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 701–772 of 772
Probabilistic Movement Primitives Based Hierarchical Multi-Task Learning FrameworkPreprint
Yue, C., Gao, T., Tao, L., Lu, L., & Wu, Y. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4626569
Guo, Y., Peng, G., Li, J., & Yang, C. (2023) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus58632.2023.10318278
“In [8], optimal learning algorithm for DS with Gaussian Mixture Models (GMM) was proposed to model the robot motions from a set of demonstrations.”
BackgroundMethodInfluentialDynamic Kinematic Primitives Track Planning for Fabrics PalletizingPreprint
zhu, L., Zhao, L., Tan, J., Zhang, D., & Cui, C. (2023) · Research Square · doi:10.21203/rs.3.rs-3781952/v1
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
“For robots applications, most actual tasks have a need for stability, to ensure convergence of learned skills to the target state, Dynamic System (DS) is a powerful tool [2].”
BackgroundDani, A. P., & Salehi, I. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-99134-6.00001-3
Autonomous Motion Control of Underwater Manipulator Based on Dynamic System
Wang, Y., Wang, S., & Ding, S. Z. (2023) · IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE) · doi:10.1109/iceace60673.2023.10441951
“Although these approaches have been applied to a certain extent, the planning of operational trajectories in real time cannot be completed using the above algorithms, as they require planning based on accurate three-dimensional (3D) maps [11].”
BackgroundMethodInfluentialJin, Z., Liu, A., Zhang, W., & Yu, L. J. (2023) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai60863.2023.10489246
A Novel Collaborative Imitation Learning Framework for Dual-Arm Flipping Tasks
Wang, W., Zeng, C., Shi, D., & Yang, C. (2023) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai60863.2023.10489110
“[20] proposes the Stable Estimator of Dynamical System (SEDS), which pre-learns the mixing coefficients as well as the number of mixing using GMM, and then learns LPV-DS by optimizing the MSE or log-likelihood function while preserving the stability of DS. [21] extends SEDS, while maintaining…”
MethodDynamical Systems Based Compliance Control Approach Without Direct Force Information
He, Z., Guo, Y., Huang, T., & Liu, W. (2024) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit58233.2024.10541014
“˙ x d ∈ R D denotes the desired velocity of the end-effector produced by the original DS. h ( · ) can be derived from particular learning algorithms [25], [26] In this paper, we use the Stable Estimator of Dynamical Systems (SEDS) as it possesses natural advantages in the field of compliance.”
MethodD3NN: Data-Driven Dual-level Neural Network Tool for Dynamical System Modeling and Abstraction
Yang, Y., Mo, Z., & Xiang, W. (2024) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2024.07.417
Yang, Y., Mo, Z., & Xiang, W. (2024) · ASME Letters in Dynamic Systems and Control · doi:10.1115/1.4066516
Learning Underwater Intervention Skills Based on Dynamic Movement Primitives
Yang, X., Zhang, Y., Li, R., Zheng, X., & Zhang, Q. (2024) · Electronics · doi:10.3390/electronics13193860
Wang, Z., Tian, G., & Guo, S. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3476685 · Cited by 3
“Autonomous dynamical systems are used to explain the encoding of point-to-point motions in [31].”
Kim, J., & Joe, S. (2024) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais63750.2024.10814529
“Gaussian Mixture Models (GMMs) offer a convenient and compact approach to encoding a set of human demonstrations for a specific task or skill, and have been widely applied in recent years [7]–[9].”
Zhou, J., Zuo, G., Li, X., Yu, S., & Dong, S. (2025) · ISA Transactions · doi:10.1016/j.isatra.2025.02.027
Ding, G., Zang, X., Zhang, X., Li, C., Zhu, Y., & Zhao, J. (2025) · Applied Sciences · doi:10.3390/app15063171
Storm: An Experience-Based Framework for Robot Learning From Demonstration
Quiroga, N., Mitrevski, A., Plöger, P. G., & Hassan, T. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3558696
“Various approaches can also be used to model trajectories, such as GMMs [27], [28], dynamic motion primitives [29], convolutional neural networks [16], [24], or recurrent networks [9], [19], [22].”
