The DOI matches its Crossref record; 113 of the 117 references it cites were found in a registry or an index.
A tutorial on task-parameterized movement learning and retrieval
Open accessOverview
Integrity signals
Registry
Cites
Statistics
Verification
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 the citing paper
“The authors show how different trajectories can be generated from the same set of task parameters through weighting of the learned local models.”
From Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation (2019) · cites this paper as [7]
In the citing paper
“To address these issues, this paper builds on the confidence weighting scheme presented in [7] and the frame importance sampling in [8], and presents an autonomous method for weighting task frames during regression to improve model extrapolation, while retaining local structure observed in demonstration data.”
From Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation (2019) · cites this paper as [7]
In the citing paper
“The authors propose this is a useful mechanism for providing human prior knowledge about the importance of different task parameters to the model.”
From Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation (2019) · cites this paper as [7]
Citations
Cites
Maximum Likelihood from Incomplete Data Via the EM 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
Estimating the Dimension of a Model
Schwarz, G. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344136 · Cited by 47,033
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
Gaussian Processes for Machine Learning
Rasmussen, C. E., & Williams, C. K. I. (2005) · doi:10.7551/mitpress/3206.001.0001 · Cited by 11,705
Tensor Decompositions and Applications
Kolda, T. G., & Bader, B. W. (2009) · SIAM Review · doi:10.1137/07070111x · Cited by 10,624
On Spectral Clustering: Analysis and an algorithm
Ng, A. Y., Jordan, M. I., & Weiss, Y. (2001) · Cited by 8,159
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 7,330
Learning Deep Architectures for AI
Bengio, Y. (2009) · now publishers, Inc. eBooks · doi:10.1561/9781601982957 · Cited by 5,050
Optimal feedback control as a theory of motor coordination
Todorov, E., & Jordan, M. I. (2002) · Nature Neuroscience · doi:10.1038/nn963 · Cited by 3,081
Apprenticeship learning via inverse reinforcement learning
Abbeel, P., & Ng, A. Y. (2004) · International Conference on Machine Learning · doi:10.1145/1015330.1015430 · Cited by 2,855
Flagged first, then by citations
4 of the 117 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- Krishnan S, Garg A, Patil S, Lea C, Hager G, Abbeel P, Goldberg K (2015) Unsupervised surgical task segmentation with milestone learning. In: Proceedings of international symposium on robotics research (ISRR)
- MacQueen JB (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of of the 5th Berkeley symposium on mathematical statistics and probability, pp 281–297
- Wang Y, Zhu J (2015) DP-space: Bayesian nonparametric subspace clustering with small-variance asymptotics. In: Proceedings of international conference on machine learning (ICML), pp 1–9. Lille, France
Cited by
Sorted by citations
Items 101–200 of 427
A robot learning from demonstration framework for skillful small parts assembly
Hu, H., Yang, X., & Lou, Y. (2022) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-022-08652-z · Cited by 19
“By taking time/phase variable t as query variable, given the task frames (2), a retrieved or generalized assembly motion trajectory will be computed through TP-GMR algorithm [20].”
BackgroundMethodInfluentialLearning Riemannian Manifolds for Geodesic Motion Skills
Beik-Mohammadi, H., Hauberg, S., Arvanitidis, G., et al. (2021) · doi:10.15607/rss.2021.xvii.082 · Cited by 18
“Three main lines of work stand out in the LfD field, namely, (1) dynamical-system-based approaches [20] which focus on capturing motion dynamics, (2) probabilistic methods [6, 29, 19] which exploit data variability and model uncertainty, and more recently, (3) neu-Fig.”
BackgroundLauretti, C., Tamantini, C., & Zollo, L. (2024) · IEEE Access · doi:10.1109/access.2023.3349093 · Cited by 18
“Other approaches based on the Gaussian Mixture Model (GMM) and the Gaussian Mixture Regression (GMR) resort to probabilistic methods for merging multiple demonstrations and building a representative trajectory [31], [32], [33].”
