Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models
Open accessThe DOI matches its Crossref record; 41 of the 43 references it cites were found in a registry or an index.
Abstract
Abstract—This paper presents a method for learning discrete robot motions from a set of demonstrations. We model a motion as a nonlinear autonomous (i.e. time-invariant) Dynamical System (DS), and define sufficient conditions to ensure global asymptotic stability at the target. We propose a learning method, called Stable Estimator of Dynamical Systems (SEDS), to learn the parameters of the DS to ensure that all motions follow closely the demonstrations while ultimately reaching in and stopping at the target. Time-invariance and global asymptotic stability at the target ensures that the system can respond immediately and appropriately to perturbations encountered during the motion. The method is evaluated through a set of robot experiments and on a library of human handwriting motions.
Overview
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
“In this model the convergence of all trajectories to the target is guaranteed, but the final velocity at the target is always zero (i.e. the target is an asymptotically stable point).”
From Learning to Play Minigolf: A Dynamical System-Based Approach (2012) · cites this paper as [2]
In the citing paper
“The resulting model from SEDS is globally asymptotically stable, i.e. starting from any point in the space, all trajectories converge to the origin.”
From Learning to Play Minigolf: A Dynamical System-Based Approach (2012) · cites this paper as [2]
In the citing paper
“The optimization constraints given by Eq. (10) ensure the global asymptotic stability of the function f̂(x;θ) (see [2]).”
From Learning to Play Minigolf: A Dynamical System-Based Approach (2012) · cites this paper as [2]
In the citing paper
“Gaussian distributions are used in PoMPs [114] and SEDs [115] for better generalisation behaviour.”
From Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future Prospects (2023) · cites this paper as [115]
In the citing paper
“We use the dynamical systems approach to encode motion from several demonstrations. This enables a rapid and reactive adaptation of the arm motion in the presence of sensor uncertainty.”
From Catching Objects in Flight (2014) · cites this paper as [20]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
A new look at the statistical model identification
Akaike, H. (1974) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1974.1100705 · Cited by 51,879
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
Slotine, J.-J. E., & Li, W. (1991) · CERN Document Server (European Organization for Nuclear Research) · Cited by 18,975
Gaussian Processes for Machine Learning
Rasmussen, C. E., & Williams, C. K. I. (2005) · doi:10.7551/mitpress/3206.001.0001 · Cited by 11,705
McLachlan, G., & Peel, D. (2000) · Wiley Series in Probability and Statistics · doi:10.1002/0471721182 · Cited by 10,991
Nonlinear programming: theory and algorithms
(1993) · Computers & Operations Research · doi:10.1016/0305-0548(93)90042-h · Cited by 5,779
ANew Look at the Statistical Model Identification
AKAlKE, H. (2011) · Cited by 4,177
Nonlinear Programming: Theory and Algorithms
Bazaraa, M. S., Sherali, H. D., & Shetty, C. M. (2006) · Wiley eBooks · doi:10.1002/0471787779 · Cited by 2,369
Sparse Gaussian Processes using Pseudo-inputs
Snelson, E., & Ghahramani, Z. (2005) · Cited by 1,415
Research works printed but not linked: 1
- schaal, 2002, Scalable locally weighted statistical techniques for real time robot learning, Appl Intell Spec Issue Scalable Robot Appl Neural Netw, 17, 49
Cited by
Items 601–700 of 772
A Constrained DMP Framework for Robot Skills Learning and Generalization from Human Demonstrations
Yang, C., Lu, Z., & Wang, N. (2025) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-78501-6_6 · Cited by 2
A Safety-Critical Dynamic System Framework for High-Precision Learning From Demonstration
Huang, H., Fu, J., Jin, Z., Liu, A., Zhang, W., & Yang, C. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3592739 · Cited by 1
“Subsequent works [12], [13] utilize Lyapunov stability theory as a stability certificate to enhance DS performance.”
Responsible Gaussian Model: Matrix-Based Approximation of Gaussian Mixture Model
Obayashi, W., Aoki, T., & Tatsukawa, T. (2025) · IEEE Access · doi:10.1109/access.2025.3604006 · Cited by 1
“GMM have been applied in speaker prediction [10], texture image classification [11], robot dynamical systems [12], and anomaly detection in deep learning [13].”
