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 201–300 of 427
Learning from Demonstration Based on a Classification of Task Parameters and Trajectory Optimization
Vidaković, J., Jerbić, B., Šekoranja, B., Švaco, M., & Šuligoj, F. (2019) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-019-01101-2 · Cited by 8
Wu, H., Zhai, D., & Xia, Y. (2024) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2024.3384602 · Cited by 7
“For example, in [2], the Gaussian mixture model-Gaussian mixture regression (GMM-GMR) method is employed to fit multitra-jectory data.”
Luciani, B., Costante, S., Braghin, F., Pedrocchi, A., & Gandolla, M. (2024) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob60516.2024.10719741 · Cited by 7
“For our specific application, we have retrieved the steps presented in [14].”
MethodN-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning
Manrique-Córdoba, J., de la Casa, M. A., & Sabater-Navarro, J. M. (2025) · Sensors · doi:10.3390/s25072145 · Cited by 7
“For instance, the literature reports the use of Hidden Markov Models (HMMs) [2–4] and Gaussian Mixture Models (GMMs) [3,5,6] for modeling task demonstrations at the trajectory level.”
A Review of Compliant Movement Primitives
Deniša, M., Petrič, T., Gams, A., & Ude, A. (2016) · InTech eBooks · doi:10.5772/64058 · Cited by 7
“Other approaches of generalization, not relying on DMPs, are thoroughly discussed in [16].”
BackgroundLearning Competing Constraints and Task Priorities from Demonstrations of Bimanual Skills.
Silvério, J., Calinon, S., Rozo, L. D., et al. (2017) · Cited by 7
Self-citationKernelized Movement Primitives
Huang, Y., Rozo, L., Silvério, J., et al. (2017) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.1708.08638 · Cited by 7
“In order to address this problem, we extend KMP by using local coordinate systems and affine transformations as in Calinon (2016); Huang et al. (2018), which allows KMP to exhibit better extrapolation capabilities (Section 3.3).”
InfluentialOptimizing Sequences of Probabilistic Manipulation Skills Learned from Demonstration
Schwenkel, L., Guo, M., & Bürger, M. (2019) · Conference on Robot Learning · Cited by 7
Enayati, N., Mariani, S., Wahrburg, A., & Zanchettin, A. M. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.2687 · Cited by 8
“Acquired demonstrations are commonly aligned in time using methods such as dynamic time warping or cross-correlation analysis (Calinon 2016).”
MethodReview of the techniques used in motor‐cognitive human‐robot skill transfer
Guan, Y. H., Wang, N., & Yang, C. (2021) · Cognitive Computation and Systems · doi:10.1049/ccs2.12025 · Cited by 7
Temporal Logic Guided Motion Primitives for Complex Manipulation Tasks with User Preferences
Wang, H., He, H., Shang, W., & Kan, Z. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811707 · Cited by 7
“Other representative works that exploit DMP for motion generation include [7], [12], [15].”
BackgroundMa, R., Chen, J., & Oyekan, J. O. (2023) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2023.102539 · Cited by 7
A Non-parametric Skill Representation with Soft Null Space Projectors for Fast Generalization
Silvério, J., & Huang, Y. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161065 · Cited by 7
“Alternative approaches using mixture models and hidden Markov models [2] are also endowed with strong generalization capabilities particularly under the framework of task-parameterized movement models [3], [4].”
MethodRobotic Fabric Flattening with Wrinkle Direction Detection
Qiu, Y., Zhu, J., Santina, C. D., Gienger, M., & Kober, J. (2024) · Springer proceedings in advanced robotics · doi:10.1007/978-3-031-63596-0_30 · Cited by 7
Exploiting the task space redundancy in robot programming by demonstration
Alizadeh, T., & Karimi, N. (2018) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2018.8484455 · Cited by 7
“For more details of the TP-GMM approach refer to [16].”
MethodMotor Skills Learning and Generalization with Adapted Curvilinear Gaussian Mixture Model
Zhang, H., & Leng, Y. (2019) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-019-00999-y · Cited by 7
“Typical methods are GMM and GMR[3].”
MethodLearning to Sequence Multiple Tasks with Competing Constraints
Duan, A., Camoriano, R., Ferigo, D., Huang, Y., Calandriello, D., Rosasco, L., & Pucci, D. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968496 · Cited by 7
“The demonstrated trajectories are usually represented through the well-established movement primitives [2], [3], [4] for later reproduction and adaptation on robot platforms.”