Constraint-aware learning of policies by demonstration
Armesto, L., Moura, J., Ivan, V., et al. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364918784354 · Cited by 18
“In order to estimate the null-space policy, we propose to use locally weighted models Atkeson et al. (1997), however, the method used to model such policy is not that relevant and other wellknown approaches in DPL might be used too Ijspeert et al. (2003); Hussein et al. (2015); Calinon (2016).”
MethodMalekzadeh, M. S., Queißer, J. F., & Steil, J. J. (2019) · Advanced Robotics · doi:10.1080/01691864.2019.1587313 · Cited by 18
“A separate TP-GMM is learned for encoding each of the subtasks.”
BackgroundMethodInfluentialGeneralizing demonstrated motion trajectories using coordinate-free shape descriptors
Vochten, M., Laet, T. D., & Schutter, J. D. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.103291 · Cited by 18
Learning Soft Robotic Assembly Strategies from Successful and Failed Demonstrations
Hamaya, M., von Drigalski, F., Matsubara, T., Tanaka, K., Lee, R., Nakashima, C., Shibata, Y., & Ijiri, Y. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341504 · Cited by 18
“8 shows the fitted PC-GMM and GMR in y position, which was the direction toward the hole.”
MethodInfluentialLafleche, J.-F., Saunderson, S., & Nejat, G. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2885584 · Cited by 18
Trajectory-Based Skill Learning Using Generalized Cylinders
Ahmadzadeh, S. R., & Chernova, S. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00132 · Cited by 18
“To improve its generalization capabilities, a task parameterized extension of GMM/GMR was developed that assigns reference frames to task-related objects and landmarks (Calinon, 2016).”
MethodSequential robot imitation learning from observations
Tanwani, A. K., Yan, A., Lee, J., Calinon, S., & Goldberg, K. Y. (2021) · The International Journal of Robotics Research · doi:10.1177/02783649211032721 · Cited by 21
“…of the mixture model with the same set of basis vectors, albeit different scale with semi-tied covariance matrices (Gales, 1999; Tanwani and Calinon, 2016); and (3) Bayesian non-parametric sequence clustering under small variance asymptotics (SVA) (Kulis and Jordan, 2012; Roychowdhury et…”
BackgroundMethodInfluentialSelf-citationFuzzy dynamical system for robot learning motion skills from human demonstration
Teng, T., Gatti, M., Poni, S., Caldwell, D. G., & Chen, F. (2023) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2023.104406 · Cited by 16
The BesMan Learning Platform for Automated Robot Skill Learning
Gutzeit, L., Fabisch, A., Otto, M., Metzen, J. H., Hansen, J. M., Kirchner, F., & Kirchner, E. A. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00043 · Cited by 18
“Works by Manschitz et al. (2016); Calinon (2016); Niekum et al. (2015) select the reference frame automatically but we did not consider this here.”
BackgroundAn Energy-based Approach to Ensure the Stability of Learned Dynamical Systems
Saveriano, M. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196978 · Cited by 20
“For instance [2], [21] introduce task-dependent parameters to customize the robot motion, while [22] investigates the possibility to merge multiple DMPs to plan more complex pose trajectories.”
BackgroundPrioritized Inverse Kinematics: Generalization
An, S.-I., & Lee, D. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2927945 · Cited by 17
“PRIORITIZED Inverse Kinematics (PIK) in the velocity level has been studied intensively for decades along with the growth of the robotic society and the study on the PIK has been used and expanded in many areas such as constrained PIK [1][2][3][4], task switching [5][6][7][8][9], prioritized control [10][11][12][13][1…”
BackgroundCalinon, S., & Lee, D. (2017) · Springer eBooks · doi:10.1007/978-94-007-7194-9_68-1 · Cited by 17
Self-citationAdaptive heterogeneous multi-robot collaboration from formal task specifications
Schillinger, P., García, S., Makris, A., Roditakis, K., Logothetis, M., Alevizos, K., Ren, W., Tajvar, P., Pelliccione, P., Argyros, A., et al. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103866 · Cited by 16
Passive Bimanual Skills Learning From Demonstration With Motion Graph Attention Networks
Dong, Z., Li, Z., Yan, Y., et al. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3152974 · Cited by 16
“This paradigm shares the same motivation as TP-GMM [24].”
