Towards Learning a Generalist Model for Embodied Navigation
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Building a generalist agent that can interact with the world is the intriguing target of AI systems, thus spurring the research for embodied navigation, where an agent is required to navigate according to instructions or respond to queries. Despite the major progress attained, previous works primarily focus on task-specific agents and lack gen-eralizability to unseen scenarios. Recently, LLMs have pre-sented remarkable capabilities across various fields, and provided a promising opportunity for embodied navigation. Drawing on this, we propose the first generalist model for embodied navigation, NaviLLM. It adapts LLMs to em-bodied navigation by introducing schema-based instruction. The schema-based instruction flexibly casts various tasks into generation problems, thereby unifying a wide range of tasks. This approach allows us to integrate di-verse data sources from various datasets into the training, equipping NaviLLM with a wide range of capabilities required by embodied navigation. We conduct extensive ex-periments to evaluate the performance and generalizability of our model. The experimental results demonstrate that our unified model achieves state-of-the-art performance on CVDN, SOON, and ScanQA. Specifically, it surpasses the previous stats-of-the-art method by a significant margin of 29% in goal progress on CVDN. Moreover, our model also demonstrates strong generalizability and presents im-pressive results on unseen tasks, e.g. embodied question answering and 3D captioning. Our code is available at https://github.com/LaVi-Lab/NaviLLM.
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
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1516 · Cited by 2,428
Habitat: A Platform for Embodied AI Research
Savva, M., Kadian, A., Maksymets, O., Zhao, Y., Wijmans, E., Jain, B., Straub, J., Liu, J., Koltun, V., Malik, J., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00943 · Cited by 1,237 · cited 1×
“One of the distinctions be-tween our work and other multi-modal LLMs is that, our work is designed for embodied AI, including navigation and 3D understanding, which previous works don’t consider.”
BackgroundAnderson, P., Wu, Q., Teney, D., Bruce, J., Johnson, M., Sunderhauf, N., Reid, I., Gould, S., & van den Hengel, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00387 · Cited by 1,187
Code as Policies: Language Model Programs for Embodied Control
Liang, J., Huang, W., Xia, F., Xu, P., Hausman, K., Ichter, B., Florence, P., & Zeng, A. (2023) · 2023 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48891.2023.10160591 · Cited by 767 · cited 1×
“As depicted in Figure 2 (a), the scene encoder takes the current visual observation as input, and transforms it into a series of scene representations (§3.2.1).”
BackgroundInfluentialCode as Policies: Language Model Programs for Embodied Control
Liang, J., Huang, W., Xia, F., Xu, P., Hausman, K., Ichter, B., Florence, P., & Zeng, A. (2022) · arXiv · doi:10.48550/arxiv.2209.07753 · Cited by 767
RT-1: Robotics Transformer for Real-World Control at Scale
Brohan, A., Brown, N., Carbajal, J., Chebotar, Y., Dabis, J., Finn, C., Gopalakrishnan, K., Hausman, K., Herzog, A., Hsu, J., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.06817 · Cited by 727
Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023) · arXiv · doi:10.48550/arxiv.2304.08485 · Cited by 682
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
Ahn, M., Brohan, A., Brown, N., Chebotar, Y., Cortes, O., David, B., Finn, C., Fu, C., Gopalakrishnan, K., Hausman, K., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.01691 · Cited by 624
On evaluation of embodied navigation agents
Anderson, P., Chang, A., Chaplot, D. S., Dosovitskiy, A., Gupta, S., Koltun, V., Kosecka, J., Malik, J., Mottaghi, R., Savva, M., et al. (2018) · arXiv · doi:10.48550/arxiv.1807.06757 · Cited by 622
AI2-THOR: An Interactive 3D Environment for Visual AI
Kolve, E., Mottaghi, R., Han, W., VanderBilt, E., Weihs, L., Herrasti, A., Deitke, M., Ehsani, K., Gordon, D., Zhu, Y., et al. (2017) · arXiv · doi:10.48550/arxiv.1712.05474 · Cited by 578 · cited 1×
“This has led to the emergence of embodied navigation [2, 33, 47], where an agent located in 3D environment is required to navigate according to various forms of instructions and provide textual responses based on user queries.”
BackgroundMiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Zhu, D., Chen, J., Shen, X., Li, X., & Elhoseiny, M. (2023) · arXiv · doi:10.48550/arxiv.2304.10592 · Cited by 469 · cited 2×
“However, it does not address the problem of calibrating LLMs for embodied navigation that requires the ability of sequential decision-making.”
BackgroundREVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments
Qi, Y., Wu, Q., Anderson, P., Wang, X., Wang, W. Y., Shen, C., & van den Hengel, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01000 · Cited by 331 · cited 2×
“Lastly, we also provide visualization for NaviLLM on unseen scenes and tasks (§5.4).”
