DREAM: Domain-aware Reasoning for Efficient Autonomous Underwater Monitoring

• URL: http://arxiv.org/abs/2509.13666v1
• Date: Wed, 17 Sep 2025 03:35:52 GMT
• Title: DREAM: Domain-aware Reasoning for Efficient Autonomous Underwater Monitoring
• Abstract summary: We present DREAM, a Vision Language Model (VLM)-guided autonomy framework for long-term underwater exploration and habitat monitoring.<n>In oyster-monitoring task, our framework takes 31.5% less time than the previous baseline with the same amount of oysters.<n>In shipwreck scenes, our framework successfully explores and maps the wreck without collisions, requiring 27.5% fewer steps than the vanilla model.
• Score: 14.347123589187964
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CORAL: COntextual Reasoning And Local Planning in A Hierarchical VLM Framework for Underwater Monitoring [10.250809787836607]
  Oyster reefs are critical ecosystem species that sustain biodiversity, filter water, and protect coastlines, yet they continue to decline globally.<n>Regular underwater monitoring to assess reef health is costly, hazardous, and limited when performed by human divers.<n>Existing autonomous underwater vehicles (AUVs) rely on geometry-based navigation that cannot interpret scene semantics.<n>Recent vision-language models (VLMs) enable semantic reasoning for intelligent exploration, but existing VLM-driven systems adopt an end-to-end paradigm.<n>We propose CORAL, a framework that decouples high-level semantic reasoning from low-level reactive control.
  arXiv  Detail & Related papers  (2026-03-16T03:35:08Z)
• Autonomous Sea Turtle Robot for Marine Fieldwork [45.22208456166796]
  We present a sea turtle-inspired autonomous underwater robot that closed the gap between bioinspired locomotion and field-ready autonomy.<n>The robot combines robust depth-heading stabilization with obstacle avoidance and target-centric control, enabling it to track and interact with moving objects in complex terrain.
  arXiv  Detail & Related papers  (2026-02-24T21:36:19Z)
• Docking and Persistent Operations for a Resident Underwater Vehicle [0.0]
  This work presents the development, deployment, and operation of a resident infrastructure using a mini-class Remotely Operated Vehicle (ROV) at 90m depth.<n>The ROVis equipped with enhanced onboard processing and perception, allowing it to autonomously navigate using USBL signals.<n>The system demonstrated a 90% autonomous docking success rate and completed full inspection missions within four minutes.
  arXiv  Detail & Related papers  (2026-02-18T10:50:04Z)
• IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation [56.43007596544299]
  IndustryNav is the first dynamic industrial navigation benchmark for active spatial reasoning.<n>A study of nine state-of-the-art Visual Large Language Models reveals that closed-source models maintain a consistent advantage.
  arXiv  Detail & Related papers  (2025-11-21T16:48:49Z)
• NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding [60.76337064425815]
  We study the underwater scene understanding methods, which aim to achieve automated underwater exploration.<n>NautData is a dataset containing 1.45 M image-text pairs supporting eight underwater scene understanding tasks.<n>We propose a plug-and-play vision feature enhancement (VFE) module, which explicitly restores clear underwater information.
  arXiv  Detail & Related papers  (2025-10-31T14:00:35Z)
• OceanGym: A Benchmark Environment for Underwater Embodied Agents [69.56465775825275]
  OceanGym is the first comprehensive benchmark for ocean underwater embodied agents.<n>It is designed to advance AI in one of the most demanding real-world environments.<n>By providing a high-fidelity, rigorously designed platform, OceanGym establishes a testbed for developing robust embodied AI.
  arXiv  Detail & Related papers  (2025-09-30T17:09:32Z)
• DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation [55.888688171010365]
  DORAEMON is a cognitive-inspired framework consisting of Ventral and Dorsal Streams that mimics human navigation capabilities.<n>We evaluate DORAEMON on the HM3D, MP3D and GOAT datasets, where it achieves state-of-the-art performance on both success rate (SR) and success weighted by path length (SPL) metrics.
  arXiv  Detail & Related papers  (2025-05-28T04:46:13Z)
• ForesightNav: Learning Scene Imagination for Efficient Exploration [57.49417653636244]
  We propose ForesightNav, a novel exploration strategy inspired by human imagination and reasoning.<n>Our approach equips robotic agents with the capability to predict contextual information, such as occupancy and semantic details, for unexplored regions.<n>We validate our imagination-based approach using the Structured3D dataset, demonstrating accurate occupancy prediction and superior performance in anticipating unseen scene geometry.
