# OceanPlan: Hierarchical Planning and Replanning for Natural Language AUV Piloting in Large-scale Unexplored Ocean Environments

arXiv: https://arxiv.org/abs/2403.15369 · HTML: https://mlsanity.com/paper/2403.15369/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2024.

## Built on by (most cited first, 7 of 7)

- [A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science](https://mlsanity.com/paper/2504.09848/) (2025)
- [A Roadmap to Guide the Integration of LLMs in Hierarchical Planning](https://mlsanity.com/paper/2501.08068/) (2025)
- [KUNPENG: An Embodied Large Model for Intelligent Maritime](https://mlsanity.com/paper/2407.09048/) (2024)
- [DREAM: Domain-aware Reasoning for Efficient Autonomous Underwater Monitoring](https://mlsanity.com/paper/2509.13666/) (2025)
- [Towards a General Framework for HTN Modeling with LLMs](https://mlsanity.com/paper/2511.18165/) (2025)
- [LLM-VLM Fusion Framework for Autonomous Maritime Port Inspection using a Heterogeneous UAV-USV System](https://mlsanity.com/paper/2601.13096/) (2026)
- [AquaBEV-Nav: Learned BEV Occupancy for Underwater Navigation and Exploration](https://mlsanity.com/paper/2609.32156/) (2026)

## Abstract (arXiv)

We develop a hierarchical LLM-task-motion planning and replanning framework to efficiently ground an abstracted human command into tangible Autonomous Underwater Vehicle (AUV) control through enhanced representations of the world. We also incorporate a holistic replanner to provide real-world feedback with all planners for robust AUV operation. While there has been extensive research in bridging the gap between LLMs and robotic missions, they are unable to guarantee success of AUV applications in the vast and unknown ocean environment. To tackle specific challenges in marine robotics, we design a hierarchical planner to compose executable motion plans, which achieves planning efficiency and solution quality by decomposing long-horizon missions into sub-tasks. At the same time, real-time data stream is obtained by a replanner to address environmental uncertainties during plan execution. Experiments validate that our proposed framework delivers successful AUV performance of long-duration missions through natural language piloting.