A skill learning approach based on dynamic movement primitives and quadratic-neural energy functions
Liu, Y., Liu, C., He, Y., Peng, X. L., & Li, M. (2025) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2025.105183 · Cited by 1
Extended neural contractive dynamical systems: On multiple tasks and Riemannian safety regions
Beik-Mohammadi, H., Hauberg, S., Arvanitidis, G., Neumann, G. M., & Rozo, L. D. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251366326 · Cited by 3
“In these cases, asymptotic stability, which guarantees stability only with respect to a fi xed point (Khansari-Zadeh and Billard, 2011; Rana et al., 2020; Zhang et al., 2022), is insuf fi cient, demanding a more general stability concept.”
Agrawal, S., Kussaba, H. T. M., Chen, L., Binny, A. E., Jagtap, P., Haddadin, S., & Swikir, A. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247176 · Cited by 1
“The DS corresponding to (3) is given by and the stability of the origin of (5) is certified by either (i) using the Lyapunov function V ( x ) = ∥ x ∥ 2 , as in [16]; or (ii) searching for a generic quadratic Lyapunov function, i.e.”
InfluentialNeural Networks in the Loop: Learning with Stability and Robustness Guarantees
Manchester, I. R., Wang, R., & Barbara, N. H. (2026) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-022624-032459 · Cited by 11
Learning Globally Stable Neural Imitation Policies via Reshaped Energy Functions
Huang, H., Zheng, W., Duan, J., Huang, K., Guo, J., & Yang, C. (2026) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2026.3665234 · Cited by 1
“A seminal work in this area is the Stable Esti-mator of Dynamical Systems (SEDS) [8], which introduces a quadratic function (QF) as the LF, ensuring the stability of the learned system.”
Multi-neurotransmitter synergistically regulated basal ganglia reinforcement learning model
Zhang, S.-P., Jiang, W.-G., Deng, X., Gu, Y.-H., Yao, N., Liang, X.-L., & Huang, Z.-G. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.108941 · Cited by 1
A Humanoid TacTip Gripper With SSIM-CNN Recognition for Strawberry Harvesting
Guo, K., Chen, H., Feng, Y., Li, J. J., Lu, Z., & Yang, C. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3697535 · Cited by 1
“A similar model, resembling Stable Estimators of Dynamical Systems (SEDS) and Locally Active-Globally Stable Dynamical Systems (LAGS-DS), has been introduced in [34] and [35].”
Shi, B., Ou, Y., Zhao, G., & Wang, D. (2026) · ISA Transactions · doi:10.1016/j.isatra.2026.06.045 · Cited by 1
Human task reproduction with Gaussian mixture models
Nakano, T., Yu, K., & Ohnishi, K. (2015) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit.2015.7125112 · Cited by 1
“used GMM and GMR for the learning of robot motions from a set of demonstrations [11].”
MethodExperimental evaluation of motion reproduction system with selected information
Seinan, K. Y. O., Nozaki, T., Mizoguchi, T., & Ohnishi, K. (2014) · IEEE International Workshop on Advanced Motion Control (AMC) · doi:10.1109/amc.2014.6823263 · Cited by 1
Real-time imitation human upper-body movement with joint and self-collision constraints
Yihong, C., & Qijun, C. (2013) · IEEE Conference on Robotics, Automation and Mechatronics (RAM) · doi:10.1109/ram.2013.6758550 · Cited by 1
“Many researches have already touched upon this topic.”
BackgroundThe extraction of key-posture frames from the video of 3-D motion of a human
Hwang, C., & Chen, B.-L. (2013) · IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA) · doi:10.1109/civemsa.2013.6617396 · Cited by 1
“There are many researches about robot imitation [1] [2] [3] [4] [5] [6] [7].”
BackgroundContext-GMM: Incremental learning of sparse priors for Gaussian mixture regression
Ribes, A., Cerquides, J., Demiris, Y., & de Mántaras, R. L. (2012) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2012.6491172 · Cited by 2
“This technique has proven very successful in learning by demonstration tasks [2][3][4][5].”
