New framework models AUV maneuvering using sea-trial data

Researchers have developed a new differentiable composite approximation framework for modeling autonomous underwater vehicle (AUV) maneuvering using sea-trial data. This framework jointly calibrates a polynomial-basis component and a data-adaptive basis component, allowing for more accurate predictions of AUV behavior. A gradient-based co-calibration method with a sensitivity-aware mechanism and a neural residual component is used for prediction. The system also incorporates a procedure to estimate and compensate for ocean-current effects, improving the learning targets. Evaluations using sea-trial data from a 7-meter AUV demonstrated improved trajectory and velocity prediction compared to existing methods. AI

IMPACT This framework could improve the accuracy and efficiency of autonomous underwater vehicle operations by enabling better real-time modeling and prediction.

RANK_REASON The item is an academic paper detailing a new framework for AUV maneuvering modeling. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• autonomous underwater vehicle
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• cs.LG
• cs.RO
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →