Human-Robot Interaction Human-Robot Interaction Edited by Daisuke Chugo I-Tech IV Published by Intech Intech Olajnica 19/2, 32000 Vukovar, Croatia Abstracting and non-profit use of the material is permitted with credit to the source. Statements and opinions expressed in the chapters are these of the individual contributors and not necessarily those of the editors or publisher. No responsibility is accepted for the accuracy of information contained in the published articles. Publisher assumes no responsibility liability for any damage or injury to persons or property arising out of the use of any materials, instructions, methods or ideas contained inside. After this work has been published by the In-Teh, authors have the right to republish it, in whole or part, in any publication of which they are an author or editor, and the make other personal use of the work. © 2010 Intech Free online edition of this book you can find under www.sciyo.com Additional copies can be obtained from: publication@sciyo.com First published February 2010 Printed in India Technical Editor: Teodora Smiljanic Cover designed by Dino Smrekar Human-Robot Interaction, Edited by Daisuke Chugo p. cm. ISBN 978-953-307-051-3 Preface Robot’s performance is increased greatly in recent years and their applications are not limited for industries and manufacturing. Robots are becoming a necessary part of our life and in near future, this trend will be increasing. In our future society, robots may nurse elderly, may look after children and may assist our household work. Furthermore, robots may work together with us in factories, offices and our homes. Robots may become our good friends. For realizing such a wonderful futures, there are still many hard problems both in technically and socially. As good friends know their characteristics each other, robots should have enough performance to know and understand the human. Human-robot interaction (HRI) is the study of interactions between people (users) and robots. HRI is multidisciplinary with contributions from the fields of human-computer interaction, artificial intelligence, robotics, speech recognition, and social science (psychology, cognitive science, anthropology, and human factors). There has been a great deal of work done in the area of human-robot interaction to understand how a human interacts with a computer. However, there has been very little work done in understanding how people interact with robots. For robots becoming our friends, these studies will be required more and more. Therefore, the aim of this book is to provide an overview of the state-of-art, to present new ideas, original results and practical experiences. The content of this book has been structured into 5 technical research sections with 18 chapters written by well-recognized researchers world-side. I hope the readers of this book enjoy its reading and this book helps their understanding on HRI. Editor Daisuke CHUGO Kwansei Gakuin University, Hyogo Japan Contents Preface V Human-Robot Communication 1. Understanding Activities and Intentions for Human-Robot Interaction 001 Richard Kelley, Alireza Tavakkoli, Christopher King, Monica Nicolescu and Mircea Nicolescu 2. Interaction between a Human and an Anthropomorphized Object 019 Hirotaka Osawa and Michita Imai 3. Probo, an Intelligent Huggable Robot for HRI Studies with Children 033 Kristof Goris, Jelle Saldien, Bram Vanderborght and Dirk Lefeber 4. Scaling Effects for Synchronous vs. Asynchronous Video in Multi-robot Search 043 Huadong Wang, Prasanna Velagapudi, Jijun Wang, Paul Scerri, Michael Lewis and Katia Sycara Human-Robot Interaction Architectures 5. Handling Manually Programmed Task Procedures in Human–Service Robot Interactions 057 Yo Chan Kim and Wan Chul Yoon 6. A Genetic Algorithm-based Approach to Dynamic Architectural Deployment 067 Dongsun Kim and Sooyong Park 7. Comparison an On-screen Agent with a Robotic Agent in an Everyday Interaction Style: How to Make Users React Toward an On-screen Agent as if They are Reacting Toward a Robotic Agent 085 Takanori Komatsu VIII Assistive Robotics 8. Development of a Virtual Group Walking Support System 101 Masashi Okubo 9. A Motion Control of a Robotic Walker for Continuous Assistance during Standing, Walking and Seating Operation 109 Daisuke Chugo and Kunikatsu Takase Sensors and Perception Designed for Human-Robot Interaction 10. Development and Performance Evaluation of a Neural Signal Based Computer Interface 127 Changmok Choi and Jung Kim 11. Integration of Electrotactile and Force Displays for Telexistence 141 Katsunari Sato, Naoki Kawakami, and Susumu Tachi 12. Predictive Tracking in Vision-based Hand Pose Estimation using Unscented Kalman Filter and Multi-viewpoint Cameras 155 Albert Causo, Kentaro Takemura, Jun Takamatsu, Tsukasa Ogasawara, Etsuko Ueda and Yoshio Matsumoto 13. Real Time Facial Feature Points Tracking with Pyramidal Lucas-Kanade Algorithm 171 F. Abdat, C. Maaoui and A. Pruski 14. Improving Human-Robot Interaction through Interface Evolution 183 Brenden Keyes, Mark Micire, Jill L. Drury and Holly A. Yanco Skill