MethodSelf-citationOh, H., Sasaki, H., Michael, B., & Matsubara, T. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.11.008 · Cited by 16
MILD: Multimodal Interactive Latent Dynamics for Learning Human-Robot Interaction
Prasad, V., Koert, D., Stock‐Homburg, R., Peters, J., & Chalvatzaki, G. (2022) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids53995.2022.10000239 · Cited by 17
“For a more in-depth explanation of training GMMs, HMMs and HSMMs in the context of robot learning, we refer the reader to [6], [32].”
BackgroundLearning assistive teleoperation behaviors from demonstration
Havoutis, I., & Calinon, S. (2016) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2016.7784308 · Cited by 16
“Next, we use Gaussian Mixture Regression (GMR) to compute and estimate the desired probe angle (x3) conditioned on the position of the probe in the task frame.”
MethodInfluentialSelf-citationA Brief Survey on the Role of Dimensionality Reduction in Manipulation Learning and Control
Ficuciello, F., Falco, P., & Calinon, S. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2818933 · Cited by 16
“Such trajectory distribution encoding with dynamic features has been exploited in robotics for human-like motion planning and control [36], [35], [37].”
BackgroundMethodSelf-citationIncremental Skill Learning of Stable Dynamical Systems
Saveriano, M., & Lee, D. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594474 · Cited by 20
“Taskparameterized motion primitives [9], [28] extend the standard DMP by introducing extra task-dependent parameters useful to adapt robot movements to novel scenarios.”
BackgroundGómez-García, J. A., Moro-Velázquez, L., Mendes-Laureano, J., et al. (2019) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2019.03.027 · Cited by 16
Small-variance asymptotics for non-parametric online robot learning
Tanwani, A. K., & Calinon, S. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364918816374 · Cited by 16
“The stepwise reference trajectory is tracked in a smooth manner with a finite-horizon linear quadratic tracking controller (Tanwani and Calinon 2016) (see Appx.”
BackgroundMethodInfluentialSelf-citationHierarchical Neural Dynamic Policies
Bahl, S., Gupta, A. K., & Pathak, D. (2021) · Robotics: Science and Systems · doi:10.15607/rss.2021.xvii.023 · Cited by 17
Imitation learning for coordinated human–robot collaboration based on hidden state-space models
Wang, L., Wang, G., Jia, S., et al. (2022) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2021.102310 · Cited by 16
A Hybrid Framework for Understanding and Predicting Human Reaching Motions
Oguz, O. S., Zhou, Z., & Wollherr, D. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00027 · Cited by 15
“Especially,itisknownthatGMMs tendtoperformpoorlyinhigh-dimensionalspaceswhenfewdata pointsareavailable(Calinon,2016).”
Toward Real-time Assessment of Workload: A Bayesian Inference Approach
Luo, R., Wang, Y., Weng, Y., Paul, V., Brudnak, M., Jayakumar, P., Reed, M., Stein, J. L., Ersal, T., & Yang, X. J. (2019) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1071181319631293 · Cited by 14
Teaching Human Teachers to Teach Robot Learners
Sena, A., Zhao, Y., & Howard, M. J. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8461194 · Cited by 15
“Each user-provided demonstration, Dm, contains Tm data points which are then concatenated to form a data set, D, of N points, with N = ∑M 1 Tm [13].”
BackgroundMethodRing Gaussian Mixture Modelling and Regression for collaborative robots
Zaatari, S. E., Li, W., & Usman, Z. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103864 · Cited by 15
“However, since HMM models the sequence between a finite discrete number of states, it is intrinsically suited for task-level learning rather than motion-level learning [13].”
