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
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 301–400 of 427
Data-Driven Forward Stochastic Reachability Analysis for Human-in-the-Loop Systems
Choi, J., Byeon, S., & Hwang, I. (2023) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc49753.2023.10383447 · Cited by 2
“Let the augmented trajectory of the system be defined as Then, the proper parameters of the joint probability distribution P ( u , x ) can be computed by feeding ζ to the Expectation Maximization (EM) algorithm [10].”
MethodBowen, C., & Alterovitz, R. (2020) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-44051-0_15 · Cited by 2
Toward Generalization of Bipedal Gait Cycle During Stair Climbing Using Learning From Demonstration
Goldfarb, N., Bales, C., & Fischer, G. S. (2021) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2021.3070019 · Cited by 2
“GMM/GMR code used in this paper were based on Calinon open-source libraries [16], [29], [30].”
Method(2020) · eScholarship (California Digital Library) · Cited by 2
Efficiently Learning Manipulations by Selecting Structured Skill Representations
Sharma, M. K., & Kroemer, O. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981422 · Cited by 1
“Some of the widely used skill representations include, Dynamic Movement Primitives (DMPs) [6], [21], [22], Neural Networks [23], [24], [25], Task-Parameterized GMMs (TP-GMMs) [26], [27].”
MethodLearning Compliant Assembly Strategy From Demonstration
Liu, S., Sheng, J., & Ou, Y. (2023) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar58764.2023.10249450 · Cited by 1
“Generally, regression algorithms in machine learning are used to build models, such as Gaussian Mixture Regression (GMR)[20], Gaussian Process Regression (GPR)[21], Support Vector Regression (SVR)[22], Locally Weighted Regression (LWR)[13], Hidden Markov Model (HMM)[23], etc. GMR needs to store all…”
MethodA Novel Approach for Efficient Gaussian Mixture Model using Dynamics-motivated Optimal Excitation
Kim, T., Jeong, J., Kong, T., Lee, H., & Oh, S. (2024) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie54533.2024.10595794 · Cited by 1
“The formula for GMR, a method for modeling dynamics with GMM and using it for regression, is as follows [20].”
MethodComparison of motion encoding frameworks on human manipulation actions
Jahn, L., Wörgötter, F., & Kulvičius, T. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104869 · Cited by 1
“There are multiple ways to encode trajectories using GMMs [9], [13], [7], [8].”
InfluentialChoi, J., Byeon, S., & Hwang, I. (2024) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2024.3518118 · Cited by 1
“The weight, mean, and covariance, i.e., parameters of H , can be obtained by feeding ζ to a clustering algorithm (e.g., expectation–maximization (EM) algorithm) where T is the given trajectory of a target HITL system and 26].”
Generalizable Motion Policies Through Keypoint Parameterization and Transportation Maps
Franzese, G., Prakash, R., Santina, C. D., & Kober, J. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3582821 · Cited by 2
“Ideally,therobotwouldgeneralizethelearnedskilltonovel o.o.d. situationswithoutrequiringtheaggregationofhundreds ofthousandsofdemonstrations[11],regulateitsstiffnessas afunctionoftheuncertainty[12],oractivelyaskfordatain uncertain situations [4].”
InfluentialGaussian path model library for intuitive robot motion programming by demonstration
Soutukorva, S., Suomalainen, M., Kollingbaum, M. J., et al. (2025) · 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case58245.2025.11163890 · Cited by 1
“Lately, different kinds of Gaussian-based models have proven popular; a good overview with examples is provided in [3].”
Koelmans, T., Mol, N., & Prendergast, J. M. (2025) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids65713.2025.11203100 · Cited by 1
“Other approaches, such as Gaussian Mixture Models (GMMs) and Inverse Reinforcement Learning (IRL) [15], [16] typically require multiple demonstrations.”
Madera, J., & Fey, A. M. (2025) · IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) · doi:10.1109/ro-man63969.2025.11217863 · Cited by 1
“Previous work has fused GMM models represented in different task frames which allows for adaptive robot models [32].”
