The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
GNM: A General Navigation Model to Drive Any Robot
Open accessAbstract
Learning provides a powerful tool for vision-based navigation, but the capabilities of learning-based policies are constrained by limited training data. If we could combine data from all available sources, including multiple kinds of robots, we could train more powerful navigation models. In this paper, we study how a general goal-conditioned model for vision-based navigation can be trained on data obtained from many distinct but structurally similar robots, and enable broad generalization across environments and embodiments. We analyze the necessary design decisions for effective data sharing across robots, including the use of temporal context and standardized action spaces, and demonstrate that an omnipolicy trained from heterogeneous datasets outperforms policies trained on any single dataset. We curate 60 hours of navigation trajectories from 6 distinct robots, and deploy the trained GNM on a range of new robots, including an underactuated quadrotor. We find that training on diverse data leads to robustness against degradation in sensing and actuation. Using a pre-trained navigation model with broad generalization capabilities can bootstrap applications on novel robots going forward, and we hope that the GNM represents a step in that direction. For more information on the datasets, code, and videos, please check out our project page11sites.google.com/view/drive-any-robot.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“For robotics, world models are essential for tasks such as navigation [179], object detection [204], and task planning [69], requiring a precise understanding of external dynamics [51] and the ability to generate interactive and embodied environments [148].”
From Understanding World or Predicting Future? A Comprehensive Survey of World Models (2026) · cites this paper as [179]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We use multi-GPU training with batch sizes between 400–1200 and perform gradient updates using the Adam optimizer [47] with a learning rate of 5× 10−4.”
MethodImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“Machine learning methods have enabled broad generalization with real-world applicability in natural language processing [1], visual perception [2–4], and other domains [5, 6] by leveraging Internet-scale data.”
BackgroundA simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857 · cited 1×
“Such large-scale models also support the ability to be adapted for new tasks by reusing the representations learned from broader, larger, and more general datasets, for example by or zero-shot transfer [7–9], or fine-tuning on target-domain data.”
MethodQuo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
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×
“which is a popular strategy for pre-training in many visionbased applications [49, 50], improves a bit but still struggles in a majority of the environments.”
BackgroundCNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2014.131 · Cited by 4,451 · cited 1×
“which is a popular strategy for pre-training in many visionbased applications [49, 50], improves a bit but still struggles in a majority of the environments.”
BackgroundBDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., & Darrell, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00271 · Cited by 2,641 · cited 1×
“Learning from large, diverse robotic datasets has been studied for various robotic applications where data sharing across similar robots helps scale learning to challenging environments [10–12].”
BackgroundHierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511 · cited 1×
“cessing [1], visual perception [2–4], and other domains [5, 6] by leveraging Internet-scale data.”
BackgroundTarget-driven visual navigation in indoor scenes using deep reinforcement learning
Zhu, Y., Mottaghi, R., Kolve, E., Lim, J. J., Gupta, A., Fei-Fei, L., & Farhadi, A. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989381 · Cited by 1,533
Evaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436 · cited 1×
“cessing [1], visual perception [2–4], and other domains [5, 6] by leveraging Internet-scale data.”
Background
Research works printed but not linked: 6
- wei, 0, Finetuned language models are zeroshot learners, International Conference on Learning Representations (ICLR)
- shah, 0, Offline reinforcement learning for customizable visual navigation, Conference on Robot Learning (CoRL)
- kahn, 0, Self-Supervised Deep RL with Generalized Computation Graphs for Robot Navigation, International Conference on Robotics and Automation (ICRA)
- eysenbach, 2019, Search on the Replay Buffer: Bridging Planning and RL, Neural Information Processing Systems (NeurIPS)
- radford, 2018, Improving language understanding by generative pre-training
- shaban, 0, Se-mantic terrain classification for off-road autonomous driving, Conference on Robot Learning (CoRL)
Cited by
Large language models empowered agent-based modeling and simulation: a survey and perspectives
Gao, C., Lan, X., Li, N., Yuan, Y., Ding, J., Zhou, Z., Xu, F., & Li, Y. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-03611-3 · Cited by 294
“For simulating the human-like navigation behaviors in the physical environment, LM-Nav (Shah et al., 2023) combines large language models with image-language alignment algorithms.”
NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration
Sridhar, A., Shah, D., Glossop, C., & Levine, S. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610665 · Cited by 468
“We train NoMaD on a combination of GNM and SACSoN datasets, large heterogeneous datasets collected across a diverse set of environments and robotic platforms, including pedestrian-rich environments, spanning over 100 hours of real-world trajectories [40, 41].”
MethodSelf-citationOpen X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration 0
O’Neill, A., Rehman, A., Maddukuri, A., Gupta, A., Padalkar, A., Lee, A., Pooley, A., Gupta, A., Mandlekar, A., Jain, A., et al. (2024) · 2024 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra57147.2024.10611477 · Cited by 210
Self-citationUnderstanding World or Predicting Future? A Comprehensive Survey of World Models
Ding, J., Zhang, Y., Shang, Y., Zhang, Y., Zong, Z., Feng, J., Yuan, Y., Su, H., Li, N., Sukiennik, N., et al. (2026) · ACM Computing Surveys · doi:10.1145/3746449 · Cited by 169
“For robotics, world models are essential for tasks such as navigation [225], object detection [259], and task planning [92], requiring a precise understanding of external dynamics [69] and the ability to generate interactive and embodied environments [189].”
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Khazatsky, A., Pertsch, K., Nair, S., Balakrishna, A., Dasari, S., Karamcheti, S., Nasiriany, S., Srirama, M., Chen, L., Ellis, K., et al. (2024) · Robotics: Science and Systems XX · doi:10.15607/rss.2024.xx.120 · Cited by 159
Self-citation
Metadata
- Authors
- Shah, D., Sridhar, A., Bhorkar, A., Hirose, N., & Levine, S.
- Affiliations
- University of California, Berkeley (US)
- Toyota Motor North America (United States) (US)
- Venue
- 2023 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2023-05-29
- Pages
- 7226-7233
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W4383108302
- Cited by
- 85
- References
- 48
- Citations by year
- 2026: 19 · 2025: 41 · 2024: 21 · 2023: 4
- FWCI
- 15.09
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- Toyota Research Institute
- Defense Advanced Research Projects Agency
- Air Force Office of Scientific Research (FA9550-, FA9550-22-1-0273, -21-1-)
- Army Research Office (W911NF-21-1-, W911NF-17, W911NF-21-1-0097, W911NF, W911NF-17-2-0181)
- 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
- visual navigation, robot navigation, temporal context, embodied AI
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: GNM: A General Navigation Model to Drive Any Robot. https://app.cochat.ai/papers/10.1109/icra48891.2023.10161227
- The paper
- Shah, D., Sridhar, A., Bhorkar, A., Hirose, N., & Levine, S. (2023). GNM: A General Navigation Model to Drive Any Robot. 2023 IEEE International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra48891.2023.10161227
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.