BackgroundMethodInfluentialIntent inference in shared-control teleoperation system in consideration of user behavior
Wang, L., Li, Q., Lam, J., Wang, Z., & Zhang, Z. (2021) · Complex & Intelligent Systems · doi:10.1007/s40747-021-00533-4 · Cited by 16
Safe and Adaptive 3-D Locomotion via Constrained Task-Space Imitation Learning
Ding, J., Lam, T. L., Ge, L., Pang, J., & Huang, Y. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3239099 · Cited by 15
“We use Gaussian mixture model (GMM) to model the joint probability distribution P ( t, η ) [34], [39], [40], yielding where π m , μ m = µ t,m µ η,m and Σ m = Σ tt,m Σ tη,m Σ ηt,m Σ ηη,m , respectively correspond to the prior probability, mean, and covariance of the m th Gaussian component in GMM.…”
MethodLearning and generalization of task-parameterized skills through few human demonstrations
Prados, A., Garrido, S., & Barber, R. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108310 · Cited by 15
Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models
Tanwani, A. K., Lee, J., Thananjeyan, B., Laskey, M., Krishnan, S., Fox, R., Goldberg, K. Y., & Calinon, S. (2019) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-44051-0_12 · Cited by 14
Self-citationLearning Haptic Exploration Schemes for Adaptive Task Execution
Eiband, T., Saveriano, M., & Lee, D. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793934 · Cited by 17
“The computations of the GMM and GMR are carried out using pbdlib [39].”
MethodsEMG-Driven Functional Electrical Stimulation Tuning via Muscle Force
Zhou, Y., Zeng, J., Li, K., Hargrove, L. J., & Liu, H. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.3026280 · Cited by 15
“Due to the exceptionally powerful ability, GMR has been very successfully applied in robotics control to reproduce smooth averaged motor trajectories with full covariance [31].”
MethodBian, G., Chen, Z., Li, Z., et al. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120134 · Cited by 14
Generating Calligraphic Trajectories with Model Predictive Control
Berio, D., Calinon, S., & Leymarie, F. F. (2017) · Goldsmiths (University of London) · Cited by 14
Self-citationGuo, M., & Bürger, M. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3111481 · Cited by 14
“Compared with traditional motion planning from [11], LfD is an intuitive way to transfer human skills to robots, see [3], [4], [12].”
InfluentialLearning to Hit: A statistical Dynamical System based approach
Khurana, H., Bombile, M., & Billard, A. G. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635976 · Cited by 14
“The model has been implemented using the architecture in [17].”
MethodErgodic imitation: Learning from what to do and what not to do
Kalinowska, A., Prabhakar, A., Fitzsimons, K., & Murphey, T. D. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561746 · Cited by 14
Restoring Application Traffic of Latency-Sensitive Networked Systems Using Adversarial Autoencoders
Sacco, A., Esposito, F., & Marchetto, G. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3192305 · Cited by 13
Supporting Semantic Capture During Kinesthetic Teaching of Collaborative Industrial Robots
Stenmark, M., Haage, M., Topp, E. A., et al. (2018) · International Journal of Semantic Computing · doi:10.1142/s1793351x18400093 · Cited by 13
Hybrid Probabilistic Trajectory Optimization Using Null-Space Exploration
Huang, Y., Silvério, J., Rozo, L., et al. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460550 · Cited by 13
“It is worth pointing out that the prediction in (2) can be approximated by a single Gaussian distribution [9], which facilitates the combination of trajectory constraints coming from both Cartesian and joint spaces, as explained in the next section.”
BackgroundMethodA learning from demonstration framework for implementation of a feeding task
Ettehadi, N., & Behal, A. (2018) · Encyclopedia with Semantic Computing and Robotic Intelligence · doi:10.1142/s2529737618500016 · Cited by 13
Reactive motion generation on learned Riemannian manifolds
Beik-Mohammadi, H., Hauberg, S., Arvanitidis, G., Neumann, G., & Rozo, L. D. (2023) · The International Journal of Robotics Research · doi:10.1177/02783649231193046 · Cited by 12
“The current LfD approaches do not need an environment model and some can quickly adapt to settings with dynamic targets (Osa et al. 2018; Ijspeert et al. 2013; Calinon 2016).”
BackgroundInfluentialEnhanced task parameterized dynamic movement primitives by GMM to solve manipulation tasks
Li, J., Cong, M., Liu, D., et al. (2023) · Robotic Intelligence and Automation · doi:10.1108/ria-07-2022-0199 · Cited by 12
PI-ELM: Reinforcement learning-based adaptable policy improvement for dynamical system
Hu, Y., Wang, X., Liu, Y., Ding, W., & Knoll, A. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119700 · Cited by 12
Liu, J., Sim, H., Li, C., Tan, K. C., & Chen, F. (2023) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc49753.2023.10383296 · Cited by 12
“More details can be found in the appendix of [12].”