BackgroundMethodVariational Inference with Mixture Model Approximation for Applications in Robotics
Pignat, E., Lembono, T. S., & Calinon, S. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197166 · Cited by 7
Self-citationContextual Policy Search for Task-Level Adaptation in Physical Human–Robot Interaction
Hou, Z., Ma, T., Wang, W., & Yu, H. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3529908 · Cited by 6
“Task-parameterized GMM can achieve adaptation across multiple tasks by combining the different linear transformations from multiple frames [25], [26].”
How Can Everyday Users Efficiently Teach Robots by Demonstration?
Sakr, M., Zhang, Z., Li, B., Zhang, H., der Loos, H. F. M. V., Kulić, D., & Croft, E. A. (2025) · ACM Transactions on Human-Robot Interaction · doi:10.1145/3737892 · Cited by 13
“Continuous trajectories can then be generated from the global mixture model using Gaussian Mixture Regression (GMR); Calinon [14] provides further details.”
Robotics for Occupational Therapy: Learning Upper-Limb Exercises From Demonstrations
Hu, S., Mendonca, R. J., Johnson, M. J., & Kuchenbecker, K. J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3098945 · Cited by 8
“Some approaches primarily utilize a Gaussian mixture model (GMM), which statistically encodes various types of data from demonstrations,andGaussianmixtureregression(GMR),which generalizesrobotcommands[26].”
MethodLearning Medical Suturing Primitives for Autonomous Suturing
Amirshirzad, N., Sunal, B., Bebek, Ö., & Öztop, E. (2021) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49439.2021.9551415 · Cited by 6
Learning Interactively to Resolve Ambiguity in Reference Frame Selection
Franzese, G., Celemin, C. E., & Kober, J. (2020) · Research Repository (Delft University of Technology) · Cited by 9
Ding, Z. (2020) · Springer eBooks · doi:10.1007/978-981-15-4095-0_8 · Cited by 7
Akbulut, B., Girgin, T., Mehrabi, A., Asada, M., Uğur, E., & Öztop, E. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160895 · Cited by 6
“Primitives [19], [20], [21], Probabilistic Movement Primitives [22], [23], Compliant Parametric DMPs [24], [25] or statistical models [26], CNMP has the advantage of providing a single framework that can learn distributions of comFig.”
BackgroundOkada, M., Komatsu, M., Okumura, R., et al. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342096 · Cited by 6
“Accord-ingly, various methods have been proposed, e.g., Fourier basis-based segmentation [23], clustering by GMM [24], [25], movement matching from a pre-existing skill set of Dynamic Movement Primitives [26], simultaneous segmentation and learning of Probabilistic Movement Primitives [27], and…”
MethodRobot programming by demonstration of multiple tasks within a common environment
Alizadeh, T., & Saduanov, B. (2017) · IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) · doi:10.1109/mfi.2017.8170389 · Cited by 6
“For more details refer to [7] and [8].”
Interactive Generation of Calligraphic Trajectories from Gaussian Mixtures
Berio, D., Leymarie, F. F., & Calinon, S. (2019) · Unsupervised and semi-supervised learning · doi:10.1007/978-3-030-23876-6_2 · Cited by 6
Self-citationHierarchical Task-Parameterized Learning from Demonstration for Collaborative Object Movement
Hu, S., & Kuchenbecker, K. J. (2019) · Applied Bionics and Biomechanics · doi:10.1155/2019/9765383 · Cited by 6
“First, we utilize the TP-GMM algorithm [11] as the basis for demonstration encoding and generalization because of its validated merits in many tasks.”
MethodInfluentialAccelerating Robot Trajectory Learning for Stochastic Tasks
Vidaković, J., Jerbić, B., Šekoranja, B., et al. (2020) · IEEE Access · doi:10.1109/access.2020.2986999 · Cited by 6
“Task parametrization is a commonly used way to encode generalization capabilities into a trajectory model [1], [2], [3].”
Reward Conditioned Neural Movement Primitives for Population-Based Variational Policy Optimization
Akbulut, M. T., Bozdoğan, U., Tekden, A. E., et al. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560897 · Cited by 6
“Learning frameworks that are based on dynamic systems [18], probabilistic modeling [19] and combination of them [20], [21] have been popular in recent years.”
