Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning
Open accessAbstract
Motivated by the recursive Newton-Euler formulation, we propose a novel cascaded Gaussian process learning framework for the inverse dynamics of robot manipulators. This approach leads to a significant dimensionality reduction which in turn results in better learning and data efficiency. We explore two formulations for the cascading: the inward and outward, both along the manipulator chain topology. The learned modeling is tested in conjunction with the classical inverse dynamics model (semi-parametric) and on its own (non-parametric) in the context of feed-forward control of the arm. Experimental results are obtained with Jaco 2 six-DOF and SARCOS seven-DOF manipulators for randomly defined sinusoidal motions of the joints in order to evaluate the performance of cascading against the standard GP learning. In addition, experiments are conducted using Jaco 2 on a task emulating a pouring maneuver. Results indicate a consistent improvement in learning speed with the inward cascaded GP model and an overall improvement in data efficiency and generalization.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
A teleoperation frequency of 50Hz is sufficient for non-bilateral teleoperation.
“A teleoperation frequency of 50Hz is common among other non-bilateral systems [7, 50, 39] and in practice demonstrates sufficient performance.”
From Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware (2023) · cites this paper as [50]
The Setup section (page unavailable) says the robot’s torque controller runs at 40 Hz, but does not describe a teleoperation system. The Training section mentions a dataset collected at 50 Hz, not a teleoperation frequency. Searches for non-bilateral teleoperation and sufficient performance at 50 Hz found no passage addressing the claim. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Gaussian Processes for Machine Learning
Rasmussen, C. E., & Williams, C. K. I. (2005) · doi:10.7551/mitpress/3206.001.0001 · Cited by 11,705 · see citing works
ROS: an open-source Robot Operating System
Quigley, M. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · Cited by 8,729 · see citing works
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471 · see citing works
Gaussian Processes in Machine Learning
Rasmussen, C. E. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-28650-9_4 · Cited by 5,734 · see citing works
Design and use paradigms for gazebo, an open-source multi-robot simulator
Koenig, N., & Howard, A. (2005) · 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566) · doi:10.1109/iros.2004.1389727 · Cited by 3,638 · see citing works
Sparse Gaussian Processes using Pseudo-inputs
Snelson, E., & Ghahramani, Z. (2005) · Cited by 1,415 · see citing works
Gaussian Processes for Data-Efficient Learning in Robotics and Control
Deisenroth, M. P., Fox, D., & Rasmussen, C. E. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.218 · Cited by 659 · see citing works
Model learning for robot control: A survey
Nguyen-Tuong, D., & Peters, J. (2011) · Cognitive Processing · doi:10.1007/s10339-011-0404-1 · Cited by 503 · see citing works
An overview of dynamic parameter identification of robots
Wu, J., Wang, J., & You, Z. (2010) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2010.03.013 · Cited by 414 · see citing works
Sparse Spectrum Gaussian Process Regression
Lázaro-Gredilla, M., Quiñonero-Candela, J., Rasmussen, C. E., & Figueiras-Vidal, A. R. (2010) · doi:10.5555/1756006.1859914 · Cited by 353 · see citing works
Model Learning with Local Gaussian Process Regression
Nguyen-Tuong, D., Seeger, M., & Peters, J. (2009) · Advanced Robotics · doi:10.1163/016918609x12529286896877 · Cited by 316 · see citing works
Using model knowledge for learning inverse dynamics
Nguyen-Tuong, D., & Peters, J. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509858 · Cited by 172 · see citing works
Experimental Evaluation of Nonlinear Feedback and Feedforward Control Schemes for Manipulators
Khosla, P. K., & Takeo Kanade, A. (1988) · The International Journal of Robotics Research · doi:10.1177/027836498800700102 · Cited by 171 · see citing works
Statistical Learning for Humanoid Robots
Vijayakumar, S., D’Souza, A., Shibata, T., Conradt, J., & Schaal, S. (2002) · Autonomous Robots · doi:10.1023/a:1013258808932 · Cited by 89 · see citing works
Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control †
Reinhart, F., Shareef, Z., & Steil, J. J. (2017) · Sensors · doi:10.3390/s17020311 · Cited by 81 · see citing works
Online semi-parametric learning for inverse dynamics modeling
Romeres, D., Zorzi, M., Camoriano, R., & Chiuso, A. (2016) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2016.7798708 · Cited by 40 · see citing works
Stability of Controllers for Gaussian Process Dynamics
Vinogradska, J., Bischoff, B., Nguyen-Tuong, D., & Peters, J. (2017) · Max Planck Digital Library · Cited by 40 · see citing works
Semi-parametric Gaussian process for robot system identification
Wu, T., & Movellan, J. R. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385977 · Cited by 35 · see citing works
Derivative-Free Online Learning of Inverse Dynamics Models
Romeres, D., Zorzi, M., Camoriano, R., Traversaro, S., & Chiuso, A. (2019) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2019.2891222 · Cited by 33 · see citing works
Featherstone, R., & Orin, D. E. (2016) · Springer handbooks · doi:10.1007/978-3-319-32552-1_3 · Cited by 27 · see citing works
Chung, W. K., Fu, L., & Kröger, T. (2016) · Springer handbooks · doi:10.1007/978-3-319-32552-1_8 · Cited by 26 · see citing works
Independent Joint Learning: A novel task-to-task transfer learning scheme for robot models
Um, T. T., Park, M. S., & Park, J.-M. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907694 · Cited by 20 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- R. Featherstone and D. E. Orin, "Dynamics," in Springer Handbook of Robotics. Springer, 2016, pp. 37-66.
