# DREAM: Domain-aware Reasoning for Efficient Autonomous Underwater Monitoring

arXiv: https://arxiv.org/abs/2509.13666 · HTML: https://mlsanity.com/paper/2509.13666/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 41 of its 71 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 41)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought](https://mlsanity.com/paper/2305.15021/) (2023)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model](https://mlsanity.com/paper/2305.11176/) (2023)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [OceanGPT: A Large Language Model for Ocean Science Tasks](https://mlsanity.com/paper/2310.02031/) (2023)
- [Experimental Comparison of Open Source Visual-Inertial-Based State Estimation Algorithms in the Underwater Domain](https://mlsanity.com/paper/1904.02215/) (2019)
- [The invariant extended Kalman filter as a stable observer](https://mlsanity.com/paper/1410.1465/) (2014)
- [Navigation in the Presence of Obstacles for an Agile Autonomous Underwater Vehicle](https://mlsanity.com/paper/1903.11750/) (2019)
- [Cook2LTL: Translating Cooking Recipes to LTL Formulae using Large Language Models](https://mlsanity.com/paper/2310.00163/) (2023)
- [OysterNet: Enhanced Oyster Detection Using Simulation](https://mlsanity.com/paper/2209.08176/) (2022)
- [OysterSim: Underwater Simulation for Enhancing Oyster Reef Monitoring](https://mlsanity.com/paper/2209.09395/) (2022)
- [AquaVis: A Perception-Aware Autonomous Navigation Framework for Underwater Vehicles](https://mlsanity.com/paper/2110.01646/) (2021)
- [OceanPlan: Hierarchical Planning and Replanning for Natural Language AUV Piloting in Large-scale Unexplored Ocean Environments](https://mlsanity.com/paper/2403.15369/) (2024)
- [AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis](https://mlsanity.com/paper/2502.01785/) (2025)
- [UIVNAV: Underwater Information-driven Vision-based Navigation via Imitation Learning](https://mlsanity.com/paper/2309.08806/) (2023)
- [SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey](https://mlsanity.com/paper/2411.00172/) (2024)
- [ODYSSEE: Oyster Detection Yielded by Sensor Systems on Edge Electronics](https://mlsanity.com/paper/2409.07003/) (2024)
- [Verti-Bench: A General and Scalable Off-Road Mobility Benchmark for Vertically Challenging Terrain](https://mlsanity.com/paper/2502.11426/) (2025)
- [Llamarine: Open-source Maritime Industry-specific Large Language Model](https://mlsanity.com/paper/2503.00203/) (2025)
- [Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions](https://mlsanity.com/paper/2503.00527/) (2025)
- [Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning](https://mlsanity.com/paper/2503.15724/) (2025)
- [OceanChat: Piloting Autonomous Underwater Vehicles in Natural Language](https://mlsanity.com/paper/2309.16052/) (2023)
- [3D Water Quality Mapping using Invariant Extended Kalman Filtering for Underwater Robot Localization](https://mlsanity.com/paper/2409.11578/) (2024)
- [Word2Wave: Language Driven Mission Programming for Efficient Subsea Deployments of Marine Robots](https://mlsanity.com/paper/2409.18405/) (2024)

## Built on by (most cited first, 2 of 2)

- [AquaBEV: Monocular Underwater BEV Occupancy with 3D Sonar Supervision](https://mlsanity.com/paper/2609.04411/) (2026)
- [AquaBEV-Nav: Learned BEV Occupancy for Underwater Navigation and Exploration](https://mlsanity.com/paper/2609.32156/) (2026)

## Abstract (arXiv)

The ocean is warming and acidifying, increasing the risk of mass mortality events for temperature-sensitive shellfish such as oysters. This motivates the development of long-term monitoring systems. However, human labor is costly and long-duration underwater work is highly hazardous, thus favoring robotic solutions as a safer and more efficient option. To enable underwater robots to make real-time, environment-aware decisions without human intervention, we must equip them with an intelligent "brain." This highlights the need for persistent,wide-area, and low-cost benthic monitoring. To this end, we present DREAM, a Vision Language Model (VLM)-guided autonomy framework for long-term underwater exploration and habitat monitoring. The results show that our framework is highly efficient in finding and exploring target objects (e.g., oysters, shipwrecks) without prior location information. In the oyster-monitoring task, our framework takes 31.5% less time than the previous baseline with the same amount of oysters. Compared to the vanilla VLM, it uses 23% fewer steps while covering 8.88% more oysters. In shipwreck scenes, our framework successfully explores and maps the wreck without collisions, requiring 27.5% fewer steps than the vanilla model and achieving 100% coverage, while the vanilla model achieves 60.23% average coverage in our shipwreck environments.