Generalized Task-Parameterized Skill Learning
Open accessAbstract
Programming by demonstration has recently gained much attention due to its user-friendly and natural way to transfer human skills to robots. In order to facilitate the learning of multiple demonstrations and meanwhile generalize to new situations, a task-parameterized Gaussian mixture model (TP-GMM) has been recently developed. This model has achieved reliable performance in areas such as human-robot collaboration and dual-arm manipulation. However, the crucial task frames and associated parameters in this learning framework are often set by the human teacher, which renders three problems that have not been addressed yet: (i) task frames are treated equally, without considering their individual importance, (ii) task parameters are defined without taking into account additional task constraints, such as robot joint limits and motion smoothness, and (iii) a fixed number of task frames are pre-defined regardless of whether some of them may be redundant or even irrelevant for the task at hand. In this paper, we generalize the task-parameterized learning by addressing the aforementioned problems. Moreover, we provide a novel learning perspective which allows the robot to refine and adapt previously learned skills in a low dimensional space. Several examples are studied in both simulated and real robotic systems, showing the applicability of our approach.
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?
People often struggle to provide adequate demonstration sets.
“Given that people often struggle to provide adequate demonstration sets [1], [3]”
From Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation (2019) · cites this paper as [1]
The Introduction (p. 2) says human demonstrations might not be optimal for the robot because demonstrators may focus on completing the task rather than exploiting the robot’s capabilities. That supports a concern about demonstration quality, but it does not establish that people often struggle to provide adequate demonstration sets. (LLM, conf=0.78)
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
A survey of robot learning from demonstration
Argall, B. D., Chernova, S., Veloso, M., & Browning, B. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.10.024 · Cited by 3,227 · see citing works
Active Learning with Statistical Models
Cohn, D. A., Zoubin Ghahramani, A., & Jordan, M. I. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.295 · Cited by 2,054 · see citing works
Atkeson, C. G., Moore, A., & Schaal, S. (1997) · Artificial Intelligence Review · doi:10.1023/a:1006559212014 · Cited by 1,684 · see citing works
Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors
Ijspeert, A. J., Nakanishi, J., Hoffmann, H., Pástor, P., & Schaal, S. (2012) · Neural Computation · doi:10.1162/neco_a_00393 · Cited by 1,586 · see citing works
(2013) · Lincoln Repository (University of Lincoln) · Cited by 503 · see citing works
A tutorial on task-parameterized movement learning and retrieval
Calinon, S. (2016) · Intelligent Service Robotics · doi:10.1007/s11370-015-0187-9 · Cited by 422 · cited 1× · see citing works
“Note that intuitive insights on this variant have been studied for two frames [11] and multiple frames [12], while here we aim to provide a mathematical proof.”
BackgroundLearning variable impedance control
Buchli, J., Stulp, F., Theodorou, E. A., & Stefan Schaal, A. (2011) · The International Journal of Robotics Research · doi:10.1177/0278364911402527 · Cited by 353 · see citing works
Learning Physical Collaborative Robot Behaviors From Human Demonstrations
Rozo, L., Calinon, S., Caldwell, D. G., et al. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2540623 · Cited by 316 · see citing works
Self-citationA Generalized Path Integral Control Approach to Reinforcement Learning
TheodorouEvangelos, BuchliJonas, & SchaalStefan (2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953033 · Cited by 282 · see citing works
Kernelized movement primitives
Huang, Y., Rozo, L. D., Silvério, J., & Caldwell, D. G. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364919846363 · Cited by 263 · see citing works
Self-citationCOMpliant huMANoid COMAN: Optimal joint stiffness tuning for modal frequency control
Tsagarakis, N. G., Morfey, S., Cerda, G. M., et al. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630645 · Cited by 230 · see citing works
A task-parameterized probabilistic model with minimal intervention control
Calinon, S., Bruno, D., & Caldwell, D. G. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907339 · Cited by 149 · see citing works
Self-citationReinforcement learning for imitating constrained reaching movements
Guenter, F., Hersch, M., Calinon, S., & Billard, A. (2007) · Advanced Robotics · doi:10.1163/156855307782148550 · Cited by 144 · see citing works
Robot Skill Learning: From Reinforcement Learning to Evolution Strategies
Stulp, F., & Sigaud, O. (2013) · Paladyn Journal of Behavioral Robotics · doi:10.2478/pjbr-2013-0003 · Cited by 133 · see citing works
Task-level imitation learning using variance-based movement optimization
Mühlig, M., Gienger, M., Hellbach, S., Steil, J. J., & Goerick, C. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152439 · Cited by 84 · see citing works
Learning bimanual end-effector poses from demonstrations using task-parameterized dynamical systems
Silvério, J., Rozo, L. D., Calinon, S., & Caldwell, D. G. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353413 · Cited by 63 · see citing works
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 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 3
- [3][3] C. E. Rasmussen, C. K. I. Williams, Gaussian Processes for Machine Learning. The MIT Press, 2006. -
- [9][9] M. Muhlig, M. Gienger, S. Hellbach, J. J. Steil and C. Goerick, 'Tasklevel imitation learning using variance-based movement optimization,' in Proc . IEEE International Conference on Robotics and Automation , 2009, pp. 1177-1184. -
- [12][12] T. Alizadeh, Statistical learning of task modulated human movements through demonstration , University of Genova, PhD thesis, 2014. -
Cited by
Sorted by citations
Sena, A., Michael, B., & Howard, M. (2019) · 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967688 · Cited by 26 · see citing works
“Modification of the regression procedure is considered in [7], where the authors propose confidence-weighted task parameterised movement learning, but not in the context of improving extrapolation.”
Method
- Authors
- Huang, Y., Silvério, J., Rozo, L., & Caldwell, D. G.
- Affiliations
- Italian Institute of Technology (IT)
- Venue
- 2018 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2018-05
- Pages
- 5667-5674
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2796176989
- Cited by
- 49
- References
- 17
- Citations by year
- 2026: 5 · 2025: 8 · 2024: 7 · 2023: 8 · 2022: 5 · 2021: 7 · 2020: 3 · 2019: 6
- FWCI
- 6.01
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Biomedical Engineering › Prosthetics and Rehabilitation Robotics
- Keywords
- programming by demonstration, task parameters, robot skill learning, skill refinement, skill adaptation, movement smoothness, human-robot collaboration, dual-arm manipulation
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
