Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets
Open accessAbstract
Robot learning holds the promise of learning policies that generalize broadly. However, such generalization requires sufficiently diverse datasets of the task of interest, which can be prohibitively expensive to collect. In other fields, such as computer vision, it is common to utilize shared, reusable datasets, such as ImageNet, to overcome this challenge, but this has proven difficult in robotics. In this paper, we ask: what would it take to enable practical data reuse in robotics for end-to-end skill learning? We hypothesize that the key is to use datasets with multiple tasks and multiple domains, such that a new user that wants to train their robot to perform a new task in a new domain can include this dataset in their training process and benefit from cross-task and cross-domain generalization. To evaluate this hypothesis, we collect a large multi-domain and multi-task dataset, with 7,200 demonstrations constituting 71 tasks across 10 environments, and empirically study how this data can improve the learning of new tasks in new environments. We find that jointly training with the proposed dataset and 50 demonstrations of a never-before-seen task in a new domain on average leads to a 2x improvement in success rate compared to using target domain data alone. We also find that data for only a few tasks in a new domain can bridge the domain gap and make it possible for a robot to perform a variety of prior tasks that were only seen in other domains. These results suggest that reusing diverse multi-task and multi-domain datasets, including our open-source dataset, may pave the way for broader robot generalization, eliminating the need to re-collect data for each new robot learning project.
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.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Generative adversarial imitation learning
Ho, J., & Ermon, S. (2016) · arXiv · doi:10.48550/arxiv.1606.03476 · Cited by 1,942 · see citing works
Mandlekar, A., Booher, J., Spero, M., Tung, A., Gupta, A., Zhu, Y., Garg, A., Savarese, S., & Fei-Fei, L. (2019) · arXiv · doi:10.48550/arxiv.1911.04052 · Cited by 48 · see citing works
Flagged first, then by citations
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
Self-citationAffordances from Human Videos as a Versatile Representation for Robotics
Bahl, S., Mendonca, R., Chen, L., Jain, U., & Pathak, D. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01324 · Cited by 119 · see citing works
“It has been common to introduce some form of prior derived from human knowledge, which could take the form of corrective interactions [22, 41, 64], structured policy spaces [2, 7, 7, 17, 48, 80, 89, 94, 102, 118], offline robotics data [24, 53, 54, 67, 92], using pretrained visual representations [79,84,100,116,117] o…”
BackgroundHabitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale
Ramrakhya, R., Undersander, E., Batra, D., & Das, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00511 · Cited by 90 · see citing works
OpenVLA: An Open-Source Vision-Language-Action Model
Kim, M. J., Pertsch, K., Karamcheti, S., Xiao, T., Balakrishna, A., Nair, S., Rafailov, R., Foster, E., Lam, G., Sanketi, P., et al. (2024) · arXiv · doi:10.48550/arxiv.2406.09246 · Cited by 62 · see citing works
“Fractal [92] 12.7% Kuka [45] 12.7% Bridge[6, 47] 13.3% Taco Play [93, 94] 3.0% Jaco Play [95] 0.4% Berkeley Cable Routing [96] 0.2% Roboturk [97] 2.3% Viola [98] 0.9% Berkeley Autolab UR5 [99] 1.2% Toto [100] 2.0% Language Table [101] 4.4% Stanford Hydra Dataset [102] 4.4% Austin Buds Dataset [103]…”
BackgroundInfluentialSelf-citationDayDreamer: World Models for Physical Robot Learning
Wu, P., Escontrela, A., Hafner, D., Goldberg, K., & Abbeel, P. (2022) · arXiv · doi:10.48550/arxiv.2206.14176 · Cited by 76 · see citing works
“One class of methods attempts to scale up experience collection through a fleet of robots (Kalashnikov et al., 2018; 2021; Ebert et al., 2021; Dasari et al., 2019; Levine et al., 2018).”
