Organizations: Embodied Robotics and Automation Lab, University of South Florida, Tampa, FL 33620, USA · Computer Science Department, George Mason University, Fairfax, VA 22032, USA · Department of Mechanical Engineering, University of Maryland, College Park, MD 20742, USA · Naval Architecture and Ocean Engineering at the Seoul National University, Seoul 08826, South Korea
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.
Figures & tables
Fig. 1 : Real-world BlueROV operation in a representative underwater cave environment at Blue Grotto, Florida.
Fig. 2 : Overview of the proposed framework. Multimodal observations are rendered at each step, interpreted by a VLM under Chain-of-Thought prompting, and converted into a parameterized motion command that is applied directly to the vehicle pose.
Fig. 3 : Navigation trajectories in 5 simulated cave scenarios (S1–S5): first row is top-down views and second row is side views; orange: AUV trajectories.
Fig. 4 : VLM inference on a real image captured by a BlueROV2 at Blue Grotto
1ERA Lab, University of South Florida, Florida, USA · University of Maryland- College Park, College Park, Maryland · 2YES Lab, University of South Florida, Florida, USA
Susheel Vadakkekuruppath and Jason M. O’Kane are with the Department of Computer Science and Engineering, Texas A&M University, USA · Herman B. Amundsen and Marios Xanthidis are with the Aquaculture Robotics and Automation, SINTEF Ocean