- A. Dalla Libera, E. Tosello, R. Carli, G. Pillonetto, and S. Ghidoni, "A semi-parametric robot inverse dynamics estimator with friction compensation for human-robot interaction," in Intelligent Robots and Systems (IROS), 2018 IEEE/RSJ International Conference on. IEEE, 2018.
Cited by
Sorted by citations
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
Zhao, T., Kumar, V., Levine, S., & Finn, C. (2023) · Robotics: Science and Systems XIX · doi:10.15607/rss.2023.xix.016 · Cited by 674 · see citing works
Giacomuzzo, G., Carli, R., Romeres, D., & Libera, A. D. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3474851 · Cited by 35 · see citing works
Adaptive Robotic Information Gathering via non-stationary Gaussian processes
Chen, W., Khardon, R., & Liu, L. (2023) · The International Journal of Robotics Research · doi:10.1177/02783649231184498 · Cited by 23 · see citing works
Fast Approximate Multioutput Gaussian Processes
Joukov, V., & Kulić, D. (2022) · IEEE Intelligent Systems · doi:10.1109/mis.2022.3169036 · Cited by 16 · see citing works
Tao, Y., Chen, S., Liu, H., Wan, J., Wei, H., & Wang, T. (2024) · Robotica · doi:10.1017/s0263574724001905 · Cited by 13 · see citing works
A convolution neural network based semi-parametric dynamic model for industrial robot
Zhuang, C., Yao, Y., Shen, Y., & Xiong, Z. (2021) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/09544062211039875 · Cited by 11 · see citing works
Data-Efficient Gaussian Process Online Learning for Adaptive Control of Multi-DoF Robotic Arms
Deng, L., Li, W., & Pan, Y. (2022) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2022.04.174 · Cited by 10 · see citing works
Forward Dynamics Estimation from Data-Driven Inverse Dynamics Learning??
Libera, A. D., Giacomuzzo, G., Carli, R., Nikovski, D. N., & Romeres, D. (2023) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2023.10.1620 · Cited by 7 · see citing works
Control of Mechanical Systems via Feedback Linearization Based on Black-Box Gaussian Process Models
Libera, A. D., Amadio, F., Nikovski, D. N., Carli, R., & Romeres, D. (2021) · European Control Conference (ECC) · doi:10.23919/ecc54610.2021.9654429 · Cited by 7 · see citing works
Giacomuzzo, G., Turcato, N., Libera, A. D., & Carli, R. (2023) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2023.10.1858 · Cited by 5 · see citing works
Learning Robot Inverse Dynamics Using Sparse Online Gaussian Process with Forgetting Mechanism
Li, W., Li, Z., Liu, Y., & Pan, Y. (2022) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim52237.2022.9863336 · Cited by 4 · see citing works
General Robot Dynamics Learning and Gen2RealPreprint
Xing, D., Li, J., Yang, Y., & Xu, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.02402 · Cited by 4 · see citing works
Dong, H. F., Li, Y., Wu, X., Jin, Z., Li, G., & Chen, J. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3578980 · Cited by 3 · see citing works
Learning Causal Structure Distributions for Robust Planning
Murillo-González, A., Xu, J., & Liu, L. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3598663 · Cited by 2 · see citing works
Linear Gaussian Processes for Data-Efficient Robot Dynamics Learning
Du, D., Liu, C., Ni, C., Qi, N., & Liu, Y. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-8155-7_350 · Cited by 1 · see citing works
Research on Dynamic Model of Flexible-Jointed Space Manipulator Based on Gaussian Process
Liu, C., Gong, T., Pan, F., Gong, S., & Hua, G. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055959
Giacomuzzo, G., Romeres, D., Carli, R., & Libera, A. D. (2025) · European Control Conference (ECC) · doi:10.23919/ecc65951.2025.11187126
Fu, Z., Niu, J., Liu, M., Liu, G. L., & Gao, X. (2026) · Nonlinear Dynamics · doi:10.1007/s11071-026-12571-z
Elocla, N. M., Chehadeh, M. S., Elrefaei, H., & Zweiri, Y. (2026) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-026-02437-2
- Authors
- Rezaei-Shoshtari, S., Meger, D., & Sharf, I.
- Affiliations
- McGill University (CA)
- ORCID
- Sharf, Inna
- Venue
- 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- Publisher
- IEEE
- Published
- 2019-11
- Pages
- 6871-6877
- ISSN
- 2153-0858 (ISSN-L)
- OpenAlex
- W2978369754
- Cited by
- 19
- References
- 22
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 2 · 2023: 4 · 2022: 4 · 2021: 4
- FWCI
- 0.77
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Natural Sciences and Engineering Research Council of Canada
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference
- Physical Sciences › Engineering › Control and Systems Engineering › Robotic Mechanisms and Dynamics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Keywords
- robot manipulators, data-efficient learning, dimensionality reduction, feedforward control, nonparametric models, generalization, pouring task
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