Teaching and Reproduction for In-Hand Object Manipulation
Yashima, M., Yamawaki, T., & Kurimoto, I. (2025) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2025.p0444
Watson, J., Urain, J., Carvalho, J., Funk, N., & Peters, J. (2025) · Springer eBooks · doi:10.1007/978-3-319-74095-9_6
Movement Primitive Categorization Balancing the Learnability and Adaptability
Xu, X., You, M., Zhou, H., Qian, Z., Xue, J., Xu, W., & He, B. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3588839
“DMP uses non-linear systems to imitate movement from demonstrations that have been used successfully for various robotic tasks such as grasping [7], human-robot interaction [10], and lifting tasks [11].”
Robot Learning Using Multi-Coordinate Elastic Maps
Hertel, B., & Azadeh, R. (2025) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/ur65550.2025.11078120
“We 1 Available at: https://github.com/brenhertel/MC-Elmap first use MC-Elmap on each shape in the LASA dataset [12], a 2D handwriting dataset consisting of 25 shapes (JShape2 has been omitted), shown in Fig.”
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 · Cited by 1
“Therefore, a wide range of research on learning state-dependent dynamical systems (DS) ˙ x = f ( x ) focuses on enforcing Lyapunov stability at a desired attractor [9], [10], [11].”
InfluentialSu, 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 · Cited by 2
Finger flow: Reactive reach-while-grasp generation for robotic arms with multi-fingered hands
Meng, X., Maurenbrecher, H., Albu‐Schäffer, A., & Keppler, M. (2025) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2025.105222 · Cited by 2
Jiang, T., Nie, P., Zhang, J., Xie, E., Zou, H., & Zhang, B. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-2095-4_10
Neural-Lyapunov Fusion: Stable Dynamical System Learning for Robotic Motion Generation
Zhang, H., Zhang, Y., Zou, Y., Li, H., & Cheng, L. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246877
“Dynamic Systems (DS) theory provides a rigorous mathematical framework for modeling such trajectories while ensuring stability through formal convergence proofs [2].”
InfluentialXu, Z., Hu, M., Xiao, K., Fang, Q., Liu, C., & Chen, Q. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247451 · Cited by 2
“To address these challenges, some researchers have parameterized the robot’s structure using human models [6], defining keypoint correspondences to frame the imitation task as a keypoint tracking problem [10], [11].”
Chen, L., Zhao, X., Campanha, M. P. S., Wegener, A., Naceri, A., Swikir, A., & Haddadin, S. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247327
LAMPS: A Novel Robot Generalization Framework for Learning Adaptive Multi-Periodic Skills
Liu, Z., Luo, H., Liang, X., & Fang, Y. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246906
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
“GMR can reproduce the output desired robot behavior online through Gaussian Conditioning calculated through the learned synergistic relationship of the selected kinematic input and output data [13], [14].”
LAIF: Learning by demonstration through Active Incremental data Fusion of task observations
Papageorgiou, D., Efstathopoulos, N., Angus, Y., & Kounalakis, N. (2025) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist66504.2025.11268388
“The most common DSs utilized in LbD, in the literature, are the Dynamic Movement Primitives (DMPs) [6] and the Gaussian Mixture Models (GMMs) [7].”
SUN: Stochastic UNsupervised Learning for Data Noise and Uncertainty Reduction
Christakis, N., & Drikakis, D. (2025) · Applied Sciences · doi:10.3390/app152412954
Augmented-SVM for Gradient Observations with Application to Learning Multiple-Attractor Dynamics
Shukla, A., & Billard, A. (2014) · Springer eBooks · doi:10.1007/978-3-319-02300-7_1
“To generate an initial estimate of each individual dynamical system, we used the technique proposed in Khansari-Zadeh and Billard (2011).”
BackgroundMethodInfluentialSelf-citationDynamic System Learning with Exponential Convergence Guarantee for Periodic Robotic Skills Encoding
Jin, Z., Yang, C., & Lv, C. (2025) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm65671.2025.11293542
“In [4], DSs were learned under the guidance of quadratic energy functions.”
