OceanGym: A Benchmark Environment for Underwater Embodied Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908675034054656 |
|---|---|
| author | Xue, Yida Mao, Mingjun Ru, Xiangyuan Zhu, Yuqi Ren, Baochang Qiao, Shuofei Wang, Mengru Deng, Shumin An, Xinyu Zhang, Ningyu Chen, Ying Chen, Huajun |
| author_facet | Xue, Yida Mao, Mingjun Ru, Xiangyuan Zhu, Yuqi Ren, Baochang Qiao, Shuofei Wang, Mengru Deng, Shumin An, Xinyu Zhang, Ningyu Chen, Ying Chen, Huajun |
| contents | We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments. Unlike terrestrial or aerial domains, underwater settings present extreme perceptual and decision-making challenges, including low visibility, dynamic ocean currents, making effective agent deployment exceptionally difficult. OceanGym encompasses eight realistic task domains and a unified agent framework driven by Multi-modal Large Language Models (MLLMs), which integrates perception, memory, and sequential decision-making. Agents are required to comprehend optical and sonar data, autonomously explore complex environments, and accomplish long-horizon objectives under these harsh conditions. Extensive experiments reveal substantial gaps between state-of-the-art MLLM-driven agents and human experts, highlighting the persistent difficulty of perception, planning, and adaptability in ocean underwater environments. By providing a high-fidelity, rigorously designed platform, OceanGym establishes a testbed for developing robust embodied AI and transferring these capabilities to real-world autonomous ocean underwater vehicles, marking a decisive step toward intelligent agents capable of operating in one of Earth's last unexplored frontiers. The code and data are available at https://github.com/OceanGPT/OceanGym. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26536 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OceanGym: A Benchmark Environment for Underwater Embodied Agents Xue, Yida Mao, Mingjun Ru, Xiangyuan Zhu, Yuqi Ren, Baochang Qiao, Shuofei Wang, Mengru Deng, Shumin An, Xinyu Zhang, Ningyu Chen, Ying Chen, Huajun Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Robotics We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments. Unlike terrestrial or aerial domains, underwater settings present extreme perceptual and decision-making challenges, including low visibility, dynamic ocean currents, making effective agent deployment exceptionally difficult. OceanGym encompasses eight realistic task domains and a unified agent framework driven by Multi-modal Large Language Models (MLLMs), which integrates perception, memory, and sequential decision-making. Agents are required to comprehend optical and sonar data, autonomously explore complex environments, and accomplish long-horizon objectives under these harsh conditions. Extensive experiments reveal substantial gaps between state-of-the-art MLLM-driven agents and human experts, highlighting the persistent difficulty of perception, planning, and adaptability in ocean underwater environments. By providing a high-fidelity, rigorously designed platform, OceanGym establishes a testbed for developing robust embodied AI and transferring these capabilities to real-world autonomous ocean underwater vehicles, marking a decisive step toward intelligent agents capable of operating in one of Earth's last unexplored frontiers. The code and data are available at https://github.com/OceanGPT/OceanGym. |
| title | OceanGym: A Benchmark Environment for Underwater Embodied Agents |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Robotics |
| url | https://arxiv.org/abs/2509.26536 |