Motion imitation and recognition using parametric hidden Markov models

Herzog, Dennis; Ude, Aleš; Krüger, Volker

doi:10.1109/ichr.2008.4756002

Cited by 17 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Herzog et al [29] examined modeling of human and robot trajectories using parametric hidden Markov models (PHMM, [30]). PHMMs can capture inter-class variations between examples and as such ideal for representing manipulation trajectories.…”

Section: Hierarchical Approach and Lower Level Methodsmentioning

confidence: 99%

“…The trajectory can then be classified as belonging to the model with the highest likelihood. PHMMs have been previously used for trajectory learning, recognition and reproduction in robotics [29,32]. However, these authors only considered the recognition of presegmented sequences and did not use semantic relations between objects.…”

Section: Verification With Low Level Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Probabilistic semantic models for manipulation action representation and extraction

Vuga

Aksoy

Wörgötter

et al. 2015

Robotics and Autonomous Systems

View full text Add to dashboard Cite

Section: Hierarchical Approach and Lower Level Methodsmentioning

confidence: 99%

Section: Verification With Low Level Modelsmentioning

confidence: 99%

Probabilistic semantic models for manipulation action representation and extraction

Vuga

Aksoy

Wörgötter

et al. 2015

Robotics and Autonomous Systems

View full text Add to dashboard Cite

“…In addition, for movements incorporating object handling, it may be desirable to generalize movement primitives by including parametrization. This can be incorporated into the proposed framework through the use of parametric hidden Markov models [29]. When considering multiple users, there is no guarantee that different demonstrators would perform the same motion primitive in the same way, it is still possible that demonstrations from different demonstrators would result in different motion primitives due to individual variability.…”

Section: Discussionmentioning

confidence: 99%

Incremental learning of human behaviors using hierarchical hidden Markov models

Kulić

Nakamura

2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper proposes a novel approach for extracting a model of movement primitives and their sequential relationships during online observation of human motion. In the proposed approach, movement primitives, modeled as hidden Markov models, are autonomously segmented and learned incrementally during observation. At the same time, a higher abstraction level hidden Markov model is also learned, encapsulating the relationship between the movement primitives. For the higher level model, each hidden state represents a motion primitive, and the observation function is based on the likelihood that the observed data is generated by the motion primitive model. An approach for incremental training of the higher order model during online observation is developed. The approach is validated on a dataset of continuous movement data.

show abstract

“…Shon et al [28] proposed a nonlinear regression algorithm for mapping motion capture data to a humanoid robot using a latent variable space to reduce the high-dimensional observation space. In [12] parametric Hidden Markov Models have been investigated for recognition and generation of human movements that explicitly encode the goal of the actions such as reaching and pointing motions. Zinnen et al [36] focused on the problem of recognizing gestures in continuous data streams using turning points to identify segments of interest in the human movements.…”

Section: Related Workmentioning

confidence: 99%

Arm gesture recognition and humanoid imitation using functional principal component analysis

Aleotti

Cionini

Fontanili

et al. 2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

A method is proposed for gesture recognition and humanoid imitation based on Functional Principal Component Analysis (FPCA). FPCA is a statistical technique of functional data analysis that has never been applied before for humanoid imitation. In functional data analysis data (e.g. gestures) are functions that can be considered as observations of a random variable on a functional space. FPCA is an extension of multivariate PCA that provides functional principal components which describe the modes of variation in the data. In the proposed approach FPCA is used for both unsupervised clustering of training data and gesture recognition.In this work we focus on arm gesture recognition. Human hand paths in Cartesian space are reconstructed from inertial sensors. Recognized gestures are reproduced by a small humanoid robot. The FPCA algorithm has also been compared to a state of the art algorithm for gesture classification based on Dynamic Time Warping (DTW). Results indicate that, in this domain, the FPCA algorithm achieves a comparable recognition rate while it outperforms DTW in terms of efficiency in execution time.

show abstract

Motion imitation and recognition using parametric hidden Markov models

Cited by 17 publications

References 13 publications

Probabilistic semantic models for manipulation action representation and extraction

Probabilistic semantic models for manipulation action representation and extraction

Incremental learning of human behaviors using hierarchical hidden Markov models

Arm gesture recognition and humanoid imitation using functional principal component analysis

Contact Info

Product

Resources

About