Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
Deep reinforcement learning provides a promising approach for vision-based control of real-world robots. However, the generalization of such models depends critically on the quantity and variety of data available for training. This data can be difficult to obtain for some types of robotic systems, such as fragile, small-scale quadrotors. Simulated rendering and physics can provide for much larger datasets, but such data is inherently of lower quality: many of the phenomena that make the real-world autonomous flight problem challenging, such as complex physics and air currents, are modeled poorly or not at all, and the systematic differences between simulation and the real world are typically impossible to eliminate. In this work, we investigate how data from both simulation and the real world can be combined in a hybrid deep reinforcement learning algorithm. Our method uses real-world data to learn about the dynamics of the system, and simulated data to learn a generalizable perception system that can enable the robot to avoid collisions using only a monocular camera. We demonstrate our approach on a real-world nano aerial vehicle collision avoidance task, showing that with only an hour of real-world data, the quadrotor can avoid collisions in new environments with various lighting conditions and geometry. Code, instructions for building the aerial vehicles, and videos of the experiments can be found at github.com/gkahn13/GtS.
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
Watkins, C. J. C. H., & Dayan, P. (1992) · Machine Learning · doi:10.1007/bf00992698 · Cited by 9,083
Domain-Adversarial Training of Neural Networks
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-58347-1_10 · Cited by 8,318
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“With the recent advent of large datasets, prior work has shown that deep neural networks trained on these large datasets can enable easy transfer to new tasks via fine-tuning [28], [29], [30], [31].”
BackgroundDeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 1×
“With the recent advent of large datasets, prior work has shown that deep neural networks trained on these large datasets can enable easy transfer to new tasks via fine-tuning [28], [29], [30], [31].”
BackgroundReinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160 · cited 1×
“Although different, this action-conditioned reward prediction approach inherits the favorable sample-efficiency property of model-based algorithms [42] because the learning procedure (Eqn.”
BackgroundSim-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 1×
“Other approaches have sought to improve transfer by minimizing the gap between simulation and reality, either by bringing the simulator closer to reality [16], [17], making reality closer to the simulator [18], [8], or randomizing visual [7], [19] or physical [20], [21], [22], [23] properties of the simulator.”
BackgroundSelf-citationGibson Env: Real-World Perception for Embodied Agents
Xia, F., Zamir, A. R., He, Z., Sax, A., Malik, J., & Savarese, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00945 · Cited by 763
Deep Reinforcement Learning: An Overview
Li, Y. (2017) · arXiv · doi:10.48550/arxiv.1701.07274 · Cited by 762 · cited 1×
“Deep reinforcement learning algorithms offer the enticing possibility of jointly automating both the perception and control systems of robots with only a minimal amount of manual engineering and a high degree of generality [1].”
BackgroundA Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots
Giusti, A., Guzzi, J., Ciresan, D. C., He, F.-L., Rodriguez, J. P., Fontana, F., Faessler, M., Forster, C., Schmidhuber, J., Caro, G. D., et al. (2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2015.2509024 · Cited by 665
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
Self-citation
Cited by
Salvato, E., Fenu, G., Medvet, E., & Pellegrino, F. A. (2021) · IEEE Access · doi:10.1109/access.2021.3126658 · Cited by 200
“Navigation [39], [40], [41], [42] Manipulation [43], [44], [45], [46], [47], [3], [8], [48] Motion control [49], [50], [51], [52], [53], [54], [55], [56], [57], [58], [59] Locomotion [49], [50], [51], [60], [61], [62] When tackling a robot control problem with RL, according to the formulation and…”
BackgroundMethodInfluentialInteractive Gibson Benchmark: A Benchmark for Interactive Navigation in Cluttered Environments
Xia, F., Shen, W. B., Li, C., Kasimbeg, P., Tchapmi, M. E., Toshev, A., Martin-Martin, R., & Savarese, S. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2965078 · Cited by 171
“This enabled seamless sim2real transfer [13], [41].”
Motion Planning for Mobile Robots—Focusing on Deep Reinforcement Learning: A Systematic Review
Sun, H., Zhang, W., Yu, R., & Zhang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3076530 · Cited by 143
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
Ghosh, D., Rahme, J., Kumar, A., Zhang, A., Adams, R. P., & Levine, S. (2021) · arXiv · doi:10.48550/arxiv.2107.06277 · Cited by 41
Self-citationReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation
Xia, F., Li, C., Martín-Martín, R., Litany, O., Toshev, A., & Savarese, S. (2020) · arXiv · doi:10.48550/arxiv.2008.07792 · Cited by 33
Metadata
- Authors
- Kang, K., Belkhale, S., Kahn, G., Abbeel, P., & Levine, S.
- Venue
- 2019 International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2019-05
- Pages
- 6008-6014
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2967452881
- Cited by
- 119
- References
- 16
- FWCI
- 6.91
- 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: Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight. https://app.cochat.ai/papers/10.1109/icra.2019.8793735
- The paper
- Kang, K., Belkhale, S., Kahn, G., Abbeel, P., & Levine, S. (2019). Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight. 2019 International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra.2019.8793735
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.