BackgroundMethodLearning robot anomaly recovery skills from multiple time-driven demonstrations
Wu, H., Yan, W., Xu, Z., Li, S., & Zhou, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.036 · Cited by 12
Real-Time Workload Estimation Using Eye Tracking: A Bayesian Inference Approach
Luo, R., Weng, Y., Jayakumar, P., Brudnak, M., Paul, V., Desaraju, V. R., Stein, J. L., Ersal, T., & Yang, X. J. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2205274 · Cited by 12
“The parameters of the HMMs were learned by the Expectation Maximization (EM) algorithm using the open source implementations from Rozo et al. (2016) and Calinon (2016).”
Alizadeh, T., & Malekzadeh, M. (2016) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2016.7844040 · Cited by 12
“As future work, the extension of the proposed approach to the trajectory-GMM [22] method in which different sub-tasks could be learned using a single model will be considered.”
MethodGeneralized Cylinders for Learning, Reproduction, Generalization, and Refinement of Robot Skills
Ahmadzadeh, S. R., Rana, M. A., & Chernova, S. (2017) · doi:10.15607/rss.2017.xiii.021 · Cited by 12
“For GMM/GMR we tuned the number of Gaussian components (5 and 10, in figures (c) and (d), respectively), and for DMPs, we tuned the number of attractors (5 and 10, in figures (e) and (f), respectively).”
MethodInfluentialNon-parametric Imitation Learning of Robot Motor Skills
Huang, Y., Rozo, L., Silvério, J., et al. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794267 · Cited by 12
“In order to make the imitation and adaptation of human skills feasible, many approaches have been developed, such as dynamic movement primitives (DMP) [2], Gaussian mixture model (GMM) [4], and probabilistic movement primitives (ProMP) [7].”
BackgroundMethodInfluentialManipulation Learning on Humanoid Robots
Gams, A., Petrič, T., Nemec, B., & Ude, A. (2022) · Current Robotics Reports · doi:10.1007/s43154-022-00082-9 · Cited by 11
“Generalization has been widely adopted in generation of motion also with variations of DMPs and other movement representations [70, 71].”
BackgroundA geometric optimal control approach for imitation and generalization of manipulation skills
Ti, B., Razmjoo, A., Gao, Y., Zhao, J., & Calinon, S. (2023) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2023.104413 · Cited by 11
“Previously, we have shown the advantage of using multiple coordinate systems located at di ff erent landmarks such as objects [43].”
BackgroundMethodInfluentialSelf-citationThe e-Bike motor assembly: Towards advanced robotic manipulation for flexible manufacturing
Rozo, L. D., Kupcsik, A., Schillinger, P., Guo, M., Krug, R., van Duijkeren, N., Spies, M., Kesper, P., Hoppe, S., Ziesche, H., et al. (2023) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2023.102637 · Cited by 14
Improved Generalization of Probabilistic Movement Primitives for Manipulation Trajectories
Yao, X., Chen, Y., & Tripp, B. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3333741 · Cited by 11
“By utilizing these task parameters, we converted the trajectory from the global reference frame to the j th local object reference frame, resulting in x ( j ) t , as explained in [12].”
MethodInfluentialA Probabilistic Approach to Multi-Modal Adaptive Virtual Fixtures
Mühlbauer, M., Hulin, T., Weber, B., et al. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3384759 · Cited by 11
“In our previous work [3] we hand-designed an arbitration function between position-and vision-based fixtures.”
BackgroundMethodInfluentialSelf-citationRuan, S., Liu, W., Wang, X., Meng, X., & Chirikjian, G. S. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3390052 · Cited by 11
“The task-parameterizedGaussianmixturemodel(TP-GMM)[29], [30]encodesthedemonstrationsusingvirtualspring–damper systemsinmultiplereferenceframes.”
