Multimodal and Multiview Deep Fusion for Autonomous Marine Navigation
This addresses the challenge of safer autonomous navigation for marine vessels, though it appears incremental as it builds on existing multimodal fusion techniques.
The paper tackles the problem of autonomous marine navigation by proposing a cross-attention transformer method for multimodal sensor fusion, resulting in improved navigational accuracy and robustness, as confirmed by real-world sea trials in adverse weather and complex maritime settings.
We propose a cross attention transformer based method for multimodal sensor fusion to build a birds eye view of a vessels surroundings supporting safer autonomous marine navigation. The model deeply fuses multiview RGB and long wave infrared images with sparse LiDAR point clouds. Training also integrates X band radar and electronic chart data to inform predictions. The resulting view provides a detailed reliable scene representation improving navigational accuracy and robustness. Real world sea trials confirm the methods effectiveness even in adverse weather and complex maritime settings.