Based Approach with Human-Robot Interaction 15. Safe Cooperation between Human Operators and Visually Controlled Industrial Manipulators 203 J. A. Corrales, G. J. Garcia, F. A. Candelas, J. Pomares and F. Torres 16. Capturing and Training Motor Skills 225 Otniel Portillo-Rodriguez, Oscar O. Sandoval-Gonzalez, Carlo Avizzano, Emanuele Ruffaldi and Massimo Bergamasco 17. Robot-Aided Learning and r-Learning Services 247 Jeonghye Han IX 18. Design of a Neural Controller for Walking of a 5-Link Planar Biped Robot via Optimization 267 Nasser Sadati, Guy A. Dumont, and Kaveh Akbari Hamed [...].. .Human-Robot Communication 1 Understanding Activities and Intentions for Human-Robot Interaction Richard Kelley, Alireza Tavakkoli, Christopher King, Monica Nicolescu and Mircea Nicolescu University of Nevada, Reno United States of America 1 Introduction As robots move from the factory and into the daily lives of men, women,... will center on the challenge of interacting with humans, rather than with machine parts or other robots To this end, modern-day roboticists are actively studying the problem of human-robot interaction – how best to create robots that can interact with humans, usually in a social setting Among the many problems of human robot interaction, one of the most interesting is the problem of intent recognition:... not make any further restrictions on the background composition, thus allowing for local changes in the background such as fluctuating lights, water fountains, waving tree branches, etc 4 Human-Robot Interaction Fig 1 The two object tracking frameworks for (a) activity modelling using a modified meanshift tracker and (b) intent recognition using a spatio-spectral tracker The proposed system models the... data samples Understanding Activities and Intentions for Human-Robot Interaction 5 in such a way that for a given test sample it can be recognized as known, or rejected as novel Training of SVDDs is a quadratic programming optimization problem This optimization converges by optimizing only on two data points with a specific condition (Platt, 19 98) which requires at least one of the data points to violate... probability of observing a particular visible state given that the model is in a particular hidden state To apply HMMs, one must give an interpretation to both the hidden states and the visible states of the model, as well as an interpretation for the model as a whole In our case, each model represents a single well-defined activity The hidden states of represent the intentions underlying the parts of the activity,... with the Baum-Welch algorithm (Rabiner, 19 89) to train the models, whose topologies have been determined by a human operator in advance During recognition, the stationary robot observes a number of individuals interacting with one another and with stationary objects It tracks those individuals using the visual Understanding Activities and Intentions for Human-Robot Interaction 7 capabilities described... approaches is possible, and may be appropriate for a particular application In the present work, we adopt the latter approach by making each context aware of its possible intentions This awareness is achieved by specifying the content of intention models and context models An intention model consists of two parts: first, an activity model, which is given by a particular HMM, and secondly a name This is the... in a vacuum Intuitively, it would seem that our understanding of others' intentions depend heavily on the contexts in which we find ourselves and those we observe This intuition is supported by 2 Human-Robot Interaction neuroscientific results (Iacobini et al., 2005), which suggest that the context of an activity plays an important and sometimes decisive role in correctly inferring underlying intentions... represent the object • Model update Once the tracking is performed the models will be updated Any unseen object in the raw list is then assigned a new ID and their models are updated accordingly 6 Human-Robot Interaction 4.5 Collision resolution In order for the system to be robust to collisions when individuals get too close so that one occludes the other the models for the occluded individual may... algorithm After the collision is over the spatio-spectral tracker resumes its normal process for these objects 5 Recognition system 5 .1 Low-level recognition via hidden Markov models As mentioned above, our system uses HMMs to model activities that consist of a number of parts that have intentional significance Recall that a hidden Markov model consists of a set of hidden states, a set of visible states, . Designed for Human-Robot Interaction 10 . Development and Performance Evaluation of a Neural Signal Based Computer Interface 12 7 Changmok Choi and Jung Kim 11 . Integration. Matsumoto 13 . Real Time Facial Feature Points Tracking with Pyramidal Lucas-Kanade Algorithm 17 1 F. Abdat, C. Maaoui and A. Pruski 14 . Improving Human-Robot Interaction through. Human-Robot Interaction Human-Robot Interaction Edited by Daisuke Chugo I-Tech IV Published by Intech Intech Olajnica 19 /2, 32000 Vukovar,