MoVEInt: Mixture of Variational Experts for Learning Human–Robot Interactions From Demonstrations
Prasad, V., Kshirsagar, A., Koert, D., Stock‐Homburg, R., Peters, J., & Chalvatzaki, G. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3396074 · Cited by 11
“Learning a joint distribution over the degrees of freedom of a human and a robot has been widely used in learning HRI from demonstrations [5], [6], [27], [28], [29], [30], [31].”
MethodInfluentialMéndez, A., Prados, A., Menéndez, E., & Barber, R. (2024) · IEEE Access · doi:10.1109/access.2024.3422808 · Cited by 11
“The task-parameterized Gaussian mixture models (TPGMM) [73] have been proposed in recent decades as an approach to robot programming through demonstration.”
MethodThe Art of Imitation: Learning Long-Horizon Manipulation Tasks From Few Demonstrations
von Hartz, J. O., Welschehold, T., Valada, A., & Boedecker, J. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3487506 · Cited by 16
“Fourth, when learning from visual observations, generating a set of candidate task parameters is an open problem [8], [9].”
BackgroundInfluentialTowards Minimal Intervention Control with Competing Constraints
Huang, Y., Silvério, J., & Caldwell, D. G. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594235 · Cited by 9
“In contrast, we here focus on a control problem and prove that (13) can be simplified by replacing different trajectory constraints by their Gaussian product (as shown in (21)), which offers an interesting insight when the previous work [4], [6] are combined with the finite LQR.”
BackgroundMethodInfluentialRana, M. A., Chen, D., Williams, J. M., Chu, V. C.-M., Ahmadzadeh, S. R., & Chernova, S. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197470 · Cited by 11
“Based on the choice of motion generation strategy, the majority of skill learning approaches can be further broadly categorized into four groups: time-invariant (stable) dynamical systems [2], [3], [13], time-dependent dynamical systems [7], [9], [10], time-dependent statistical methods [8], [14], [15], and arclength…”
BackgroundMethodLearning human compliant behavior from demonstration for force-based robot manipulation
Deng, Z., Mi, J., Chen, Z., Einig, L., Zou, C., & Zhang, J. (2016) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2016.7866342 · Cited by 12
“A conclusion of task-parameterized movement learning has been presented [8].”
BackgroundA Linearly Constrained Nonparametric Framework for Imitation Learning
Huang, Y., & Caldwell, D. G. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196821 · Cited by 11
“, [20]), we can obtain η1 η2 η3 .”
BackgroundRobust Gait Synthesis Combining Constrained Optimization and Imitation Learning
Ding, J., Xiao, X., Tsagarakis, N. G., et al. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341146 · Cited by 11
“Subsequently, Gaussian Mixture Regression (GMR) [33], [36], [37] is used to retrieve a probabilistic reference trajectory Dr = {tn, μ̂n, Σ̂n} N n=1, which in fact encapsulates the distribution of demonstrations and will be used to train KMP.”
MethodA Framework of Improving Human Demonstration Efficiency for Goal-Directed Robot Skill Learning
Wu, H., Yan, W., Xu, Z., & Zhou, X. (2021) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2021.3137262 · Cited by 11
“…recent decade, several representative solutions should be highlighted, including the Gaussian mixture model-Gaussian mixture regression (GMM-GMR) [14], [15], probabilistic movement primitives (ProMP) [16], [17], kernelized movement primitives (KMP) [18], [19], parametric hidden Markov models…”
BackgroundDynamic Graffiti Stylisation with Stochastic Optimal Control
Berio, D., Calinon, S., & Leymarie, F. F. (2017) · International Conference on Movement and Computing (MOCO) · doi:10.1145/3077981.3078044 · Cited by 11
“optimal trajectory can be retrieved iteratively using dynamic programming [5, 9], or in batch form by solving a large regularised least squares problem.”
MethodSelf-citationEwerton, M., Maeda, G. J., Koert, D., et al. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967856 · Cited by 11
“Gaussian Mixture Regression (GMR) [6] has been used to generate a behavior according to the learned model.”
MethodAkbulut, M. T., Öztop, E., Seker, M. Y., Xue, H., Tekden, A. E., & Uğur, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.11334 · Cited by 22
“Among others, learning methods that are based on dynamic systems [16] and statistical modeling [17] have been popular in the recent years.”