BackgroundWang, L., Jia, S., Wang, G., et al. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06543-0 · Cited by 6
Dynamic movement primitives based on positive and negative demonstrations
Dong, S., Yang, Z., Zhang, W., & Zou, K. (2023) · International Journal of Advanced Robotic Systems · doi:10.1177/17298806231152997 · Cited by 6
“The discontinuity of DMP and the reversibility of GMRDMP can be solved by coordinate transformation or normalization.(27) However, different transformation or normalization methods may produce very different results.”
Gaussian process based model predictive controller for imitation learning
Joukov, V., & Kulić, D. (2017) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2017.8246971 · Cited by 8
“Calinon used Gaussian Mixture Models (GMM) to build task-parameterized models and showed how they can be utilized in a model predictive control framework to generate desired accelerations [2].”
MethodAutoLfD: Closing the Loop for Learning From Demonstrations
Wu, S., Wang, Y., & Huang, Y. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3532820 · Cited by 5
“TP-GMM and its variants were developed to deal with the extrapolation issue [12], [26], [42].”
InfluentialTask-aware motion planning in constrained environments using GMM-informed RRT planners
Shaarawy, A., Rastegarpanah, A., & Stolkin, R. (2025) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2025.103095 · Cited by 5
f-Divergence Optimization for Task-Parameterized Learning from Demonstrations Algorithm
Prados, A., Méndez, A., Espinoza, G., et al. (2024) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc61747.2024.10535920 · Cited by 5
“Our contributions are: • Filtering irrelevant and redundant TPs through the use of an f-Divergence technique in a Learning from Demonstration algorithm based on TPGMM [6].”
MethodMultitarget adaptive virtual fixture based on task learning for hydraulic manipulator
Cheng, M., Li, R., Ding, R., et al. (2024) · Journal of Field Robotics · doi:10.1002/rob.22386 · Cited by 5
“Dynamic GMM only needs to encode higher ‐ order derivatives to increase the dimension, which is beneficial for complex trajectory demonstration tasks (Calinon, 2016).”
Haptic Bimanual System for Teleoperation of Time-Delayed Tasks
Sena, A., Rouxel, Q., Ivanova, E., Burdet, E., & Li, Z. (2021) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio54168.2021.9739628 · Cited by 5
“Recent work has shown the value of this approach for teleoperated systems that experience varying time delays [25], [26], [27], and the flexibility of the underlying methods in adapting the learned skills to changes in the task from the original conditions [28], [29].”
BackgroundKernelized gradient descent method for learning from demonstration
Hu, K., Zhang, J., & Wu, D. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126781 · Cited by 5
Learning Compliant Box-in-Box Insertion through Haptic-Based Robotic Teleoperation
Kana, S., Gurnani, J., Ramanathan, V., et al. (2023) · Sensors · doi:10.3390/s23218721 · Cited by 5
“Conventional generalisation techniques such as TP-GMM compute the reproduction trajectories by way of products of task-parameterised Gaussians (using a quadratic error cost, i.e., Equation (3) [44] to prioritise the frame that contributed more to the product Gaussian’s mean at a certain time).”
MethodConditional Neural Expert Processes for Learning Movement Primitives From Demonstration
Yıldırım, Y., & Uğur, E. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3477169 · Cited by 5
“The complexity of training and inference in HMMs increases as the dimensionality of the demonstrations increases, whereas variants of GMMs work well with high-dimensional data [15].”
Beam-pointing drift prediction in pulsed lasers by a probabilistic learning approach
Chang, H. Y., Fan, Z., Qiu, J., et al. (2019) · Applied Optics · doi:10.1364/ao.58.000948 · Cited by 5
Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives
Silvério, J. (2019) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.5281/zenodo.3676693 · Cited by 5
A Physiotheraphy Coaching System based on Kinect Sensor
Saratean, T., Antal, M., Pop, C. D., et al. (2020) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp51029.2020.9266178 · Cited by 5
“An alternative to learning-based systems is movement parameterization [13].”
BackgroundRobust Human Action Recognition Using Dynamic Movement Features
Zhang, H., Fu, M., Luo, H., & Zhou, W. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-65289-4_45 · Cited by 5
“Another dataset is a handwritten letter dataset provided by Calinon [19].”