BackgroundMethodHuman Demonstration Trajectory Refinement for Redundant Manipulators
Shen, L., Xiong, R., & Chu, J. (2013) · IFAC Proceedings Volumes · doi:10.3182/20130902-3-cn-3020.00038 · Cited by 1
The AAAI 2011 Robot Exhibition
Chernova, S., Dodds, Z., Stilman, M., Touretzky, D. S., & Thomaz, A. L. (2012) · AI Magazine · doi:10.1609/aimag.v33i1.2398 · Cited by 1
Distance-based Kernels for Dynamical Movement Primitives
Escudero-Rodrigo, D., & René, A. (2015) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-61499-578-4-133 · Cited by 1
“The experiments were done using IPython with Scikit-Learn [12] and ROS [13]; and the hand-written dataset (HWM) from the LASA2 was used [14].”
MethodTask Oriented Control of a Humanoid Robot Through the Implementation of a Cognitive Architecture
García, D. H., Monje, C. A., & Balaguer, C. (2016) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-016-0383-7 · Cited by 1
“In order to generate a new skill based on the merger of several robot skills previously learned, we first review a couple of useful mathematical properties from the SEDS [23] formulation chosen to learn the skills:”
BackgroundMethodInfluentialChen, J., & Lau, H. Y. K. (2016) · IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso.2016.7736287 · Cited by 1
“Parameter Refinement with Lyapunov Stability Theorem In this section, we first briefly describe the proof in [27] using Lyapunov Stability Theorem to derive sufficient conditions which ensure the global stability of the DS.”
MethodGarcía, D. H., Monje, C. A., & Balaguer, C. (2016) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881416678133 · Cited by 1
Automate robot reaching task with learning from demonstration
Chen, J., Ren, H., & Lau, H. Y. K. (2017) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2017.8023663 · Cited by 1
Solving Complex Tasks Hierarchically from Demonstrations
Zheng, W., Wu, B., & Lin, H. (2018) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2018.8431734 · Cited by 1
“In LfD, movement primitives are widely used for representing and learning basic movements in robotics [2][3][4].”
BackgroundEffective Robot Skill Synthesis via Divided Control
Kaya, O., & Öztop, E. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8664825 · Cited by 1
“learns the attractor patterns in statespace from demonstrations with Gaussian mixture models [13].”
BackgroundMethodReal-time kinematical optimal trajectory planning for haptic feedback manipulators
Zhang, S., & Dai, S. (2019) · SIMULATION · doi:10.1177/0037549718815755 · Cited by 1
Robot Motion Skills Acquisition Method Based on GU-ProMPs and Reinforcement Learning
Fu, J. Y., Wang, C., Du, J., Luo, F., & Yang, C. (2019) · WRC Symposium on Advanced Robotics and Automation (WRC SARA) · doi:10.1109/wrc-sara.2019.8931921 · Cited by 1
Jiang, Y., & Yang, C. (2022) · The MIT Press eBooks · doi:10.7551/mitpress/13780.003.0022 · Cited by 1
Trajectory Scaling for Reactive Motion Planning
Dahlin, A., & Karayiannidis, Y. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811657 · Cited by 1
Research on Operation Skill Transfer and Control Oriented to Complex Force Interaction Tasks
Jie, Z., Rui, W., He, Z., Yanhe, Z., & Xizhe, Z. (2022) · Journal of Mechanical Engineering · doi:10.3901/jme.2022.18.116 · Cited by 2
Learning Stable Dynamics via Iterative Quadratic Programming
Gesel, P., & Begum, M. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161237 · Cited by 1
“Autonomous methods, such as Stable Estimator of Dynamical Systems (SEDS) [3] and the Control Lyapunov Function-based Dynamic Movements (CLFDM) [4], benefit from temporal and spatial robustness, but are generally less accurate, especially when sharp movements are required.”
BackgroundMethodInfluentialA vision-based robotic system following the human upper-limb sewing action
Zhang, L., Wang, X., Wang, H., & Li, P. (2023) · Mechanical sciences · doi:10.5194/ms-14-347-2023 · Cited by 1
Self-Supervised Visual Motor Skills via Neural Radiance Fields
Gesel, P., Sojib, N., & Begum, M. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341682 · Cited by 2
“Dynamic system-based policies, such as DMP [6], SEDS [7], PSM [8], have proven goal-directed policies to be effective for common manipulation tasks.”
