Learning Robot Manipulation Tasks With Task-Parameterized Semitied Hidden Semi-Markov Model
Open accessAbstract
In this letter, we investigate the semitied Gaussian mixture models for robust learning and adaptation of robot manipulation tasks. We make use of the spatial and temporal correlation in the data by tying the covariance matrices of the mixture model with common synergistic directions/basis vectors, instead of estimating full covariance matrices for each cluster in the mixture. This allows the reuse of the discovered synergies in different parts of the task having similar coordination patterns. We extend the approach to task-parameterized and hidden semi-Markov models for autonomous adaptation to changing environmental situations. The planned movement sequence from the model is smoothly followed with a finite horizon linear quadratic tracking controller. Experiments to encode whole body motion data in simulation, followed by valve opening and pick-and-place via obstacle avoidance tasks with the Baxter robot, show improvement over standard Gaussian mixture models with much less parameters and better generalization ability.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In a reaching task test data set, the proposed method shows significant improvement over original TP-GMR and mPGMM.
“Significant improvement using the proposed method is shown in a test data set for a reaching task, versus the original TP-GMR method described in [4] and a modified TP method described in [5], specifically designed to improve extrapolation of learned skills.”
From Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation (2019) · cites this paper as [5]
mPGMM improves the extrapolation abilities of Task-Parameterised models while reducing computation time compared with TP-GMR.
“The authors show the proposed method improves the extrapolation abilities of TP models while reducing the computation time required compared to TP-GMR.”
From Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation (2019) · cites this paper as [5]
mPGMM uses an altered Expectation Maximisation procedure to improve the extrapolation abilities of Task-Parameterised models.
“In an attempt to improve extrapolation abilities of TP, [5] propose a modified Parameteric Gaussian Mixture Model (mPGMM) that uses an altered Expectation Maximisation (EM) procedure to improve the extrapolation abilities of the learnt model.”
From Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation (2019) · cites this paper as [5]
mPGMM can fail to preserve local structure, resulting in failure to execute the desired task effectively.
“While the proposed method helps in extrapolation of the demonstrated task, this method can fail to preserve local structure, resulting in failure to execute the desired task effectively.”
From Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation (2019) · cites this paper as [5]
Cites
Maximum Likelihood from Incomplete Data Via the <i>EM</i> Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444 · see citing works
A tutorial on hidden Markov models and selected applications in speech recognition
Rabiner, L. R. (1989) · Proceedings of the IEEE · doi:10.1109/5.18626 · Cited by 22,743 · see citing works
Sparse Subspace Clustering: Algorithm, Theory, and Applications
Elhamifar, E., & Vidal, R. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.57 · Cited by 3,130 · see citing works
Mixtures of Probabilistic Principal Component Analyzers
Tipping, M. E., & Bishop, C. (1999) · Neural Computation · doi:10.1162/089976699300016728 · Cited by 1,874 · see citing works
Maximum likelihood linear transformations for HMM-based speech recognition
Gales, M. J. F. (1998) · Computer Speech & Language · doi:10.1006/csla.1998.0043 · Cited by 1,482 · see citing works
Principles of sensorimotor learning
Wolpert, D. M., Diedrichsen, J., & Flanagan, J. R. (2011) · Nature Reviews Neuroscience · doi:10.1038/nrn3112 · Cited by 1,391 · see citing works
Combinations of muscle synergies in the construction of a natural motor behavior
d’Avella, A., Saltiel, P., & Bizzi, E. (2003) · Nature Neuroscience · doi:10.1038/nn1010 · Cited by 1,348 · see citing works
Yu, S. (2009) · Artificial Intelligence · doi:10.1016/j.artint.2009.11.011 · Cited by 737 · see citing works
Parametric hidden Markov models for gesture recognition
Wilson, A. D., & Bobick, A. (1999) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.790429 · Cited by 574 · see citing works
(2001) · Cited by 555 · see citing works
Semi-tied covariance matrices for hidden Markov models
Gales, M. (1999) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.759034 · Cited by 537 · see citing works
Model-based clustering of high-dimensional data: A review
Bouveyron, C., & Brunet-Saumard, C. (2012) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2012.12.008 · Cited by 470 · see citing works
A tutorial on task-parameterized movement learning and retrieval
Calinon, S. (2016) · Intelligent Service Robotics · doi:10.1007/s11370-015-0187-9 · Cited by 422 · cited 1× · see citing works
“Task-parameterized GMMs in [14], [22], [23] can handle new environmental situations by defining external frames of reference.”