Bimanual Skill Learning with Pose and Joint Space Constraints
Silvério, J., Calinon, S., Rozo, L., et al. (2018) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2018.8624993 · Cited by 5
“On the basis of [8], the problem is framed as a Task-Parameterized Gaussian Mixture Model (TP-GMM) [11], reviewed in Section II, whose structure is exploited to consider Jacobian matrices and quaternion-based”
BackgroundMethodInfluentialSelf-citationFigueroa, N., & Billard, A. G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.10060 · Cited by 5
“…from Demonstration (LfD) (Argall et al., 2009; Billard et al., 2008) approaches, Gaussian Mixture Models (GMM) and Hidden Markov Models (HMM), are regularly used for motion modeling, action recognition and segmentation (Calinon et al., 2007; Khansari-Zadeh and Billard, 2011; Calinon, 2015).”
MethodReinforcement Learning based Optimization for Cobot's Path Generation in Collaborative Tasks
Zaatari, S. E., Wang, Y., & Li, W. (2021) · IEEE International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd49262.2021.9437874 · Cited by 4
“Task-Parametrized Learning from Demonstrations (TP-LfD) is an effective approach to address the above issue, since it allows a cobot to adjust its path intuitively [3-6].”
BackgroundLearning from Few Demonstrations with Frame–Weighted Motion Generation
Sun, J., Kober, J., Gienger, M., et al. (2024) · Springer proceedings in advanced robotics · doi:10.1007/978-3-031-63596-0_4 · Cited by 4
Li, C., Wu, X., Teng, T., Calinon, S., & Chen, F. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611028 · Cited by 4
“The extension of GMM, namely TP-GMM [17], trained using the expectation-maximization (EM) algorithm [18], can represent demonstration motion profiles from several different perspectives for integrating task information and has been applied in many interactive tasks like object lifting [19] and…”
BackgroundMethodSelf-citationA Bayesian tracker for synthesizing mobile robot behaviour from demonstration
Magnenat, S., & Colas, F. (2021) · Autonomous Robots · doi:10.1007/s10514-021-10019-4 · Cited by 3
“Recent development in this field include mixture models using different reference frames (Calinon 2016) or even semi-Markov models for better temporal evolutions (Havoutis and Calinon 2019).”
MethodResultInfluentialLearning Robotic Contact Juggling
Tanaka, K., Hamaya, M., Joshi, D. O., et al. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636790 · Cited by 4
“Other linear and nonlinear approximation methods, such as neural networks [23], Gaussian mixture regression (GMR) [24], Gaussian process regression [25], and support vector regression [26] can also be used to generate f .”
MethodTi, B., Gao, Y., Shi, M., Fu, L., & Zhao, J. (2021) · International Journal of Advanced Robotic Systems · doi:10.1177/17298814211065577 · Cited by 4
“(5) that as the movement going on, the phase s approaches to 0, and the influence of the coupling force term will gradually weaken to guarantee that the system is approximate to a linear spring-damping system, so it can converge to the goal point in the end.”
BackgroundNeural Field Movement Primitives for Joint Modelling of Scenes and Motions
Tekden, A. E., Deisenroth, M. P., & Bekiroglu, Y. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342170 · Cited by 4
“Movement primitives [2], [3], [4], [5], [6], [7] are often built upon LfD approaches that provide an efficient way to teach robots complex motor skills.”
BackgroundMethodIdentification of Effective Motion Primitives for Ground Vehicles
Löw, T., Bandyopadhyay, T., & Borges, P. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341708 · Cited by 4
“Motion primitives are a well-known concept in robotics and a number of frameworks have been developed [4], [5], [6], [7].”
BackgroundBerio, D., Akten, M., Leymarie, F. F., Grierson, M., & Plamondon, R. (2017) · Cited by 3
Huang, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.00452 · Cited by 4
“Please refer to [6], [14] for more details on the modeling of demonstrations.”
BackgroundMethodTerrain-Adaptive Gait Planning for Lower Limb Walking Assistance Exoskeleton Robots
Zou, C., Peng, Z., Shi, K., Mu, F., Huang, R., & Cheng, H. M. (2023) · Chinese Control Conference (CCC) · doi:10.23919/ccc58697.2023.10240748 · Cited by 3
“Thus the reference trajectoryPr(ξ|t) can be retrieved by the Gaussian Mixture Regression (GMR) that satisfies [26]”
Qian, K., Yue, Z., & Bai, J. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05902-3 · Cited by 3
Lee, Y., Lee, B., Kim, S., & Park, F. C. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3575313 · Cited by 5
“Task-Parametrized Gaussian Mixture Model (TP-GMM) can produce new movements for unseen task parameters; however, it primarily addresses parameters defined as coordinate frames, making it less suitable for more general types of inputs such as vision or language [18].”