One-Shot Robust Imitation Learning for Long-Horizon Visuomotor Tasks from Unsegmented Demonstrations
Wu, S., Wang, Y., & Huang, Y. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246635 · Cited by 2
“As pointed out in numerous works on probabilistic imitation learning [8], [24], [25], different demonstrations could be collected even for the same task and such variability is naturally reflected by the variance of demonstrations.”
Markerless Upper Limb Motion Tracking: A Comparative Evaluation of Multi-View Approaches
Bajrami, A., Beraldo, G., Palpacelli, M.-C., et al. (2025) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine66377.2025.11340428 · Cited by 1
“This capability allows robots to acquire complex manipulation skills and behave socially, enhancing their integration into human-centered contexts [4].”
Investigating the Impact of Robot Degree of Redundancy on Learning from Demonstration
Bilal, M., Chacon, D. A., Lipovetzky, N., Oetomo, D., & Johal, W. (2026) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3757279.3785606 · Cited by 1
“For a detailed explanation, refer to Calinon’s work [8].”
Fast Decision Making in Human–Machine Interaction Through Estimation of Human Reaching Intent
der Auwera, J. V., Aertbeliën, E., Decré, W., et al. (2026) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2026.3675918 · Cited by 1
“Therefore, according to Calinon’s Gaussian Mixture Regression [30], the mean and covariance of the mixture are calculated, obtaining h j ( obs t ) Σ end ,j + μ end ,j μ end ,j − μ mixend μ mix end .”
Generalized Task-Parameterized Movement Primitives
Huang, Y., Silvério, J., Rozo, L. D., et al. (2017) · Cited by 1
A Learning from Demonstration Approach fusing Torque Controllers.
Silvério, J., Huang, Y., Rozo, L. D., et al. (2017) · Cited by 1
Self-citationHuman Palpation Behavior Modeling with Mixture Models: Towards Autonomous Robotic Palpation
Xu, W., Guo, J., & Ren, H. (2018) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm.2018.8610764 · Cited by 1
“trajectories [17].”
Tensor-variate Mixture of Experts
Jaquier, N., Haschke, R., & Calinon, S. (2019) · Cited by 1
Self-citationA Linearly Constrained Nonparametric Framework for Imitation Learning
Huang, Y., & Caldwell, D. G. (2019) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.1909.07374 · Cited by 1
“, [20]), we can obtain η1 η2 η3 .”
BackgroundIterative assist-as-needed control with skill learning for physical human-robot interaction
Cao, R., Cheng, L., & Xue, W. (2023) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2023.10.557 · Cited by 1
Transition State Clustering for Interaction Segmentation and Learning
Hahne, F., Prasad, V., Kshirsagar, A., et al. (2024) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3610978.3640738 · Cited by 1
Yang, C., Choi, J., Anandavel, S., & Hwang, I. (2024) · IEEE International Conference on Advanced Intelligent Mechatronics (AIM) · doi:10.1109/aim55361.2024.10637051 · Cited by 1
“In other words, the GMR provides the conditional PDF of the human control input at a given time step [7].”
BackgroundMethodGoller, T., Völz, A., & Graichen, K. (2024) · IEEE Conference on Control Technology and Applications (CCTA) · doi:10.1109/ccta60707.2024.10666568 · Cited by 1
“Popular methods for this step are e.g. task-parameterized hidden semi-markov model (TP-HSMM) [13], GMMs combined with GMR [11] or probabilistic dynamical movement primitives (ProDMPs) [21].”
MethodDFL-TORO: A One-Shot Demonstration Framework for Learning Time-Optimal Robotic Manufacturing Tasks
Barekatain, A., Habibi, H., & Voos, H. (2024) · IEEE Access · doi:10.1109/access.2024.3486615 · Cited by 1
“Existing methods often rely on multiple demonstrations to regress noise-free demonstrations while maintaining accuracy [13], [14].”