BackgroundLogic Learning From Demonstrations for Multi-Step Manipulation Tasks in Dynamic Environments
Zhang, Y., Xue, T., Razmjoo, A., & Calinon, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3418276 · Cited by 13
“While traditional LfD methods like Dynamic Movement Primitives (DMP) [6], Task-parameterized Gaussian Mixture Model (TP-GMM) [7], or Dynamical Systems (DS) [8] can generalize demonstrated trajectories for new tasks or react to disturbances at the motion level, long-horizon ′ 0 to the goal state G .”
MethodSelf-citationUsing Learning from Demonstration (LfD) to perform the complete apple harvesting task
van de Ven, R., Shoushtari, A. L., Nieuwenhuizen, A. T., et al. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109195 · Cited by 10
The Developments and Challenges Toward Dexterous and Embodied Robotic Manipulation: A Survey
Li, G., Wang, R., Xu, P., Ye, Q., & Chen, J. (2025) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2025.3642671 · Cited by 33
“Commonly used methods include dynamic movement primitives [66], the stable estimator of dynamical systems [67] , probabilistic movement primitives [68], the task-parameterized GMM [69], and kernelized movement primitives [70].”
Learning and extrapolation of robotic skills using task-parameterized equation learner networks
Pérez-Villeda, H. M., Piater, J., & Saveriano, M. (2022) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2022.104309 · Cited by 11
A Cloud-Based Robust Semaphore Mirroring System for Social Robots
Tian, N., Kuo, B., Ren, X., et al. (2018) · 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2018.8560553 · Cited by 10
“Therefore, many works have been dedicated to imitating human gestures [12]–[17], human demonstrations [14], [18] and human social interactions [19], [20] using humanoid robots.”
BackgroundMethodColomé, A., & Carme Torras, A. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2857921 · Cited by 10
Öztop, E., & Uğur, E. (2021) · Springer eBooks · doi:10.1007/978-3-642-41610-1_203-1 · Cited by 10
Learning and Reproduction of Therapist’s Semi-Periodic Motions during Robotic Rehabilitation
Martinez, C., & Tavakoli, M. (2019) · Robotica · doi:10.1017/s0263574719000651 · Cited by 9
“We implement the GMM and GMR algorithms using the code presented in.(22)”
MethodJin, Z., Qin, D., Liu, A., Zhang, W., & Li, Y. (2023) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2023.102526 · Cited by 9
Adaptive motion planning framework by learning from demonstration
Li, X., Cheng, H., & Liang, X. (2019) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-10-2018-0216 · Cited by 9
Robot Programming by Demonstration with Local Human Correction for Assembly
Cao, Z., Hu, H., Zhao, Z., et al. (2019) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961854 · Cited by 9
“the GMM to task-parametric Gaussian mixture model [15].”
Method(2019) · Conference on Robot Learning
Learning context-adaptive task constraints for robotic manipulation
Mronga, D., & Kirchner, F. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103779 · Cited by 9
“Previously introduced approaches like the one described in [22] focus on generalization over different start or target”
BackgroundMethodVergara, C., Schutter, J. D., & Aertbeliën, E. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9364328 · Cited by 9
“This aspect is important to deal with the Machine Learning phenomenon: curse of dimensionality [10].”
BackgroundMethodLi, C., Li, Z., Jiang, Z., Cui, S., Liu, H., & Cai, H. (2021) · Science China Technological Sciences · doi:10.1007/s11431-021-1901-x · Cited by 9
“With the strategy, manipulators can learn skills from human operators and reproduce the skills in different conditions [14].”
BackgroundCalinon, S., & Lee, D. (2018) · Springer eBooks · doi:10.1007/978-94-007-7194-9_68-2 · Cited by 9
Self-citationGeneralization of orientational motion in unit quaternion space
Kramberger, A., Gams, A., Nemec, B., & Ude, A. (2016) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2016.7803366 · Cited by 12
“These were extensively applied by Calinon for generalization, with an excellent tutorial and an overview provided in [15].”