BackgroundOrientation Control with Variable Stiffness Dynamical Systems
Michel, Y., Saveriano, M., Abu‐Dakka, F. J., & Lee, D. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342531 · Cited by 1
“For the desired motion, we assume that it is represented as a fi rst-order DS that can be learnt with any state-of-the-art approaches, e.g., [11], [12].”
BackgroundMethodInfluentialA Flexible Imitation Learning System Based on the Lyapunov Energy Function of the Neural Networks
Zheng, W., Li, J., Guo, J., & Du, Y. (2024) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit58233.2024.10540837 · Cited by 1
“One of the typical systems is a stable estimator of dynamical systems (SEDS)[10], this system represents the dynamic system using a Gaussian Mixture Regression model and respects the Lyapunov stability constraints.”
MethodMotion optimization based on hierarchical iterative parameter learning for complicated trajectory
Guo, Y. P., Huang, T., Huang, H., Zhao, H., & Liu, W. (2024) · Robotic Intelligence and Automation · doi:10.1108/ria-11-2023-0168 · 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
“This can be easily observed at t k ∈ [ 2 , 8 ] s for u k , 1 and the entire time horizon for u k , 2 , respectively.”
BackgroundModel-Based Reinforcement Learning Inspired by Augmented PD for Robotic Control
Li, X. Y., Shang, W., & Cong, S. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10661623 · Cited by 2
Variable Impedance Control Combining Reinforcement Learning and Gaussian Process Regression
Risi, P. D., Amadio, F., Garofalo, G., Ficuciello, F., & Falco, P. (2024) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids58906.2024.10769856 · Cited by 1
“Literature presents several other works that employ RL to optimize impedance control policies, in the form of Stable Estimator of Dynamical Systems (SEDS) [16], Coordination Matrices [17], or Kernelized Movement Primitives (KMPs) [18].”
Phase-amplitude reduction-based imitation learning
Yamamori, S., & Morimoto, J. (2024) · Advanced Robotics · doi:10.1080/01691864.2024.2441242 · Cited by 1
“Additionally, the dynamics coupling approach between the real and target systems can modify systems that deviate from the desired dynamical system [15,16].”
A Dynamical Systems-Based Peg-in-Hole Assembly Method Using Temporal Logic Task Planner
Bai, H., Nie, P., Hou, T., Zou, H., Zhang, J., & Zhang, B. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-0789-1_10 · Cited by 1
Tan, Z., Zhang, Y., Yuan, J., Song, X., Zhang, J., Wen, G., Hu, X., & Yin, H. (2025) · Machines · doi:10.3390/machines13020145 · Cited by 3
Yane, K., & Nozaki, T. (2024) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon55916.2024.10905096 · Cited by 1
“The Gaussian mixture model (GMM) can also generate motion by expressing the relationship between the position and velocity of motion as a superposition of multiple Gaussian distributions [4], [5].”
Tan, Z., Zhang, J., Zhang, Y., Song, X., Yu, Y., Wen, G., & Yin, H. (2025) · Machines · doi:10.3390/machines13050369 · Cited by 1
Bio-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 4
“…categories: (i) dynamic system-based methods, such as Dynamic Movement Primitives (DMPs) [32,33] and Stable Estimator of Dynamical Systems (SEDS) [34], which encode trajectories through attractor dynamics but are limited to few-shot demonstrations due to their deterministic nature; (ii)…”
Learning orbitally stable dynamics via transverse contraction criteria for modeling periodic tasks
Zhang, H., Cheng, L., Liu, Z., & Zhang, Y. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251369026 · Cited by 1
Human-Like Interaction with Topology-Based Optimization and Node Updating
Li, Y., Wu, J., Chen, W., Guan, Y., & Zhu, H. (2025) · International Journal of Social Robotics · doi:10.1007/s12369-025-01232-7 · Cited by 1
“In [30], the authors present a method to learn discrete robot motions from demonstrations using Gaussian Mixture Model (GMM) to model nonlinear autonomous DS that guarantee global asymptotic stability at the target.”
