Skip to content

Commit c6c05cf

Browse files
committed
修复姓名大小写带来的问题
1 parent 9f6bcea commit c6c05cf

1 file changed

Lines changed: 3 additions & 3 deletions

File tree

index.html

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@
1212
<!-- TODO: Add 5-10 relevant keywords for your research area -->
1313
<meta name="keywords" content="Robots, Underwater VLA, Vision-Language-Action, AI, ROV, Nevigation, Manipulation, Dataset">
1414
<!-- TODO: List all authors -->
15-
<meta name="author" content="Junwen Gu, Zhiheng wu, Pengxuan Si, Shuang Qiu, Yukai Feng, Luoyang Sun, Laien Luo, Lianyi Yu, Jian Wang, and Zhengxing Wu">
15+
<meta name="author" content="Junwen Gu, Zhiheng Wu, Pengxuan Si, Shuang Qiu, Yukai Feng, Luoyang Sun, Laien Luo, Lianyi Yu, Jian Wang, and Zhengxing Wu">
1616
<meta name="robots" content="index, follow">
1717
<meta name="language" content="English">
1818

@@ -143,7 +143,7 @@
143143
"image": "https://vincentgu2000.github.io/u0project/static\images\video_poster.png",
144144
"keywords": ["Robots", "Underwater VLA", "Vision-Language-Action", "AI", "ROV", "Nevigation", "Manipulation", "Dataset"],
145145
"abstract": "Underwater environments present unique challenges for robotic operation, including complex hydrodynamics, limited visibility, and constrained communication. Although data-driven approaches have advanced embodied intelligence in terrestrial robots and enabled task-specific autonomous underwater robots, developing underwater intelligence capable of autonomously performing multiple tasks remains highly challenging, as large-scale, high-quality underwater datasets are still scarce. To address these limitations, we introduce USIM, a simulation-based multi-task Vision-Language-Action (VLA) dataset for underwater robots. USIM comprises over 561K frames from 1,852 trajectories, totaling approximately 15.6 hours of BlueROV2 interactions across 20 tasks in 9 diverse scenarios, ranging from visual navigation to mobile manipulation. Building upon this dataset, we propose U0, a VLA model for general underwater robots, which integrates binocular vision and other sensor modalities through multimodal fusion, and further incorporates a convolution-attention-based perception focus enhancement module (CAP) to improve spatial understanding and mobile manipulation. Across tasks such as inspection, obstacle avoidance, scanning, and dynamic tracking, the framework achieves a success rate of 80\%, while in challenging mobile manipulation tasks, it reduces the distance to the target by 21.2\% compared with baseline methods, demonstrating its effectiveness. USIM and U0 show that VLA models can be effectively applied to underwater robotic applications, providing a foundation for scalable dataset construction, improved task autonomy, and the practical realization of intelligent general underwater robots.",
146-
"citation": "@misc{gu2025usimu0visionlanguageactiondataset, title={USIM and U0: A Vision-Language-Action Dataset and Model for General Underwater Robots}, author={Junwen Gu and Zhiheng wu and Pengxuan Si and Shuang Qiu and Yukai Feng and Luoyang Sun and Laien Luo and Lianyi Yu and Jian Wang and Zhengxing Wu}, year={2025}, eprint={2510.07869}, archivePrefix={arXiv}, primaryClass={cs.RO}, url={https://arxiv.org/abs/2510.07869}, }",
146+
"citation": "@misc{gu2025usimu0visionlanguageactiondataset, title={USIM and U0: A Vision-Language-Action Dataset and Model for General Underwater Robots}, author={Junwen Gu and Zhiheng Wu and Pengxuan Si and Shuang Qiu and Yukai Feng and Luoyang Sun and Laien Luo and Lianyi Yu and Jian Wang and Zhengxing Wu}, year={2025}, eprint={2510.07869}, archivePrefix={arXiv}, primaryClass={cs.RO}, url={https://arxiv.org/abs/2510.07869}, }",
147147
"isAccessibleForFree": true,
148148
"license": "https://creativecommons.org/licenses/by/4.0/",
149149
"mainEntity": {
@@ -483,7 +483,7 @@ <h2 class="title">BibTeX</h2>
483483
</div>
484484
<pre id="bibtex-code"><code>@misc{gu2025usimu0visionlanguageactiondataset,
485485
title={USIM and U0: A Vision-Language-Action Dataset and Model for General Underwater Robots},
486-
author={Junwen Gu and Zhiheng wu and Pengxuan Si and Shuang Qiu and Yukai Feng and Luoyang Sun and Laien Luo and Lianyi Yu and Jian Wang and Zhengxing Wu},
486+
author={Junwen Gu and Zhiheng Wu and Pengxuan Si and Shuang Qiu and Yukai Feng and Luoyang Sun and Laien Luo and Lianyi Yu and Jian Wang and Zhengxing Wu},
487487
year={2025},
488488
eprint={2510.07869},
489489
archivePrefix={arXiv},

0 commit comments

Comments
 (0)