  arXiv  Detail & Related papers  (2025-04-22T17:38:38Z)
• Benchmarking Online Object Trackers for Underwater Robot Position Locking Applications [0.9642500063568189]
  Vision-based underwater robot navigation and control has recently gained increasing attention to counter the numerous challenges faced in underwater conditions.<n>In this paper, we propose a first rigorous unified benchmarking of more than seven Machine Learning (ML)-based one-shot object tracking algorithms for vision-based position locking of ROV platforms.<n>Our proposed system uses the output result of different object tracking algorithms to automatically correct the position of the ROV against external disturbances.
  arXiv  Detail & Related papers  (2025-02-23T13:27:34Z)
• ODYSSEE: Oyster Detection Yielded by Sensor Systems on Edge Electronics [14.935296890629795]
  Oysters are a vital keystone species in coastal ecosystems, providing significant economic, environmental, and cultural benefits.<n>Current monitoring strategies often rely on destructive methods.<n>We propose a novel pipeline using stable diffusion to augment a collected real dataset with realistic synthetic data.
  arXiv  Detail & Related papers  (2024-09-11T04:31:09Z)
• CoNav: A Benchmark for Human-Centered Collaborative Navigation [66.6268966718022]
  We propose a collaborative navigation (CoNav) benchmark. Our CoNav tackles the critical challenge of constructing a 3D navigation environment with realistic and diverse human activities. We propose an intention-aware agent for reasoning both long-term and short-term human intention.
  arXiv  Detail & Related papers  (2024-06-04T15:44:25Z)
• ORBSLAM3-Enhanced Autonomous Toy Drones: Pioneering Indoor Exploration [30.334482597992455]
  Navigating toy drones through uncharted GPS-denied indoor spaces poses significant difficulties. We introduce a real-time autonomous indoor exploration system tailored for drones equipped with a monocular emphRGB camera. Our system utilizes emphORB-SLAM3, a state-of-the-art vision feature-based SLAM, to handle both the localization of toy drones and the mapping of unmapped indoor terrains.
  arXiv  Detail & Related papers  (2023-12-20T19:20:26Z)
• Aeolus Ocean -- A simulation environment for the autonomous COLREG-compliant navigation of Unmanned Surface Vehicles using Deep Reinforcement Learning and Maritime Object Detection [0.0]
  navigational autonomy in unmanned surface vehicles (USVs) in the maritime sector can lead to safer waters as well as reduced operating costs. We describe the novel development of a COLREG-compliant DRL-based collision avoidant navigational system with CV-based awareness in a realistic ocean simulation environment.
  arXiv  Detail & Related papers  (2023-07-13T11:20:18Z)
• Semi-Supervised Visual Tracking of Marine Animals using Autonomous Underwater Vehicles [0.40498500266986387]
  In-situ visual observations of marine organisms is crucial to developing behavioural understandings and their relations to their surrounding ecosystem. Recently, autonomous underwater vehicles equipped with cameras and embedded computers with GPU capabilities are being developed for a variety of applications. Semi-supervised tracking algorithms may offer alternative tracking solutions because they require less data than fully-supervised counterparts.
  arXiv  Detail & Related papers  (2023-02-14T21:08:52Z)
• Online Stochastic Variational Gaussian Process Mapping for Large-Scale SLAM in Real Time [1.3387004254920498]
  AUVs are becoming standard tools for underwater exploration and seabed mapping in both scientific and industrial applications. Their capacity to dive untethered allows them to reach areas inaccessible to surface vessels and to collect data more closely to the seafloor. navigation autonomy remains bounded by the accuracy of their dead reckoning (DR) estimate of their global position, severely limited in the absence of a priori maps of the area and GPS signal.
  arXiv  Detail & Related papers  (2022-11-10T14:21:48Z)
• Occupancy Anticipation for Efficient Exploration and Navigation [97.17517060585875]
  We propose occupancy anticipation, where the agent uses its egocentric RGB-D observations to infer the occupancy state beyond the visible regions. By exploiting context in both the egocentric views and top-down maps our model successfully anticipates a broader map of the environment. Our approach is the winning entry in the 2020 Habitat PointNav Challenge.
  arXiv  Detail & Related papers  (2020-08-21T03:16:51Z)
• Active Visual Information Gathering for Vision-Language Navigation [115.40768457718325]
  Vision-language navigation (VLN) is the task of entailing an agent to carry out navigational instructions inside photo-realistic environments. One of the key challenges in VLN is how to conduct a robust navigation by mitigating the uncertainty caused by ambiguous instructions and insufficient observation of the environment. This work draws inspiration from human navigation behavior and endows an agent with an active information gathering ability for a more intelligent VLN policy.
  arXiv  Detail & Related papers  (2020-07-15T23:54:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.