BackgroundMethodInfluentialSpeaker-Follower Models for Vision-and-Language Navigation
Fried, D., Hu, R., Cirik, V., Rohrbach, A., Andreas, J., Morency, L.-P., Berg-Kirkpatrick, T., Saenko, K., Klein, D., & Darrell, T. (2018) · arXiv · doi:10.48550/arxiv.1806.02724 · Cited by 291
Inner Monologue: Embodied Reasoning through Planning with Language Models
Huang, W., Xia, F., Xiao, T., Chan, H., Liang, J., Florence, P., Zeng, A., Tompson, J., Mordatch, I., Chebotar, Y., et al. (2022) · arXiv · doi:10.48550/arxiv.2207.05608 · Cited by 287 · cited 1×
“The first line focuses on translating visual information into textual format, which is then processed by the LLMs to generate plans [8, 30, 41, 58], landmarks [48], or code [38].”
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Brohan, A., Brown, N., Carbajal, J., Chebotar, Y., Chen, X., Choromanski, K., Ding, T., Driess, D., Dubey, A., Finn, C., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.15818 · Cited by 276 · cited 2×
“However, it does not address the problem of calibrating LLMs for embodied navigation that requires the ability of sequential decision-making.”
BackgroundMethodInfluentialRoom-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
Ku, A., Anderson, P., Patel, R., Ie, E., & Baldridge, J. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.356 · Cited by 274
VLN↻BERT: A Recurrent Vision-and-Language BERT for Navigation
Hong, Y., Wu, Q., Qi, Y., Rodriguez-Opazo, C., & Gould, S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00169 · Cited by 264 · cited 1×
“However, it does not address the problem of calibrating LLMs for embodied navigation that requires the ability of sequential decision-making.”
BackgroundTowards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training
Hao, W., Li, C., Li, X., Carin, L., & Gao, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01315 · Cited by 264
Vision-language navigation with self-supervised auxiliary reasoning tasks
Zhu, F., Zhu, Y., Chang, X., & Liang, X. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01003 · Cited by 223
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web
Majumdar, A., Shrivastava, A., Lee, S., Anderson, P., Parikh, D., & Batra, D. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58539-6_16 · Cited by 201
ScanQA: 3D Question Answering for Spatial Scene Understanding
Azuma, D., Miyanishi, T., Kurita, S., & Kawanabe, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01854 · Cited by 197
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., & Zhou, J. (2023) · arXiv · doi:10.48550/arxiv.2308.12966 · Cited by 193
Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
Shridhar, M., Manuelli, L., & Fox, D. (2022) · arXiv · doi:10.48550/arxiv.2209.05451 · Cited by 189
Peng, B., Li, C., He, P., Galley, M., & Gao, J. (2023) · arXiv · doi:10.48550/arxiv.2304.03277 · Cited by 183
LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action
Shah, D., Osinski, B., Ichter, B., & Levine, S. (2022) · arXiv · doi:10.48550/arxiv.2207.04429 · Cited by 179 · cited 1×
“As depicted in Figure 2 (a), the scene encoder takes the current visual observation as input, and transforms it into a series of scene representations (§3.2.1).”
BackgroundInfluentialThomason, J., Murray, M., Cakmak, M., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1907.04957 · Cited by 173 · cited 4×
“…navigation, ranging from vision-language navigation that follows step-by-step instructions [3, 34] or coarse-grained directives [17, 43, 61], to the tasks guided by interactions between humans and agents [19, 52], and even to embodied question answering through proactive exploration [18, 55].”
BackgroundResultInfluentialAirbert: In-domain Pretraining for Vision-and-Language Navigation
Guhur, P.-L., Tapaswi, M., Chen, S., Laptev, I., & Schmid, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00166 · Cited by 139 · cited 1×
“However, it does not address the problem of calibrating LLMs for embodied navigation that requires the ability of sequential decision-making.”
BackgroundHOP: History-and-Order Aware Pretraining for Vision-and-Language Navigation
Qiao, Y., Qi, Y., Hong, Y., Yu, Z., Wang, P., & Wu, Q. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01498 · Cited by 82
Learning from Unlabeled 3D Environments for Vision-and-Language Navigation
Chen, S., Guhur, P.-L., Tapaswi, M., Schmid, C., & Laptev, I. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19842-7_37 · Cited by 35
Hwang, M., Jeong, J., Kim, M., Oh, Y., & Oh, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00646 · Cited by 26
BEVBert: Multimodal Map Pre-training for Language-guided Navigation
An, D., Qi, Y., Li, Y., Huang, Y., Wang, L., Tan, T., & Shao, J. (2022) · arXiv · doi:10.48550/arxiv.2212.04385 · Cited by 20
Self-citation
Cited by
Navgpt-2: Unleashing navigational reasoning capability for large vision-language models
Zhou, G., Hong, Y., Wang, Z., Wang, X. E., & Wu, Q. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72667-5_15 · Cited by 63
Embodied navigation with multi-modal information: A survey from tasks to methodology
Wu, Y., Zhang, P., Gu, M., Zheng, J., & Bai, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102532 · Cited by 34
SignNav: Directional Signage-Cue Guided Visual Navigation in Large-Scale Indoor Environments
Sun, J., Huang, Y., Li, H., Xiao, S., Guo, S., Ghaffari, M., Li, Q., Xu, C., & Kong, H. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3730302
Metadata
- Authors
- Zheng, D., Huang, S., Zhao, L., Zhong, Y., & Wang, L.
- Venue
- 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2024-06-16
- Pages
- 13624-13634
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4402703032
- Cited by
- 68
- References
- 34
- FWCI
- 14.85
- 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
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.