Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment, including halting motions while performing computations. Another advantage when robots are involved, is that the amount of time a robot is occupied learning a task-rather than being productive-can be reduced by transferring the learned task to the real robot. Transfer learning requires some amount of fine-tuning on the real robot. For tasks which involve complex (non-linear) dynamics, the fine-tuning itself may take a substantial amount of time. In order to reduce the amount of fine-tuning we propose to learn robustified controllers in simulation. Robustified controllers are learned by exploiting the ability to change simulation parameters (both appearance and dynamics) for successive training episodes. An additional benefit for this approach is that it alleviates the precise determination of physics parameters for the simulator, which is a non-trivial task. We demonstrate our proposed approach on a real setup in which a robot aims to solve a maze game, which involves complex dynamics due to static friction and potentially large accelerations. We show that the amount of fine-tuning in transfer learning for a robustified controller is substantially reduced compared to a non-robustified controller.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“Adding additional goals (sub-goals), basically a form of curriculum learning [24], can improve the learning as well [25].”
BackgroundLi, Z., & Hoiem, D. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2773081 · Cited by 4,202
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
Peng, X. B., Andrychowicz, M., Zaremba, W., & Abbeel, P. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8460528 · Cited by 1,309 · cited 2×
“Since we are considering tasks involving (much) more complex dynamics, we instead follow a similar approach as [19], and perform randomization of appearance, physics and system parameters with model-free RL.”
MethodLi, Z., & Hoiem, D. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_37 · Cited by 659
CAD2RL: Real Single-Image Flight Without a Single Real Image
Sadeghi, F., & Levine, S. (2017) · Robotics: Science and Systems XIII · doi:10.15607/rss.2017.xiii.034 · Cited by 618
CNN Features off-the-shelf: an Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · arXiv · doi:10.48550/arxiv.1403.6382 · Cited by 607
Sim-to-Real Robot Learning from Pixels with Progressive Nets
Rusu, A. A., Vecerik, M., Rothörl, T., Heess, N., Pascanu, R., & Hadsell, R. (2016) · arXiv · doi:10.48550/arxiv.1610.04286 · Cited by 385 · cited 1×
“TL from simulated to real has also been applied to learn robot tasks [7]–[11].”
MethodOne-Shot Visual Imitation Learning via Meta-Learning
Finn, C., Yu, T., Zhang, T., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1709.04905 · Cited by 341 · cited 1×
“Along those lines, teaching a robot to perform tasks by human demonstration, or imitation learning, could teach robots complicated tasks without the need for elaborate reward functions, e.g., [38].”
BackgroundLearning Dexterous In-Hand Manipulation
OpenAI, Andrychowicz, M., Baker, B., Chociej, M., Jozefowicz, R., McGrew, B., Pachocki, J., Petron, A., Plappert, M., Powell, G., et al. (2018) · arXiv · doi:10.48550/arxiv.1808.00177 · Cited by 248
Cited by
Salvato, E., Fenu, G., Medvet, E., & Pellegrino, F. A. (2021) · IEEE Access · doi:10.1109/access.2021.3126658 · Cited by 200
“[56] shows the benefits of using DR and Asynchronous Actor Critic Agent (A3C) algorithm [86] (on-policy) for learning the controller, with respect to not using DR.”
MethodSim2real transfer for reinforcement learning without dynamics randomization
Kaspar, M., Munoz Osorio, J. D., & Bock, J. (2020) · 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341260 · Cited by 87
Measuring Progress in Deep Reinforcement Learning Sample Efficiency
Dorner, F. E. (2021) · arXiv · doi:10.48550/arxiv.2102.04881 · Cited by 6
Metadata
- Authors
- Baar, J. V., Sullivan, A., Cordorel, R., Jha, D., Romeres, D., & Nikovski, D.
- Venue
- 2019 International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2019-05
- Pages
- 6001-6007
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2890728188
- Cited by
- 45
- References
- 11
- FWCI
- 3.21
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics. https://app.cochat.ai/papers/10.1109/icra.2019.8793561
- The paper
- Baar, J. V., Sullivan, A., Cordorel, R., Jha, D., Romeres, D., & Nikovski, D. (2019). Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics. 2019 International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra.2019.8793561
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.