MeshDMP: Motion Planning on Discrete Manifolds Using Dynamic Movement Primitives
Vedove, M. D., Abu‐Dakka, F. J., Palopoli, L., Fontanelli, D., & Saveriano, M. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128556 · Cited by 4
“…set of demonstrations is collected, either by visual observation or kinesthetic teaching [1], different mathematical frameworks can be used to encode such motions, such as Dynamic Movement Primitives (DMPs) [2], [3], Probabilistic MPs [4], Kernelised MPs [5], or Gaussian Mixture Models (GMMs) [6].”
Robot Programming by Demonstration with Oral Instructions for Assembly
Hu, H., Li, A., Zhang, N., et al. (2020) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar49640.2020.9303282 · Cited by 3
“In addition, since the demonstrations provided by the human operator do not share the same start and end configurations, the task-parameterized policy [12] is selected to deal with this issue.”
BackgroundA Feature Reserved Teaching Method for Pick-Place System under Robot Operating System
Du, W., Ding, C., Wu, J., & Xiong, Z. (2021) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio54168.2021.9739365 · Cited by 3
“Therefore various probabilistic methods are analysed to generate executable motion from demonstration, such as Gaussian mixture regression(GMR) [9] , dynamical movement primitives(DMP) [10], probabilistic movement primitives(ProMP) [11] to name a few.”
MethodLearning-Based Compensation-Corrective Control Strategy for Upper Limb Rehabilitation Robots
Xie, P., Lin, C., Cai, S., & Xie, L. (2022) · International Journal of Social Robotics · doi:10.1007/s12369-022-00943-5 · Cited by 3
Effective Learning and Online Modulation for Robotic Variable Impedance Skills
Zhai, X., Ou, Y., Xu, Z., et al. (2022) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio55434.2022.10011841 · Cited by 3
“Among those methods, the Dynamic Movement Primitive (DMP), Gaussian Mixture Model-Gaussian Mixture Regression (GMM-GMR) [16], [17], Kernelized Movement Primitives (KMP) [18], [19], Gaussian Process (GP) [20] , and Probabilistic Movement Primitives (ProMPs) [21], [22].”
MethodState Prediction of Human-in-the-Loop Multi-rotor System with Stochastic Human Behavior Model
Choi, J., Byeon, S., & Hwang, I. (2022) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2023.01.113 · Cited by 3
Bootstrapped Gaussian Mixture Model-Based Data-Driven Forward Stochastic Reachability Analysis
Choi, J., Park, H., & Hwang, I. (2023) · IEEE Control Systems Letters · doi:10.1109/lcsys.2023.3347188 · Cited by 3
“The weight, mean, and covariance of G can be computed by using the EM algorithm while the number of the Gaussian components M can be chosen using a proper model selection criterion, such as the Bayesian information criterion (BIC) [12].”
BackgroundMethodInfluentialUnifying Skill-Based Programming and Programming by Demonstration through Ontologies
Eiband, T., Lay, F. S., Nottensteiner, K., et al. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.01.059 · Cited by 3
Xu, X., Qian, K., Zhou, B., et al. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102702 · Cited by 3
Bargmann, D., Kraus, W., & Huber, M. F. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802802 · Cited by 3
Stein Movement Primitives for Adaptive Multi-Modal Trajectory Generation
Yin, Z., Lai, T. Y., Khan, S., et al. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801403 · Cited by 3
Learning quasi-periodic robot motions from demonstration
Li, X., Cheng, H., Chen, H., et al. (2019) · Autonomous Robots · doi:10.1007/s10514-019-09891-y · Cited by 3
Wang, L., Jia, S., Wang, G., et al. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283066 · Cited by 3
“Inspired by [14], if a connection between the GMM parameters and the task-specific feature is established, an individual primitive model could generate more extensions.”