BackgroundMethodBio-Signal-Guided Robot Adaptive Stiffness Learning via Human-Teleoperated Demonstrations
Xia, W., Liao, Z., Lu, Z., & Yao, L. (2025) · Biomimetics · doi:10.3390/biomimetics10060399 · Cited by 1
“…to few-shot demonstrations due to their deterministic nature; (ii) probabilistic modeling methods, including GMM/R [35], Task-Parameterized GMMs [36], Probabilistic Move-Biomimetics ment Primitives (ProMPs) [37], Kernelized Movement Primitives (KMPs) [38], and Hidden (Semi-) Markov Models…”
Generalization of task model using compliant movement primitives in a bimanual setting
Batinica, A., Nemec, B., Santos-Victor, J., et al. (2017) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2017.8324707 · Cited by 1
“We refer the reader to [21] for an extensive overview of generalization of kinematic behavior.”
BackgroundLearning of Motion Primitives Using Reference-Point-Dependent GP-HSMM for Domestic Service Robots
Iwata, K., Nakamura, T., & Nagai, T. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-01370-7_35 · Cited by 1
A Framework for Teaching Impedance Behaviours by Combining Human and Robot ‘Best Practice’
Zhao, Y., Sena, A., Wu, F., et al. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593502 · Cited by 1
“In the first step, the data covariance matrix Σ can be estimated using the Gaussian mixture model (GMM) and GMR method [19].”
MethodProbabilistic Learning of Torque Controllers from Kinematic and Force Constraints
Silvério, J., Huang, Y., Rozo, L., et al. (2017) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.1712.07249 · Cited by 1
“Two popular approaches are GMM, combined with Gaussian Mixture Regression [20], and GPR [15].”
MethodSelf-citationTowards Orientation Learning and Adaptation in Cartesian Space
Huang, Y., Abu‐Dakka, F. J., Silvério, J., et al. (2019) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.1907.03918 · Cited by 1
“It is worth mentioning that, given the joint probability distribution P(s, ξ) in (32), GMR can be employed to predict the corresponding output for a query input s∗ through calculating P(ξ|s∗) .”
BackgroundMethodResultInfluentialLong Time Sequential Task Learning From Unstructured Demonstrations
Zhang, H., Liu, Y., & Zhou, W. (2019) · IEEE Access · doi:10.1109/access.2019.2929107 · Cited by 1
“Among them, the dynamical system approaches based on the GMM and Gaussian mixture regression (GMR) [21]–[23], [39], [40] and the DMP [14] are the most frequent.”
MethodLippi, V., Maurer, C., & Mergner, T. (2021) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0010297005790585 · Cited by 1
“…where reaction forces may reasonably be more important than the trajectories themselves, models representing the stiffness of the robot (e.g. Calinon, 2016; Calinon et al., 2007) or specifications of the particular mechanical variables (torques, velocity positions, etc.) involved in the…”
BackgroundAdaptive Obstacle Avoidance Optimization Algorithm Based on Learning from Demonstration
Li, W., Cheng, H., Liang, Z., Xiao, J., & Zhang, X. (2021) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber53097.2021.9588300 · Cited by 1
Goldfarb, N., Zhou, H., Bales, C., & Fischer, G. S. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630810 · Cited by 1
“LfD has been used to reproduce handclapping [5], chess-playing, and holding objects such as sugar cubes and cups [6] based on demonstration and full-”
MethodImitation of Manipulation Skills Using Multiple Geometries
Ti, B., Gao, Y., Zhao, J., et al. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981683 · Cited by 1
“In [21], we demonstrated the advantage of considering several Cartesian coordinate systems centered on objects or landmarks of interest within a LQR control strategy expressed in task space, which required an inverse kinematics solution to be implemented as a separated process.”
BackgroundMethodSelf-citationQuantifying Teaching Behaviour in Robot Learning from DemonstrationPreprint
Sena, A., & Howard, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.04218 · Cited by 1
Variational Inference with Mixture Model Approximation: Robotic ApplicationsPreprint
Pignat, E., Lembono, T. S., & Calinon, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.09597 · Cited by 1
“Forward kinematics can also be computed in several taskspaces, associated with objects of interest [15].”
BackgroundSelf-citationGeneralized Task-Parameterized Skill LearningPreprint
Huang, Y., Silvério, J., Rozo, L., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.01696 · Cited by 1
“The projected trajectories in each frame { j } are computed by [4] ( If we consider the estimation of consistent features among the projected trajectories from a probabilistic perspective, GMM can be employed [4, 8, 9, 12], which has shown reliable modeling of joint distribution of trajectories.”