Cui, C., & Guo, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6026259
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
“…via-points movement primitives (VMP) incorporated ProMP with DMP to handle via-point constraints but did not form a DMP capable of representing full trajectory – – – – – HMM/HSMM [8] – – – – – GP [10] – – ProMP [11] – KMP [12] – DMP [13] – – – – SEDS [14] – – – – PDMP [15] – – distributions [17].”
Safe and Stable Neural Network Dynamical Systems for Robot Motion Planning
Binny, A. E., Anand, M., Kussaba, H. T. M., Chen, L., Agrawal, S., Abu‐Dakka, F. J., & Swikir, A. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3655207 · Cited by 5
“Since NNs are trained on bounded domains, S 2 -NNDS ensures only local asymptotic stability in a domain X , unlike prior work guaranteeing global stability [5], [8].”
InfluentialQiao, M., Qiu, Y., Li, A., Zhou, J., Deng, W., & Lan, L. Y. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae3b5b · Cited by 1
“To address this, this paper employs a GMM [40] for refined modeling of the measurement noise.”
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
GeoSACS: Geometric Shared Autonomy via Canal Surfaces
Rajapakshe, S., Dastenavar, A., Hagenow, M., Odobez, J., & Senft, E. (2026) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3757279.3785579 · Cited by 1
“This paradigm is explored extensively in surgical robotics [28, 43], where surgeons retain initiative and the robot augments execution.”
Dual-loop neural prediction-based trajectory tracking control for robotic arms
Zhuang, T., & Zhuang, Y. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3723
Vo, M.-T., Le, V. P. T., & Vo, T. V. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-21631-1_34 · Cited by 1
Dermy, O. (2018) · theses.fr (ABES) · doi:10.70675/66c4dacezf631z43bez873cz81160a1d5dda · Cited by 4
“pydmps DMP [65] Python Sarcos [109] Dynamical Systems approach to Learn Robot Motions GMM, SEDS [126] Matlab iCub [127] [128] Function Approximation, DMP, and Black-Box Optimization DMP [210] Python C++ iCub [140] [209]”
Contributions to robotic control design with formal safety and stability guarantees
Schlehuber-Caissier, P. (2018) · theses.fr (ABES) · doi:10.70675/b1567b29z3bf7z41c8z867fz59499674b0c6
Lu, Y., Zhang, Y., & Wu, H. (2026) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-026-0355-1
Free Your Hands: Human-Demonstration-Free Diffusion Policy Adaptation for Robotic Manipulation
Yuan, G., Yang, M., Zhang, J., Pang, J., & Xu, D. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3686290
“For transfer learning and domain adaptation in embodied AI, compared to cross-embodiment [18] and cross-skill transfer [19], cross-environment adaptation [4], [38] is the most widely studied setting and is particularly important for real-world applications [15], [39], [40], [41].”
Learning Complex Robotic Manipulation Tasks Using Neural Networks: A Dynamical Systems Approach
Zhang, J. S., Zhang, S., & Yang, C. (2026) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2026.3672785
“3) Compared with existing studies [7], [17], and [23], the DS learning method proposed in this research achieves higher accuracy in generating trajectories on the LASA dataset.”
InfluentialIdentification for stable second-order nonlinear systems
Jin, Z., Liu, A., Zhang, W., Yu, L., Yang, C., & Lv, C. (2026) · Systems & Control Letters · doi:10.1016/j.sysconle.2026.106427
Disturbance-Robust Dynamical System Learning With Neural ODEs and Flow-Matching Augmentation
Liu, B., Nie, P., Fu, Z., Jiang, T., Fang, Z., Yao, J., & Li, L. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3692049
“LAGS-DS [11] introduces local contraction behavior building on [7], endowing the DS with both global stability and local attractivity.”
InfluentialLearning Dynamical Systems for Robust Robotic Shaving
Hou, T., Bai, H., & Ding, Y. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11522157
“…by Khansari-Zadeh and Billard proposed the stable estimator of dynamical systems (SEDS), which incorporates stability constraints into the Gaussian Mixture Regression (GMR) framework through quadratic Lyapunov functions (QLF), thereby guaranteeing globally asymptotically stable (GAS) motions [12].”