MethodInfluentialPhase-Synchronized Learning of Periodic Compliant Movement Primitives (P-CMPs)
Petrič, T. (2020) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2020.599889 · Cited by 3
“The task-specific Gaussian Mixture Models (TP-GMM) were proposed by Khansari-Zadeh and Billard (2011) and were also used in Calinon (2016). Another possibility is also Hidden Markov Models (HMM) that were used in Lee and Ott (2011). While these approaches rely on generating trajectories based on existing database entr…”
MethodInfluentialTensor-variate mixture of experts for proportional myographic control of a robotic hand
Jaquier, N., Haschke, R., & Calinon, S. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103812 · Cited by 3
“Examples include video streams [2], movements in multiple coordinate systems [3], electroencephalography (EEG) [4, 5] or tactile myography (TMG) data [6].”
BackgroundSelf-citationLearning-Adaptive Deadband Sampling for Teleoperation-based Skill Transfer over the Tactile Internet
Güleçyüz, B., Oppici, L., Xu, X. W., Noll, A., & Steinbach, E. G. (2021) · International Symposium on Wireless Communication Systems · doi:10.1109/iswcs49558.2021.9562240 · Cited by 3
Contributions to the Design of Automatic Voice Quality Analysis Systems using Speech Technologies
Gómez-García, J. A. (2018) · doi:10.20868/upm.thesis.49565 · Cited by 3
Learning Task Priorities from DemonstrationsPreprint
Silvério, J., Calinon, S., Rozo, L., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.06791 · Cited by 3
“The approach is based on Task-Parameterized Gaussian Mixture Models (TP-GMM) [9] that we further develop here to tackle learning problems of increased complexity.”
BackgroundMethodInfluentialSelf-citationA Workload Adaptive Haptic Shared Control Scheme for Semi-Autonomous DrivingPreprint
Luo, R., Weng, Y., Wang, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.00167 · Cited by 3
“The parameters of the HMMs were learned by the Expectation Maximization algorithm using the open source implementations from [21], [22].”
MethodFu, Q., Zhao, W., Fang, S., et al. (2024) · Applied Sciences · doi:10.3390/app14188339 · Cited by 2
Learning Multimodal Latent Dynamics for Human–Robot Interaction
Prasad, V., Heitlinger, L., Koert, D., et al. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3582829 · Cited by 2
“We refer the reader to [14] and [70] for further details on HMMs in the context of robot learning.”
Coordination of Learned Decoupled Dual-Arm Tasks through Gaussian Belief Propagation
Prados, A., Espinoza, G., Moreno, L. E., & Barber, R. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246414 · Cited by 2
“At high level, we use a custom LfD algorithm based on a Task-Parameterized Gaussian Mixture Model (TP-GMM) [9], where we obtain a model that learns both the position and orientation required to perform a specific task.”
Human-Like Robot Impedance Regulation Skill Learning From Human–Human Demonstrations
Li, C., Wu, X., Chen, Y., et al. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3643445 · Cited by 2
“The task-parameterized Gaussian mixture model (TP-GMM) represents demonstration motions from several different perspectives for integrating task information, which allows the cobots to adjust trajectories to new situations [11].”
Self-citationProbabilistic Adaptive Control for Robust Behavior Imitation
Jankowski, J., Girgin, H., & Calinon, S. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3061310 · Cited by 2
“For that, demonstrated skills can be represented as a probability distribution in the state space [2], [3] and additionally in task-parameterized state spaces [4].”
BackgroundSelf-citationInteractive Human-in-the-loop Coordination of Manipulation Skills Learned from Demonstration
Guo, M., & Bürger, M. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811813 · Cited by 2
Active learning of time-optimal motion for an industrial manipulator with variable payload
Li, J., Wahrburg, A., & Enayati, N. (2023) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2023.10.1585 · Cited by 3
A Novel Approach to Coupling Terms to Avoid Obstacles in a Manipulator Movement Reproduction
Kim, B. S., & Lee, M. C. (2024) · International Journal of Control Automation and Systems · doi:10.1007/s12555-023-0419-2 · Cited by 2
Vedove, M. D., Lamon, E., Fontanelli, D., Palopoli, L., & Saveriano, M. (2024) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case59546.2024.10711399 · Cited by 2
“Examples of the most used are (task-parameterized) Gaussian Mixture Model (GMM) [1], Dynamical Movement Primitives (DMPs) [2], [3], Probabilistic Movement Prim-itives (ProMP) [4], and Kernelized Movement Primitives (KMP) [5].”