Exploration in structured space of robot movements for autonomous augmentation of action knowledge
Forte, D., Nemec, B., & Ude, A. (2015) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2015.7251464 · Cited by 2
“Other researchers have studied how to generalize the available movement primitives to new situations [9]–[12] or represent multiple movements within a dynamical system that can represent multiple control policies [13], [14].”
BackgroundCooperative movements through hierarchical database search
Deniša, M., Nemec, B., & Ude, A. (2017) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2017.8023494 · Cited by 2
“Other representations of movement primitives that can be used with multiple demonstrations include Hidden Markov models [15], Gaussian mixture models [16], [17], Probabilistic Movement Primitives [18], etc.”
BackgroundLong 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.”
MethodConcurrent Probabilistic Motion Primitives for Obstacle Avoidance and Human-Robot Collaboration
Fu, J. Y., Wang, C., Du, J., & Luo, F. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-27529-7_59 · Cited by 1
Soltani, K., & McAree, P. R. (2016) · CRC Press eBooks · doi:10.1201/9781315166056-2 · Cited by 1
Prediction of operating dynamics in floating-zone crystal growth using Gaussian mixture model
Omae, R., Sumitani, S., Tosa, Y., & Harada, S. (2022) · Science and Technology of Advanced Materials Methods · doi:10.1080/27660400.2022.2107884 · Cited by 1
“Considering these characteristics of the trajectories for these materials processes, prediction of the dynamics using GMR is a good choice since GMR can efficiently construct nonlinear dynamics within a neighbourhood around the space covered by the demonstrations, which was successfully demonstrated in learning the no…”
MethodProbabilistic Movement Primitives Based on Weight Combination
Fu, J. Y., Wang, Y., Luo, F., & Li, X. (2022) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm54641.2022.9959162 · Cited by 1
“Their ability to complete tasks is limited, such as slow learning speed and low accuracy[1-3].”
BackgroundMethodGenerative 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
“It can also be used to train both time-dependent [1, 5] or time-independent policies [18].”
BackgroundFan, J., Ba, H., Guo, X., & Hao, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.06752 · Cited by 1
“However, the most efficient model-based algorithms have used relatively simple function approximators, such as Gaussian processes [24] [25], time-varying linear models [26] [27], and mixtures of Gaussians [28], and the model error caused by the approximation tends to cripple the performance of model-based approaches,…”
Kégl, B., Hurtado, G., & Thomas, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.11587 · Cited by 7
“…modelling (Uria et al., 2015), and speech synthesis (Wang et al., 2017), to our knowledge, neither DARMDN nor RNADE have been used in the context of MBRL. DMDN has been used in robotics by Khansari-Zadeh & Billard (2011) and it is an important brick in the world model of Ha & Schmidhuber (2018).”
MethodLearning ODEs via Diffeomorphisms for Fast and Robust IntegrationPreprint
Zhi, W., Lai, T., Ott, L., Bonilla, E. V., & Ramos, F. T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.01650 · Cited by 3
“We use three sets of data from [24]: (i) 7 demonstrations of drawing “S” shapes on a flat surface; (ii) 14 demonstrations of placing a cube on a shelf; (iii) 12 demonstrations of drawing out Table 2: The mean squared error and mean integration times (± 1 standard deviations) when using latent ODEs…”
Federated Ensemble Model-based Reinforcement Learning.Preprint
Wang, J., Hu, J. W., Mills, J., & Min, G. (2021) · arXiv (Cornell University) · Cited by 4
An 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
“In recent years, many novel LfD approaches have been developed for complicated tasks, of which DMPs [2], SEDS [3], GMM [4], ProMP [5], KMP [6] and HMM [7] are outstanding representatives.”
