Imitation in Robotics
Yasser Mohammad(Author)
Productivity Press
1st Edition
Published on 15. October 2020
Book
Hardback
225 pages
978-1-4987-6907-5 (ISBN)
Description
Imitation underlies our culture, language, and feelings, and robotic imitation has social aspects that are usually ignored. However, roboticists are now starting to understand the power of imitation learning, utilizing animal and human imitation as inspiration. This book provides a reference to state-of-the-art techniques in imitation, demonstration learning, and apprenticeship learning. Recent case studies are given to help the reader appreciate the subtleties of each outlined technique and provide a starting point for new ideas and algorithms. The book is supported by a MATLAB toolbox that provides full implementation of most of the algorithms discussed for a hands-on learning approach.
More details
Language
English
Place of publication
Portland
United States
Publishing group
Taylor & Francis Inc
Target group
College/higher education
Professional and scholarly
Dimensions
Height: 234 mm
Width: 156 mm
ISBN-13
978-1-4987-6907-5 (9781498769075)
Copyright in bibliographic data is held by Nielsen Book Services Limited or its licensors: all rights reserved.
Schweitzer Classification
Person
Yasser Mohammad received his Ph.D. in Computers and Systems from Kyoto University, Japan in 2009 and is a tenured Assistant Professor at Assiut University, Egypt. He is the author of over 70 papers in international journals and conferences in the areas of robotics, HRI, and data mining. From 2012 to 2014, he was a JSPS post-doctoral fellow at Kyoto University. He is a senior member of IEEE and a member of IEEE RAS, ICROS, and ISAI. He is an editorial board member of New Generation Computing, a member of the reviewer board of Applied Intelligence, and a reviewer for several international journals including AI&Society, Social Robotics, TiiS, and IJARS.
Content
Introduction. Imitation: The Opportunity and the Challenge. Imitation in Animals and Humans. Challenges of Imitation in Robotics. Tackling the Correspondence Problem. Action Segmentation and Significance Estimation. Evaluation and Fluid Imitation. Modeling Demonstrations. Inverse Optimal Control. Inverse Reinforcement Learning. Dynamic Motor Primitives. HMM Approaches. Gaussian Mixture Approaches. Gaussian Processes for LfD. Symbolization and Other Approaches.