BackgroundMethodInfluentialAkbulut, M. T., Seker, M. Y., Tekden, A. E., et al. (2020) · arXiv (Cornell University) · Cited by 1
Guo, M., & Bürger, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.08993 · Cited by 1
“Compared with traditional motion planning from [11], LfD is an intuitive way to transfer human skills to robots, see [3], [4], [12].”
InfluentialAn Extended DMPs framework for Decoupled Quaternions Learning and generalizationPreprint
Liao, Z., Zhao, F., Jiang, G., & Mei, X. (2021) · Research Square · doi:10.21203/rs.3.rs-838739/v1 · Cited by 1
“On that account, TP-GMM [27] is developed to adapt the context by extracting the relevance between different tasks.”
MethodTask compatibility and feasibility maximization for whole-body control
Lober, R. (2017) · doi:10.70675/438dc1b8za70fz4402zb0abz2c7d5bbb5b12 · Cited by 1
“(a) shows the metric defined by Equations (3.67) and (3.68), and (b) shows the metric defined by (3.69). . . . . . . . . 69 5.1 In MFPS, the problem is composed of an agent (control architecture) which interacts with its environment (robot + surroundings) using actions, a(k), the environment’s state, s(k + 1), changes…”
MethodInfluentialImitation learning for a continuum trunk robot
Malekzadeh, M., Queißer, J. F., & Steil, J. J. (2017) · Publikationen an der Universität Bielefeld (Universität Bielefeld)
Robot Learning with Invariant Hidden Semi-Markov Models
Tanwani, A. K., Lee, J., Laskey, M., et al. (2018)
Action Generation Adapted to Low-Level and High-Level Robot-Object Interaction States
Maestre, C., Mukhtar, G., Gonzales, C., & Doncieux, S. (2019) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2019.00056
“Third, the method builds complex trajectories using imitation learning (Billard and Calinon, 2016), in which an external agent performs one or more kinesthetic demonstrations of an action generating a dataset of low-level states of the robot and the environment objects.”
Generating and Adapting Probabilistic Movement Primitives
Colomé, A., & Carme Torras, A. (2019) · Springer tracts in advanced robotics · doi:10.1007/978-3-030-26326-3_8
Generation of expressive motions for a tabletop robot interpolating from hand-made animations
Mier, G., Caballero, F., Nakamura, K., et al. (2019) · IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) · doi:10.1109/ro-man46459.2019.8956246
“The first method we consider is the TPGMM [22].”
MethodInfluentialLearning and Robotic Imitation of Therapist’s Behavior for Rehabilitation Therapy
Martínez, C. M. (2018) · ERA: Education and Research Archive (University of Alberta) · doi:10.7939/r3610w78t
Task-Adaptive Robot Learning from Demonstration under Replication with Gaussian Process Models.Preprint
Arduengo, M., Colomé, A., Sol, J. B., Sentis, L., & Carme Torras, A. (2020) · arXiv (Cornell University)
Generative adversarial training of product of policies for robust and adaptive movement primitivesPreprint
Pignat, E., Girgin, H., & Calinon, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.03316 · Cited by 1
“To that end, a common approach is to learn MPs in multiple parametric task spaces1 [4, 5, 6].”
BackgroundMethodInfluentialSelf-citationStructured Policy Representation: Imposing Stability in arbitrarily conditioned dynamic systemsPreprint
Urain, J., Tateo, D., Ren, T., & Peters, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.06224
Learning to Shift Attention for Motion GenerationPreprint
Zhou, Y., Gao, J., & Asfour, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.12141
“During the execution, TP-GMMs combine those GMMs and generates motions for new task queries.”
MethodInfluentialBayesian Disturbance Injection: Robust Imitation Learning of Flexible PoliciesPreprint
Oh, H., Sasaki, H., Michael, B., & Matsubara, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.13623
“In this, Gaussian Mixture Modelling (GMM) [10] is used as a basis function to capture non-linearities during learning, and has been utilized in imitation learning that deals with human demonstrations [11].”