MethodLearning Multi-Reference Frame Skills from Demonstration with Task-Parameterized Gaussian Processes
Montero, M. R., Franzese, G., Kober, J., & Santina, C. D. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10803060 · Cited by 2
“To evaluate the proposed method, its performance is compared to that of the state-of-the-art TPGMM algorithm [8], [25].”
Interactive Incremental Learning of Generalizable Skills With Local Trajectory Modulation
Knauer, M., Albu‐Schäffer, A., Stulp, F., et al. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3542209 · Cited by 2
“…for different conditions of the ring-loading task: Table VI shows the individual successes and failures, as well as the success rates, for various box locations in the ring-loading task, comparing the performance of TP-GMM [2], TP-KMP [8] and our approach (TP-KMP with via-points from Experiment 1).”
InfluentialInductive learning of robot task knowledge from raw data and online expert feedback
Meli, D., & Fiorini, P. (2025) · Machine Learning · doi:10.1007/s10994-024-06636-6 · Cited by 2
“State-of-the-art approaches rely on probabilistic models to capture the variability of the environment and execution, e.g., Gaussian Mixture Models (GMMs) as in Calinon (2016); Kyrarini et al. (2019) and Hidden Markov Models (HMMs) as in Tanwani & Calinon (2016); Medina & Billard (2017).”
Adaptive Virtual Fixture Based on Learning Trajectory Distribution for Comanipulation Tasks
Luo, S., Cheng, M., & Ding, R. (2025) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2025.3540123 · Cited by 2
“Moreover, partial demonstrations can be easily used; this merit is meaningful when a complex task is difficult to be demonstrated at once [27].”
InfluentialOverbeek, A. H. G., van der Kooij, H., Dresscher, D., & Vlutters, M. (2025) · Advanced Robotics Research · doi:10.1002/adrr.202500109 · Cited by 2
Supporting Semantic Capture during Kinesthetic Teaching of Collaborative Industrial Robots
Stenmark, M., Haage, M., Topp, E. A., et al. (2017) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc.2017.40 · Cited by 2
“An overview of methods for learning from demonstrations has recently been given by Calinon [4].”
MethodLearning from Multiple Demonstrations with Different Modes of Operations
Bozdoğan, U., & Uğur, E. (2020) · International Journal of Intelligent Systems and Applications in Engineering · doi:10.18201/ijisae.2020158887 · Cited by 2
“[22] shows task-parametrized GMMs in a wide range of tasks including handling high dimensional data by clustering, performing control etc. and extends parametrization to different models, which take GMMs as a starting point.”
Phase-based Dynamic Movement Primitives for Powered Knee-Ankle Prosthesis Control
Zhang, G., An, H., Liu, Y., Huang, Y., Ma, H., & Wei, Q. (2022) · International Conference on Robotics and Automation Sciences (ICRAS) · doi:10.1109/icras55217.2022.9842244 · Cited by 2
Human-exoskeleton Cooperative Balance Strategy for a Human-powered Augmentation Lower Exoskeleton
Song, G., Huang, R., Peng, Z., et al. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981568 · Cited by 2
“Subsequently, probabilistic reference trajectories (joint torques) are retrieved through GMR, as depicted in Fig.”
MethodInfluentialIntegrated Bi-Manual Motion Generation and Control shaped for Probabilistic Movement Primitives
Vorndamme, J., Carvalho, J., Laha, R., Koert, D., Figueredo, L., Peters, J., & Haddadin, S. (2022) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids53995.2022.10000149 · Cited by 2
“[5], a few research groups have aimed at investigating the possibilities and limitations related to such challenge either in an asymmetrical manner [6], inducing – manually or learning – a dynamic coupling or force fields, [7]–[9], through jointspace compliance [10], or following task-parametrization, as in [11], [12]…”
MethodI³: Interactive Iterative Improvement for Few-Shot Action Segmentation
Gassen, M., Metzler, F., Prescher, E., Scherf, L., Prasad, V., Kaiser, F., & Koert, D. (2023) · IEEE RO-MAN · doi:10.1109/ro-man57019.2023.10309435 · Cited by 2
“An in-depth explanation of HMMs, HSMMs and their training can be found in [5, 28], which we omit due to space constraints.”
Background
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