BackgroundAirExo: Low-Cost Exoskeletons for Learning Whole-Arm Manipulation in the Wild
Fang, H., Fang, H.-S., Wang, Y., Ren, J., Chen, J., Zhang, R., Wang, W., & Lu, C. (2024) · 2024 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra57147.2024.10610799 · Cited by 38 · see citing works
DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning
Jiang, Z., Xie, Y., Lin, K., Xu, Z., Wan, W., Mandlekar, A., Fan, L. J., & Zhu, Y. (2025) · 2025 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra55743.2025.11127809 · Cited by 24 · see citing works
(2025) · 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247088 · Cited by 13 · see citing works
Learning Interactive Real-World Simulators
Yang, S., Du, Y., Ghasemipour, K., Tompson, J., Kaelbling, L., Schuurmans, D., & Abbeel, P. (2023) · arXiv · doi:10.48550/arxiv.2310.06114 · Cited by 12 · see citing works
“An increasing amount of video data of real-robot executions paired with task descriptions such as the Bridge Data [18] and data that enabled RT-1 and RT-2 [19] are becoming increasingly available.”
Background$π_0$: A Vision-Language-Action Flow Model for General Robot Control
Black, K., Brown, N., Driess, D., Esmail, A., Equi, M., Finn, C., Fusai, N., Groom, L., Hausman, K., Ichter, B., et al. (2024) · arXiv · doi:10.48550/arxiv.2410.24164 · Cited by 13 · see citing works
“More recently, a number of high-quality datasets have been collected for robot control that enable broad generalization [23, 10, 52, 33, 34, 43, 13, 6], but typically for simpler tasks that consist of object relocation and rudimentary furniture manipulation (e.g., drawer opening) [31, 15].”
Self-citationCosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Agarwal, N., Ali, A., Bala, M., Balaji, Y., Barker, E., Cai, T., Chattopadhyay, P., Chen, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.03575 · Cited by 13 · see citing works
GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
NVIDIA, :, Bjorck, J., Castañeda, F., Cherniadev, N., Da, X., Ding, R., Fan, L. "., Fang, Y., Fox, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.14734 · Cited by 10 · see citing works
MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
Mandlekar, A., Nasiriany, S., Wen, B., Akinola, I., Narang, Y., Fan, L., Zhu, Y., & Fox, D. (2023) · arXiv · doi:10.48550/arxiv.2310.17596 · Cited by 5 · see citing works
“One popular data source is human demonstrators that teleoperate robot arms [2–6, 23– 27 ], but collecting 3 Problem Setup Imitation Learning.”
BackgroundSmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Shukor, M., Aubakirova, D., Capuano, F., Kooijmans, P., Palma, S., Zouitine, A., Aractingi, M., Pascal, C., Russi, M., Marafioti, A., et al. (2025) · arXiv · doi:10.48550/arxiv.2506.01844 · Cited by 3 · see citing works
“In particular, robotic policies (Zhao et al., 2023; Chi et al., 2024; Lee et al., 2024; Hansen et al., 2022) still face challenges in generalizing across object types, positions, environments, and tasks (Xie et al., 2024; Ebert et al., 2021).”
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
Nasiriany, S., Maddukuri, A., Zhang, L., Parikh, A., Lo, A., Joshi, A., Mandlekar, A., & Zhu, Y. (2024) · arXiv · doi:10.48550/arxiv.2406.02523 · Cited by 3 · see citing works
“It has been used extensively in prior works [49, 31, 9, 2, 16, 6, 17].”
BackgroundMethodInfluentialTowards Embodiment Scaling Laws in Robot Locomotion
Ai, B., Dai, L., Bohlinger, N., Li, D., Mu, T., Wu, Z., Fay, K., Christensen, H. I., Peters, J., & Su, H. (2025) · arXiv · doi:10.48550/arxiv.2505.05753
“…has not systematically investigated the relationship between generalization performance and the number of training embodiments at scale, likely due to the limited size of available embodiment collections, often restricted to ∼ 10 2 in simulation [74] or ∼ 10 1 in the real world [23, 49, 70, 96].”
- Authors
- Ebert, F., Yang, Y., Schmeckpeper, K., Bucher, B., Georgakis, G., Daniilidis, K., Finn, C., & Levine, S.
- Venue
- Robotics: Science and Systems XVIII
- Published
- 2022-06-27
- OpenAlex
- W3204665606
- Cited by
- 94
- References
- 5
- Citations by year
- 2026: 15 · 2025: 33 · 2024: 27 · 2023: 13 · 2022: 5 · 2021: 1
- FWCI
- 10.78
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Robotics: Science and Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- robot learning, domain generalization, cross-task generalization, multi-domain dataset, data reuse, robot demonstration, open-source dataset, domain gap
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