MethodHierarchical Neural Dynamic PoliciesPreprint
Bahl, S., Gupta, A., & Pathak, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.05627
Optimization Method of Learning from Demonstration based on Incremental GMR-GP
Xia, Z., Zhai, D., Wu, H., et al. (2021) · Chinese Control Conference (CCC) · doi:10.23919/ccc52363.2021.9550375
Orientation Probabilistic Movement Primitives on Riemannian ManifoldsPreprint
Rozo, L. D., & Dave, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.15036 · Cited by 20
“Probabilistic movement primitives (ProMPs) [4], Stable Estimators of Dynamical Systems 24 (SEDS) [8], Task-Parameterized Gaussian Mixture Models (TP-GMMs) [5], Kernelized MPs 25 (KMPs) [9] and Conditional Neural MPs (CNMPs) [6] are some of the recent probabilistic models 26 to represent motion primitives (MPs).”
Background肖, 宏., 刘, 成., & 陈, 启. (2021) · Scientia Sinica Informationis · doi:10.1360/ssi-2021-0259
Yang, C., Luo, J., & Wang, N. (2023) · Elsevier eBooks · doi:10.1016/b978-0-32-395143-2.00005-x
Towards Large-Space Manipulation Skills Learning with Mobile Manipulator
Wu, Y., Liao, Z., Gong, C., et al. (2023) · Lecture notes in mechanical engineering · doi:10.1007/978-981-19-9398-5_129
Robot Orientation Learning Based on Interaction Primitives for Human-Robot Collaboration
Wu, J., Li, Y., Chen, X., et al. (2023) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar58764.2023.10249524
“[13] and Task-Parameterized GMM/GMR [14].”
Movement Primitives with Explicit Constraints for Imitation Learning of Pick-and-Place Action
Dong, Y., Yu, Z., Chen, X., Wang, C., & Huang, Q. (2023) · WRC Symposium on Advanced Robotics and Automation (WRC SARA) · doi:10.1109/wrcsara60131.2023.10261851
A Novel Dynamic Movement Primitives for Learning from Demonstrations
Zhang, Y., Cheng, L., Zhang, H., Zou, Y., & Yan, Y. (2023) · International Conference on Information Science and Technology · doi:10.1109/icist59754.2023.10366524
“Probabilistic approaches, as discussed in the studies [11]– [13], inherently possess the capacity to learn from multiple demonstrations.”
BackgroundRETRACTED: Bagging in Hidden Semi-Markov Model for handwriting robot trajectory generation
Jin, Y., Ran, T., Yuan, L., et al. (2024) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-237275
RetractedCao, R., & Cheng, L. (2024) · International Conference on Intelligent Control and Information Processing · doi:10.1109/icicip60808.2024.10477803
“Traditional programming by demonstration (PbD) provides an easy way to enable robots to learn the motion trajectory of human in tasks directly from demonstrations [4].”
BackgroundAprendizaje por demostración mediante datos sintéticos para tareas parametrizadas
Prados, A., Mora, A., Méndez, A., et al. (2024) · Jornadas de Automática · doi:10.17979/ja-cea.2024.45.10781
PRF: A Program Reuse Framework for Automated Programming by Learning from Existing Robot Programs
Toner, T., Tilbury, D. M., & Barton, K. L. (2024) · Robotics · doi:10.3390/robotics13080118
“When more diverse demonstrations are available, statistical models based on DMPs [37] or Gaussian mixture models (GMMs) [17] can be leveraged for greater generalizability to task variation, such as rearrangements of key objects.”
BackgroundMethodWinter, T. R., Klüpfel, L., Sundaram, A. M., et al. (2026) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2026.105649
“This includes classical regression approaches applied to the domain of robotic motion generation, such as Gaussian Mixture Regression (GMR) [8, 9], Gaussian Process Regression (GPR) [10], and Locally Weighted Regression (LWR) [11].”
Sampling-based constrained motion planning with products of experts
Razmjoo, A., Xue, T., Shetty, S., & Calinon, S. (2026) · The International Journal of Robotics Research · doi:10.1177/02783649251404955 · Cited by 2
“There are three main paradigms for combining experts at the solution level in the literature: Gaussian experts (Calinon 2016; Hinton 1999), energy-based models (Gkanatsios et al. 2023), and diffusion-based models (Yang et al. 2023; Wang et al. 2024).”