BackgroundKadi, H. A., & Terzić, K. (2022) · Preprints.org · doi:10.20944/preprints202212.0305.v1 · Cited by 1
Mathematical modeling of the human smooth pursuit system
Jansson, D. (2014) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 1
From speech recognition to instruction learning
Vincke, J. (2015) · OPUS Publication Server of the University of Stuttgart (University of Stuttgart) · doi:10.18419/opus-3563
Image Extraction By Human Motion Detection Using 3D Computer Stereo Vision
Abraham, A., & Gupta, A. (2014)
Robot learning from demonstration of force-based manipulation tasks
Rozo, L. D. (2013) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-95104 · Cited by 2
Extraction and realization of human actions
Nozaki, T., Tanida, K., Mizoguchi, T., Nakano, T., Saito, Y., & Ohnishi, K. (2014) · IEEE International Workshop on Advanced Motion Control (AMC) · doi:10.1109/amc.2014.6823367
Self-organization of Computation in Neural SystemsPreprint
Tetzlaff, C., Dasgupta, S., Kulvičius, T., & Wörgötter, F. (2015) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/016725
A Programming by Demonstration with Least Square Support Vector Machine for Manipulators
Zhao, J., Li, C., Jiang, Z., & Liu, H. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-22873-0_12
Telerobotics and Robot Teaching
Yokokohji, Y. (2012) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.30.602
González-Fierro, M., García, D. H., Nanayakkara, T., & Balaguer, C. (2015)
Incremental active learning of sensorimotor models in developmental robotics
Ribes, A. (2015) · TDX (Tesis Doctorals en Xarxa)
Boosting Robot Learning and Control with Domain Constraints
Yin, H., Melo, F. S., Billard, A., & Paiva, A. (2018) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 1
Self-citationPouring Sequence Prediction using Recurrent Neural NetworkPreprint
Paul, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09393
“Another paper by Billard [16,17] presented an approach to learn arbitrary non-linear autonomous motions from human demonstrations.”
BackgroundBimanual robot skills: MP encoding, dimensionality reduction and reinforcement learning
Colomé, A. (2017) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-119092
“This fitting, which can use different regression models such as Gaussian Mixture Models (GMM) [10], is then adapted to the environmental conditions in order to modify the robot’s behavior [11].”
MethodApproaches for Creation and Evaluation of Computationally Efficient Thermofluid System Models
Baillie, B. P., Ravichandar, H. C., Salehi, I., Dani, A. P., & Bollas, G. M. (2018) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2018.09.243
“Algorithms using Lyapunov analysis to ensure the stability of nonlinear dynamical systems represented by GMMs are presented in (Khansari-Zadeh and Billard, 2011, 2014; Umlauft et al., 2017).”
MethodAction 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
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
Incremental Motion Reshaping of Autonomous Dynamical Systems
Saveriano, M., & Lee, D. (2020) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-42026-0_4
Dimensionality Reduction of Movement Primitives in Parameter SpacePreprint
Tosatto, S., Stadtmueller, J., & Peters, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.02634 · Cited by 1
“In the past, there has been some effort in providing a safe representation of the policy for robotics, mainly by the means of Movement Primitives (MPs) [8], [9], [10], [11].”
Colomé, A., & Carme Torras, A. (2019) · Springer tracts in advanced robotics · doi:10.1007/978-3-030-26326-3_1
Learning Stable Nonparametric Dynamical Systems with Gaussian Process Regression
Xiao, W., Lederer, A., & Hirche, S. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.1335 · Cited by 5
Learning 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
Structured 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 · Cited by 1
“Moreover, while most of the previous works (Khansari-Zadeh and Billard [2011], Calinon [2016], Sindhwani et al.”
ResultBayesian 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
“However, this generalization depends on the heuristic, thus unsuitable for lear ing st te-dependent feedback policies [7][9].”
BackgroundLearning to control planar hitting motions in a minigolf-like task
Kronander, K., Khansari-Zadeh, M. S. M., & Billard, A. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6048048
Self-citationSkill Modeling Based on Extreme Learning Machine
Yang, C., Zeng, C., & Zhang, J. (2021) · CRC Press eBooks · doi:10.1201/9781003119173-6
Imitation Learning via Simultaneous Optimization of Policies and Auxiliary TrajectoriesPreprint
Xie, M., Li, A., Wyk, K. V., Dellaert, F., Boots, B., & Ratliff, N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03019 · Cited by 1
Learning Dynamical System for Grasping MotionPreprint
Gao, X. D., Li, M., & Xiao, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.06728
“[2] proposed the Stable Estimator of Dynamical System (SEDS) algorithm to learn a global asymptotically stable DS.”