Learning of Movement Primitives by Gaussian Processes from demonstrations
Prados, A., Moreno, L., & Barber, R. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115258
Chen, X. S., Fang, Z., Lian, H., Jiang, D., Xu, C., Zhang, C., & Yang, G. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3704592
“GR-NADS is rigorously evaluated using the LASA benchmark dataset [14], a widely recognized standard for 2D robot motion learning.”
Li, C., Chen, Y., Wu, X., & Chen, F. (2026) · International Journal of Social Robotics · doi:10.1007/s12369-026-01418-7
Long, J., Liu, D., Cai, W., Manchester, I. R., & Zhi, W. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3713706 · Cited by 7
“Constraining the workspace: To first evaluate CASF’s ability toenforcegeometricconstraintsdirectly, weassessitsglobaland local constraint awareness in the Push-T [36] and LASA [37] environments, respectively, and further validate it in a 3D Robomimic [38] setting.”
Learning a Unified Dynamic System Model Across Diverse Robotic Demonstration Tasks
Jin, Z., Si, W., Xu, R., Yang, C., & Lv, C. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3718280
“One of the fundamental approaches, named SEDS [39], learned the f θ ( x ) via GMM / GMR approach, and equivalently transformed the constraint (2) into θ -related constraints.”
Adaptive Obstacle Avoidance in Trajectory Planning of Collaborative Robots for Dynamic Manufacturing
Li, W., Hu, Y., Wang, Y., Hu, K., & Pham, D. T. (2026) · Springer series in advanced manufacturing · doi:10.1007/978-3-032-20817-0_12
Becerra, Y., & Acosta, J. Á. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7345291
Physically consistent semi-parametric identification of robot friction with velocity–load coupling
Wei, X., Xu, S., 孟祥昶, Li, T., & Liu, J. (2026) · Control Engineering Practice · doi:10.1016/j.conengprac.2026.107236
Robot Skill Transfer From Planar to Developable Surfaces via Dynamic Movement Primitives
Shen, S., & Fu, J. Y. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3729913
“…example, dynamic system-based motion primitives, such as dynamic movement primitives (DMPs) [12] and stable estimator of dynamical systems (SEDS) [13], represent motion trajectories as stable dynamical systems that encode the underlying control policy, and are widely adopted in robot learning…”
Chen, H., Zang, X., Chen, B., & Zhao, J. (2026) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-03-2026-0136
Learning Spatially Ambiguous Trajectories From Demonstrations via Phase-Modulated Dynamical Systems
Jung, H., Kim, J., & Kim, K. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3732892
Miao, J., Yuan, H., & Cao, X. (2026) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap71856.2026.00046
“Evaluation uses matrices from 8 × 8 to 64 × 64 derived from the LASA dataset [1].”
Atoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering
Bâldea, M., Broadbelt, L. J., Ierapetritou, M., Jain, A., Kumar, A., Kwan, T. A., Llovell, F., Medford, A. J., Mitrai, I., Paulson, J. A., et al. (2026) · Industrial & Engineering Chemistry Research · doi:10.1021/acs.iecr.6c01806 · Cited by 1
Park, J., Kim, J., Dong, J., & Park, C.-E. (2026) · Asian Control Conference (ASCC) · doi:10.1109/ascc70886.2026.11701815
“In contrast, autonomous dynamical system based motion policies address this limitation by representing motion as a state dependent velocity field that naturally supports convergence to a target state [6], [7].”
SafeDMPs: Integrating Formal Safety with DMPs for Adaptive HRI
Tiwari, P., Nath, S., & Prakash, R. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11696514
“However, these methods typically require extensive training over multiple demonstrations.”
Kim, T., & Oh, S. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11696532
“…Mixture Regression (GMM/GMR), which partition the input space into interpretable local regions and provide closed-form predictions suitable for real-time control; the probabilistic formulation further captures uncertainty and multimodality for robust estimation–control integration [17], [18].”
Bouarada, O., Azam, M., Amayri, M., & Bouguila, N. (2026) · Soft Computing · doi:10.1007/s00500-026-11499-1
Zhang, J., Li, Y., Wu, B., & Hui, N. (2026) · Modelling—International Open Access Journal of Modelling in Engineering Science · doi:10.3390/modelling7050228
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.