Data & IT
Pocket
Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection
Xuefeng Zhou • Hongmin Wu • Juan Rojas • Zhihao Xu • Shuai Li
579:-
Uppskattad leveranstid 10-16 arbetsdagar
Fri frakt för medlemmar vid köp för minst 249:-
Andra format:
- Inbunden 719:-
This open access book focuses onrobot introspection,whichhas a direct impact on physical human-robot interactionandlong-term autonomy,andwhich can benefit from autonomous anomaly monitoring and diagnosis, as well as anomaly recovery strategies. In robotics,the abilitytoreason,solve their ownanomaliesand proactivelyenrich 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 caneffectivelybe modeled as a parametrichidden Markovmodel (HMM). They then adopt a nonparametric Bayesian approach in defining a prior using thehierarchical Dirichletprocess (HDP) on the standard HMM parameters,known as theHierarchical Dirichlet Process Hidden Markov Model (HDP-HMM). The HDP-HMM can examine an HMM with an unbounded number of possible states andallows flexibility in the complexity of the learned model and the development of reliable and scalable variational inference methods. This book is avaluablereferenceresource forresearchers and designers inthe fieldof robot learning and multimodal perception, as well as for senior undergraduate and graduateuniversitystudents.
- Format: Pocket/Paperback
- ISBN: 9789811562655
- Språk: Engelska
- Antal sidor: 137
- Utgivningsdatum: 2020-09-18
- Förlag: Springer Verlag, Singapore