Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection

This open access book focuses on robot introspection, which has a direct impact on physical human–robot interaction and long-term autonomy, and which can benefit from autonomous anomaly monitoring and diagnosis, as well as anomaly recovery strategies. In robotics, the ability to reason, solve their...

Full description

Bibliographic Details
Main Authors: Zhou, Xuefeng, Wu, Hongmin (Author), Rojas, Juan (Author), Xu, Zhihao (Author)
Format: eBook
Language:English
Published: Singapore Springer Nature Singapore 2020, 2020
Edition:1st ed. 2020
Subjects:
Online Access:
Collection: Springer eBooks 2005- - Collection details see MPG.ReNa
LEADER 02992nmm a2200409 u 4500
001 EB001899219
003 EBX01000000000000001062128
005 00000000000000.0
007 cr|||||||||||||||||||||
008 200810 ||| eng
020 |a 9789811562631 
100 1 |a Zhou, Xuefeng 
245 0 0 |a Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection  |h Elektronische Ressource  |c by Xuefeng Zhou, Hongmin Wu, Juan Rojas, Zhihao Xu, Shuai Li 
250 |a 1st ed. 2020 
260 |a Singapore  |b Springer Nature Singapore  |c 2020, 2020 
300 |a XVII, 137 p. 50 illus., 44 illus. in color  |b online resource 
505 0 |a Introduction to Robot Introspection -- Nonparametric Bayesian Modeling of Multimodal Time Series -- Incremental Learning Robot Complex Task Representation and Identification -- Nonparametric Bayesian Method for Robot Anomaly Monitoring -- Nonparametric Bayesian Method for Robot Anomaly Diagnose -- Learning Policy for Robot Anomaly Recovery based on Robot 
653 |a Machine learning 
653 |a Control, Robotics, Automation 
653 |a Machine Learning 
653 |a Bayesian Inference 
653 |a Statistics  
653 |a Control engineering 
653 |a Robotics 
653 |a Mathematical Modeling and Industrial Mathematics 
653 |a Robotic Engineering 
653 |a Automation 
653 |a Mathematical models 
700 1 |a Wu, Hongmin  |e [author] 
700 1 |a Rojas, Juan  |e [author] 
700 1 |a Xu, Zhihao  |e [author] 
041 0 7 |a eng  |2 ISO 639-2 
989 |b Springer  |a Springer eBooks 2005- 
028 5 0 |a 10.1007/978-981-15-6263-1 
856 4 0 |u https://doi.org/10.1007/978-981-15-6263-1?nosfx=y  |x Verlag  |3 Volltext 
082 0 |a 629.892 
520 |a This open access book focuses on robot introspection, which has a direct impact on physical human–robot interaction and long-term autonomy, and which can benefit from autonomous anomaly monitoring and diagnosis, as well as anomaly recovery strategies. In robotics, the ability to reason, solve their own anomalies and proactively enrich owned knowledge is a direct way to improve autonomous behaviors. To this end, the authors start by considering the underlying pattern of multimodal observation during robot manipulation, which can effectively be modeled as a parametric hidden Markov model (HMM). They then adopt a nonparametric Bayesian approach in defining a prior using the hierarchical Dirichlet process (HDP) on the standard HMM parameters, known as the Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM). The HDP-HMM can examine an HMM with an unbounded number of possible states and allows flexibility in the complexity of the learned model and the development of reliable and scalable variational inference methods. This book is a valuable reference resource for researchers and designers in the field of robot learning and multimodal perception, as well as for senior undergraduate and graduate university students