CAVE-NAV: VLM-Based Autonomous 3D Navigation in Underwater Cave Environments

• URL: http://arxiv.org/abs/2608.27793v1
• Date: Fri, 28 Aug 2026 00:16:09 GMT
• Title: CAVE-NAV: VLM-Based Autonomous 3D Navigation in Underwater Cave Environments
• Abstract summary: We propose a vision-language model (VLM) with Chain-of-Thought (CoT) reasoning to infer navigable directions from environmental cues.<n>High-fidelity simulations across multiple cave topologies demonstrate that the proposed framework completes all evaluations without collisions.
• Score: 11.084602981881767
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous navigation in underwater cave environments is essential for search-and-rescue operations, scientific exploration, and emergency egress. Traditional navigation systems commonly depend on dense visual features for localization and mapping. In underwater caves, however, visual degradation can undermine feature-based localization, sonar-based mapping may yield overly conservative obstacle representations, and communication constraints preclude real-time human guidance. To address these limitations, we propose an autonomous underwater cave navigation framework that leverages a vision-language model (VLM) with Chain-of-Thought (CoT) reasoning to infer navigable directions from environmental cues, including light intensity gradients, passage morphology, and geometric complexity, captured through multimodal inputs comprising RGB imagery, depth maps, and sonar-based vertical-clearance measurements, thereby supporting safe 3D navigation through confined cave passages. High-fidelity simulations across multiple cave topologies demonstrate that the proposed framework completes all evaluated end-to-end traversals without collisions while maintaining safe clearance from cave boundaries.

Related papers

• SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning [59.64305326980364]
  SpaceVLN is a navigation agent built around Spatial Cognitive Memory and Task-Guided Spatial Reasoning.<n>Built on this memory, Spatial-CoT integrates task-progress reasoning with spatial perception, analysis, and prediction.<n>Across R2R-CE, RxR-CE, GN-Bench, and HM3D-OVON, SpaceVLN achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2026-06-08T03:42:08Z)
• An Open-Source LiDAR and Monocular Off-Road Autonomous Navigation Stack [35.094251140860756]
  We present an open-source navigation stack supporting both LiDAR and monocular 3D perception without task-specific training.<n>For the monocular setup, we combine zero-shot depth prediction with metric depth rescaling using sparse SLAM measurements.<n>The resulting point cloud is used to generate a robot-centric 2.5D elevation map for costmap-based planning.
  arXiv  Detail & Related papers  (2026-04-03T15:19:20Z)
• OpenFrontier: General Navigation with Visual-Language Grounded Frontiers [54.661157616245966]
  Open-world navigation requires robots to make decisions in complex everyday environments.<n>Recent advances in vision--language navigation (VLN) and vision--language--action (VLA) models enable end-to-end policies conditioned on natural language.<n>We propose OpenFrontier, a training-free navigation framework that seamlessly integrates diverse vision--language prior models.
  arXiv  Detail & Related papers  (2026-03-05T17:02:22Z)
• WildOS: Open-Vocabulary Object Search in the Wild [12.098091049832965]
  This work presents WildOS, a unified system for long-range, open-vocabulary object search.<n>We use a foundation-model-based vision module, ExploRFM, to score frontier nodes of the graph.<n>We also introduce a particle-filter-based method for coarse localization of the open-vocabulary target query.
  arXiv  Detail & Related papers  (2026-02-22T19:14:00Z)
• TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals [10.69725316052444]
  We present a novel RGB-only, object-level topometric navigation pipeline that enables zero-shot, long-horizon robot navigation.<n>Our approach integrates global topological path planning with local metric trajectory control, allowing the robot to navigate towards object-level sub-goals while avoiding obstacles.<n>We demonstrate the effectiveness of our method in both simulated environments and real-world tests, highlighting its robustness and deployability.
  arXiv  Detail & Related papers  (2025-09-10T15:43:32Z)
• DUViN: Diffusion-Based Underwater Visual Navigation via Knowledge-Transferred Depth Features [47.88998580611257]
  We propose a Diffusion-based Underwater Visual Navigation policy via knowledge-transferred depth features, named DUViN.<n>DuViN guides the vehicle to avoid obstacles and maintain a safe and perception awareness altitude relative to the terrain without relying on pre-built maps.<n> Experiments in both simulated and real-world underwater environments demonstrate the effectiveness and generalization of our approach.
  arXiv  Detail & Related papers  (2025-09-03T03:43:12Z)
• Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation [54.04601077224252]
  Embodied scene understanding requires not only comprehending visual-spatial information but also determining where to explore next in the 3D physical world.<n>underlinetextbf3D vision-language learning enables embodied agents to effectively explore and understand their environment.<n>model's versatility enables navigation using diverse input modalities, including categories, language descriptions, and reference images.
  arXiv  Detail & Related papers  (2025-07-05T14:15:52Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• 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)
• CaveSeg: Deep Semantic Segmentation and Scene Parsing for Autonomous Underwater Cave Exploration [0.0]
  We present CaveSeg - the first visual learning pipeline for semantic segmentation and scene parsing for AUV navigation inside underwater caves. It contains pixel annotations for important navigation markers (e.g. caveline, arrows), obstacles (e.g. ground plane and overhead layers), scuba divers, and open areas for servoing.
  arXiv  Detail & Related papers  (2023-09-20T03:36:22Z)

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.