BackgroundSelf-citationParsimonious Gaussian mixture models
McNicholas, P. D., & Murphy, T. B. (2008) · Statistics and Computing · doi:10.1007/s11222-008-9056-0 · Cited by 346 · see citing works
Modelling high-dimensional data by mixtures of factor analyzers
McLachlan, G. J., Peel, D. A., & Bean, R. W. (2003) · Computational Statistics & Data Analysis · doi:10.1016/s0167-9473(02)00183-4 · Cited by 283 · see citing works
A task-parameterized probabilistic model with minimal intervention control
Calinon, S., Bruno, D., & Caldwell, D. G. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907339 · Cited by 149 · see citing works
Self-citationTask Parameterization Using Continuous Constraints Extracted From Human Demonstrations
Ureche, A. L. P., Umezawa, K., Nakamura, Y., et al. (2015) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2495003 · Cited by 67 · see citing works
Learning bimanual end-effector poses from demonstrations using task-parameterized dynamical systems
Silvério, J., Rozo, L. D., Calinon, S., & Caldwell, D. G. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353413 · Cited by 63 · see citing works
Self-citation3D Human Motion Tracking with a Coordinated Mixture of Factor Analyzers
Li, R., Tian, T.-P., Sclaroff, S., & Yang, M. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-009-0283-4 · Cited by 61 · see citing works
Modeling Inverse Covariance Matricesby Basis Expansion
Olsen, P. A., & Gopinath, R. (2004) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/tsa.2003.819943 · Cited by 59 · see citing works
Encoding the time and space constraints of a task in explicit-duration Hidden Markov Model
Calinon, S., Pistillo, A., & Caldwell, D. G. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094418 · Cited by 54 · see citing works
Self-citationField, M., Stirling, D. A., Pan, Z. S., & Naghdy, F. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2414277 · Cited by 39 · see citing works
DexROV: Dexterous Undersea Inspection and Maintenance in Presence of Communication Latencies
Gancet, J., Urbina, D. A., Letier, P., et al. (2015) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2015.06.036 · Cited by 32 · see citing works
Encoding the time and space constraints of a task in explicit-duration Hidden Markov Model
Calinon, S., Pistillo, A., & Caldwell, D. G. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6048064 · Cited by 30 · see citing works
Self-citationDP-space: Bayesian Nonparametric Subspace Clustering with Small-variance Asymptotics
Wang, Y., & Zhu, J. (2015) · Cited by 24 · see citing works
Goel, N. K., & Gopinath, R. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2001.940872 · Cited by 7 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Sena, A., Michael, B., & Howard, M. (2019) · 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967688 · Cited by 26 · see citing works
“, [14].”
- Authors
- Tanwani, A. K., & Calinon, S.
- Affiliations
- École Polytechnique Fédérale de Lausanne (CH)
- Venue
- IEEE Robotics and Automation Letters
- Published
- 2016-01
- Volume
- 1
- Issue
- 1
- Pages
- 235-242
- ISSN
- 2377-3766 (ISSN-L)
- 2377-3774
- OpenAlex
- W2285373626
- Cited by
- 84
- References
- 26
- Citations by year
- 2026: 4 · 2025: 8 · 2024: 9 · 2023: 4 · 2022: 10 · 2021: 5 · 2020: 8 · 2019: 9 · 2018: 14 · 2017: 11 · 2016: 2
- FWCI
- 10.09
- Type
- journal article
- Language
- en
- Open access
- green
- ieeexplore.ieee.org
- Locations
- IEEE Robotics and Automation Letters (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Funders
- DexROV project through the EC Horizon 2020 programme (635491)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Motor Control and Adaptation
- Keywords
- robotic manipulation, hidden semi-Markov model, synergistic effect, pick-and-place, valve opening, Baxter robot, obstacle avoidance, autonomous adaptation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
