
Bookmark and Share
  Featured Reviewer  
 
Data Mining (H.2.8 ... )
 
 
Learning (I.2.6 )
 
 
Robotics (I.2.9 )
 
Would you recommend this review?
yes
no
Other reviews under "Data Mining": Date
Feature selection and effective classifiers
Deogun J. (ed), Choubey S., Raghavan V. (ed), Sever H. (ed) Journal of the American Society for Information Science 49(5): 423-434, 1998. Type: Article
May 1 1999
Rule induction with extension matrices
Wu X. (ed) Journal of the American Society for Information Science 49(5): 435-454, 1998. Type: Article
Jul 1 1998
Predictive data mining
Weiss S., Indurkhya N., Morgan Kaufmann Publishers Inc., San Francisco, CA, 1998. Type: Book (9781558604032)
Feb 1 1999
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud, Inc.®
Terms of Use
| Privacy Policy