Self-citationChoi, J., Hunter, J. G., Hwang, I., et al. (2025) · AIAA SciTech Forum · doi:10.2514/6.2025-2250
Liu, J., Li, C., Wang, S., Dong, Z., Lam, T. L., Calinon, S., Li, M., & Chen, F. (2024) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio64047.2024.10907421
“The former involves supervised learning techniques, such as Dynamic Movement Primitives (DMP) [6], TP-GMM [7], and deep learning models [8], to obtain optimal policies by fitting data from demonstrations.”
Self-citationNonparametric Identification Modeling of Ship Manoeuvering Motion Based on Gaussian Mixture Model
Jiao, X., Ren, J., Fan, J., et al. (2024) · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · doi:10.1109/csis-iac63491.2024.10919386
“Each Gaussian distribution is called a ”component,” and the entire model is the weighted sum of these components [5].”
Schäle, D., Stoelen, M. F., & Kyrkjebø, E. (2025) · Frontiers in Robotics and AI · doi:10.3389/frobt.2025.1569476
Deep networks for few-shot manipulation learning from scratch
Chen, Y., Yao, X., & Tripp, B. (2025) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2025.105056
Generalization of Humanoid Arm Manipulation Based on Keypoints Synergetic Guidance
Shi, X., Geng, Z., Guo, W., Xu, W., Yang, Z., & Sheng, X. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3575645
“After calculating the parameters of GMM using the Expectation–maximization (EM) algorithm, for any new target location G ∗ , the conditional probability distribution of its corresponding feature space Φ( x M ) can be obtained using Gaussian mixture regression (GMR): where [21], [22].”
Loh, J. Q., Crocher, V., Oetomo, D., et al. (2025) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr66766.2025.11062990
“The µ k of each Gaussian distribution are identified by an Expectation-Maximisation algorithm which maximises the likelihood of the demonstrated trajectories to lie within the identified Gaussian distributions [13].”
Anarossi, E., Kwon, Y., Tahara, H., Tanaka, S., Shirai, K., Hamaya, M., Beltran-Hernandez, C. C., Hashimoto, A., & Matsubara, T. (2025) · IEEE Access · doi:10.1109/access.2025.3588975 · Cited by 1
“The modularity and parameterization of DMPs generate motion in a flexible manner wherein motions are encoded into easily integrated parameters that enable them to adapt to different environmental conditions [7], [8].”
RMAL-ODMPs: Orientation Skills Learning and Generalization Method for Robotic Manipulation
Wang, Z., Wang, Y., Chen, C., Peng, F., Hong, Y., Ai, Z., Tang, X., & Yan, R. (2025) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma65362.2025.11120630
“Following the extension of the task parameterized Gaussian mixture model (TP-GMM)[25] to model orientations for robotic manipulation[5], the orientation learning task can be generalized to different initial and goal orientations.”
Lee, H., Kim, J., & Yang, G. (2025) · Intelligent Service Robotics · doi:10.1007/s11370-025-00639-5
OVITA: Open-Vocabulary Interpretable Trajectory Adaptations
Maurya, A., Ghosh, T., Nguyen, A., & Prakash, R. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3606309 · Cited by 4
“By enhancing the policy with task parameterization [13], robots can generalize their learned knowledge to different variations of the same task, allowing robots to adapt to new scenarios.”
Task-Parameterized Motion Learning With Time-Sensitive Constraints
Richter, J. N., Oliveira, J., Scheurer, C., Steil, J. J., & Dehio, N. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3611083
“Mod-erntechniquesfurthermoreallowtherobotbehaviortoadaptto variationsofthetask,oftenreferredtoas Task-Parameterization [8].”
InfluentialRastegarpanah, A., Mineo, C., Contreras, C. A., et al. (2025) · Journal of Field Robotics · doi:10.1002/rob.70079
“Hence, we adopt the task ‐ parameterized Gaussian mixture model (TP ‐ GMM) Calinon (2016b), which enhances the model's flexibility in reproducing new motion trajectories that are dynamically adapted to different task parameters.”