BackgroundMethodComplex Sequential Tasks Learning with Bayesian Inference and Gaussian Mixture Model
Zhang, H., Han, X., Zhang, W., & Zhou, W. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8665229 · Cited by 10
“Among of which, dynamical system approaches based on the GMM and GMR [28]–[31] as well as DMP [15] are most popular.”
BackgroundPrados, A., Espinoza, G., Moreno, L. E., & Barber, R. (2025) · Biomimetics · doi:10.3390/biomimetics10010064 · Cited by 8
A Non-Linear Manifold Alignment Approach to Robot Learning from Demonstrations
Makondo, N., Hiratsuka, M., Rosman, B., & Hasegawa, O. (2018) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2018.p0265 · Cited by 7
“Statistical modeling [5, 8] and dynamical systems [9, 10] are amongst the most popular approaches.”
BackgroundCompliant Motion Adaptation with Dynamical System during Robot-Environment Interaction
Huang, H., Yang, C., & Su, C. (2020) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim43001.2020.9158894 · Cited by 8
“As the nonlinear property of h(·), different approximation or regression methods have been adopted to estimate the motion model [19], [20], [21].”
MethodBayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies
Oh, H., Sasaki, H., Michael, B., & Matsubara, T. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561573 · Cited by 8
Bargmann, D., Tenbrock, P. G., Halt, L., Nägele, F., Kraus, W., & Huber, M. F. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9658707 · Cited by 8
“Probabilistic methods like probabilistic motion primitives [25] or gaussian mixture models [26], [27] can increase robustness and reusablitiy.”
MethodInfluentialRobot Learning from Demonstration Using Elastic Maps
Hertel, B., Pelland, M., & Ahmadzadeh, S. R. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981241 · Cited by 8
“However, GMM/GMR has been extended to incorporate multiple frames which allow for the ability to generalize a reproduction to new conditions [13].”
BackgroundStochastic-skill-level-based Shared Control for Human Training in Urban Air Mobility Scenario
Byeon, S., Choi, J., Zhang, Y., & Hwang, I. (2023) · ACM Transactions on Human-Robot Interaction · doi:10.1145/3603194 · Cited by 8
“See [10] for the details and tutorial source codes.”
BackgroundMethodInfluentialLiao, Z., Tassi, F., Gong, C., Leonori, M., Zhao, F., Jiang, G., & Ajoudani, A. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3469961 · Cited by 9
“…mainly focus on motion learning, especially for the point-to-point movement trajectory, such as DMP [2], dynamic system (DS) [3], Gaussian mixture model and regression [4], probabilistic movement primitives [5], ker-nelized movement primitives [6], and hidden (semi) Markov model (H(s)MM) [7], etc.”
NetLfD: Network-Aware Learning From Demonstration for In-Contact Skills via Teleoperation
Güleçyüz, B., von Büren, V., Xu, X. W., & Steinbach, E. G. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3313494 · Cited by 8
Teaching Persian Sign Language to a Social Robot via the Learning from Demonstrations Approach
Hosseini, S. R., Taheri, A., Meghdari, A. F., & Alemi, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-35888-4_61 · Cited by 8
Metadata
- Authors
- Calinon, S.
- Affiliations
- Idiap Research Institute (CH)
- Corresponding author
- Calinon, Sylvain
- ORCID
- Calinon, Sylvain
- Venue
- Intelligent Service Robotics
- Published
- 2015-09-26
- Volume
- 9
- Issue
- 1
- Pages
- 1-29
- ISSN
- 1861-2776 (ISSN-L)
- 1861-2784
- OpenAlex
- W2100993276
- Cited by
- 422
- References
- 117
- Citations by year
- 2026: 31 · 2025: 48 · 2024: 43 · 2023: 40 · 2022: 30 · 2021: 63 · 2020: 41 · 2019: 49 · 2018: 43 · 2017: 26 · 2016: 8
- FWCI
- 23.76
- Type
- journal article
- Language
- en
- Open access
- green
- infoscience.epfl.ch
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Intelligent Service Robotics (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, other-oa)
- Funders
- EC Horizon 2020 (635491)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
- Keywords
- reference frames, coordinate systems, basis functions, service robotics, robotic manipulation, behavior transfer
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