MethodTeaching Robots to Grasp Like Humans: An Interactive Approach.Preprint
Mészáros, A., Franzese, G., & Kober, J. (2021) · arXiv (Cornell University)
Improving Hyperparameter Optimization by Planning AheadPreprint
Jomaa, H. S., Falkner, J. K., & Schmidt-Thieme, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.08028 · Cited by 1
“A common approach to model the environment is through Gaussian processes (GP) (Rasmussen & Kuss, 2003; Ko et al., 2007; Boedecker et al., 2014) or a mixture of GPs (Khansari-Zadeh & Billard, 2011) which provide uncertainty estimates for the predictions and, more importantly, for unexplored areas.”
肖, 宏., 刘, 成., & 陈, 启. (2021) · Scientia Sinica Informationis · doi:10.1360/ssi-2021-0259
Gesel, P., LaRoche, D. P., Arthanat, S., & Begum, M. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636454
“Lastly, SEDs learns time-invariant dynamics from multiple demonstration through a statistical encoding with stability constraints.”
BackgroundMethodInfluentialA New Phase Determination Algorithm for Iterative Learning of Human-Robot Collaboration
Simonič, M., Deniša, M., Ude, A., & Nemec, B. (2021) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar53236.2021.9659356
“…Humanoid and Cognitive Robotics Lab, Department of Automatics, Biocybernetics and Robotics, Jo ˇ zef Stefan Institute, Ljubl-jana, Slovenia, e-mail: { mihael.simonic, miha.denisa, ales.ude, bojan.nemec } @ijs.si non-linear dynamic system, which ensures global asymptotic stability at the target [4].”
BackgroundVakanski, A., & Janabi‐Sharifi, F. (2017) · doi:10.1002/9781119091882.ch6
A Robot Skill Learning Method with Obstacle Avoidance Ability Based on Dynamic System Approach
Liang, X., Jin, C., & Zhang, W. (2022) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm54641.2022.9959491
Vision-Based Intelligent Grasping System for Moving Object
Wang, C., Hu, C., & Wu, Y. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-6613-2_94
On Flexible Trajectory Description for Effective Rigid Body Motion Reproduction and Recognition
Yang, J., & Guo, Y. (2023) · Journal of Shanghai Jiaotong University (Science) · doi:10.1007/s12204-023-2604-0
“The previous studies are mainly divided into two categories: model-free approaches([8-9]) and dynamical system methods([10-11]).”
Task learning of teleoperation robot systems
Yang, C., Luo, J., & Wang, N. (2023) · Elsevier eBooks · doi:10.1016/b978-0-32-395143-2.00011-5
Yang, C., Luo, J., & Wang, N. (2023) · Elsevier eBooks · doi:10.1016/b978-0-32-395143-2.00005-x
Nakajima, H., & Nakanishi, J. (2023) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.41.478
Metadata
- Authors
- Khansari-Zadeh, S. M., & Billard, A.
- Affiliations
- École Polytechnique Fédérale de Lausanne (CH)
- ORCID
- Billard, Aude
- Venue
- IEEE Transactions on Robotics
- Published
- 2011-10
- Volume
- 27
- Issue
- 5
- Pages
- 943-957
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2129202194
- Cited by
- 771
- References
- 43
- Citations by year
- 2026: 41 · 2025: 71 · 2024: 73 · 2023: 74 · 2022: 47 · 2021: 67 · 2020: 65 · 2019: 69 · 2018: 52 · 2017: 43 · 2016: 31 · 2015: 42 · 2014: 41 · 2013: 28 · 2012: 22
- FWCI
- 27.98
- Type
- journal article
- Language
- en
- Open access
- green
- infoscience.epfl.ch
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Funders
- European Commission (FP7 ICT, 248311)
- FP7 Information and Communication Technologies
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Life Sciences › Neuroscience › Cognitive Neuroscience › Motor Control and Adaptation
- Keywords
- learning dynamical systems, global asymptotic stability, Gaussian mixture model, time-invariant systems, robustness to disturbances
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.