Su, Y., Xiong, D., Lu, Y., Huang, Y., & Han, W. (2025) · Measurement and Control · doi:10.1177/00202940251374961
Elastic Fast Marching Learning from Demonstration
Prados, A., Hertel, B., Barber, R., & Azadeh, R. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500607
Zou, C., Jiang, Z., Zhang, X., Zhang, J., Song, G., Wang, Y., Zhao, Y., Peng, Z., Qiu, J., & Cheng, H. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179001
“Such as Gaussian process regression [11] and Gaussian Mixture Model/Regression (GMM-GMR) [12] methods.”
Sensorized Gripper for Human Demonstrations
Turlapati, S. H., Golani, G., Ariffin, M. Z., & Campolo, D. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-981-96-7703-0_36
Gomes, M. F. P., da Silva, C. B., Huayhua, E. A. B., Mota, F. A., Olivi, L. R., & Rohmer, E. (2025) · Brazilian Symposium on Robotics and Workshop on Robotics in Education (SBR/WRE) · doi:10.1109/sbr/wre66973.2025.11249651
“Once the GMM is trained, Gaussian Mixture Regression (GMR) is applied to generate smooth and generalized trajectories from the demonstration data [10].”
CCDP: Composition of Conditional Diffusion Policies with Guided Sampling
Razmjoo, A., Calinon, S., Gienger, M., & Zhang, F. (2025) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros60139.2025.11247405 · Cited by 4
“Early approaches, such as Probabilistic Movement Primitives (ProMP) [21] and Task-Parameterized Gaussian Mixture Models (TP-GMM) [22], laid the groundwork for this framework.”
Self-citationAdversarial Augmentation for Task-Parameterized Underwater Skill Learning via Digital Twins *
Tu, Z., Xing, Z., Wu, X., Zhang, S., & Yang, C. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247244
Li, C., Liu, J., Teng, T., et al. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246994
“Learning from Demonstration (LfD) is a widely adopted approach for modeling human behaviors in HRC. Tech-2025 niques like Task-parameterized Gaussian Mixture Models (TP-GMM) enable robots to learn and adapt complex human motions to new scenarios [10].”
Self-citationCai, H., Greene, R., Hunt, C. L., & Thakor, N. V. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246788
“In contrast, probabilistic methods (e.g., Gaussian Mixture Models [25]) represent trajectory distributions, enabling them to handle variability in human motion and generalize to new tasks similar to the initial demonstrations.”
Encoding Robot Behavior as Sensory-Based Adaptation of Learned Skillful Trajectories
Madera, J., Varveropoulos, L., & Fey, A. M. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247078
“…state space modeled as a Gaussian Mixture Model and sensory models which adapt the learned trajectory to task constraints based on current sensory information. control by leveraging optimal control formulations such as MPC (Model Predictive Control) and LQT (Linear Quadratic Tracking) [15], [16].”
Ma, T., Yin, S., Wang, Y., et al. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246772
“Gaussian Mixture Model/Regression (GMM/GMR) [27] was applied to reproduce joint angles and learning trajectory distribution through learning from the reference database.”
Intelligent disturbance rejection control for precision operations in space missions
Cheng, X., Ma, J., Liu, C., Liu, G., Chen, M., Zhang, C., & Zhao, J. (2026) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2025.108373
Time Regulation and Stage Concatenation for Optimized Probabilistic Dynamic Movement Primitives
Wu, H., Zhai, D., Xiong, Y., & Xia, Y. (2026) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2025.3647913
“Calinon [6] adopts Gaussian mixture model–Gaussian mixture regression (GMM-GMR) to fit multitrajectory data, addressing high-dimensional inputs but suffering from limited adaptability and high computational costs.”
Multidimensional Skill Training for Human Users via Shared Control
Lin, H.-Y., Byeon, S., & Hwang, I. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-2867
Human–machine interface and anticipatory interaction
Güleçyüz, B., Singh, H., Hulin, T., Wu, Y., Nockenberg, L., Kührt, C., Krug, K., Fairhurst, M. T., & Steinbach, E. G. (2026) · Elsevier eBooks · doi:10.1016/b978-0-44-330044-8.00025-7
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
