Accurate and real-time environmental perception is essential for the safe and efficient execution of deep-sea mining operations. Semantic segmentation of forward-looking sonar (FLS) images plays a pivotal role in enabling environmental awareness for deep-sea mining vehicles (DSMVs), but remains challenging due to strong acoustic noise, blurred object boundaries, and long-range semantic dependencies. To address these issues, this study proposes DSM-Seg, a novel hybrid segmentation architecture combining Convolutional Neural Networks (CNNs) and Receptance Weighted Key-Value (RWKV) modeling. The architecture integrates a Physical Prior-Based Semantic Guidance Module (PSGM), which utilizes sonar-specific physical priors to produce high-confidence semantic guidance maps, thereby enhancing the delineation of target boundaries. In addition, a RWKV-Based Global Fusion with Semantic Constraints (RGFSC) module is introduced to suppress cross-regional interference in long-range dependency modeling and achieve the effective fusion of local and global semantic information. Extensive experiments on both a self-collected seabed terrain dataset and a public marine debris dataset demonstrate that DSM-Seg significantly improves segmentation accuracy under complex conditions while satisfying real-time performance requirements. These results highlight the potential of the proposed method to support intelligent environmental perception in DSMV applications.
With the increasing significance of deep-sea resource development, Forward-Looking Sonar (FLS) has become an essential technology for real-time environmental mapping and navigation in deep-sea mining vehicles (DSMV). However, FLS images often suffer from a limited field of view, uneven imaging, and complex noise sources, making single-frame images insufficient for providing continuous and complete environmental awareness. Existing mosaicking methods typically rely on external sensors or controlled laboratory conditions, often failing to account for the high levels of uncertainty and error inherent in real deep-sea environments. Consequently, their performance during sea trials tends to be unsatisfactory. To address these challenges, this study introduces a robust FLS image mosaicking framework that functions without additional sensor input. The framework explicitly models the noise characteristics of sonar images captured in deep-sea environments and integrates bidirectional cyclic consistency filtering with a soft-weighted feature refinement strategy during the feature-matching stage. For image fusion, a radial adaptive fusion algorithm with a protective frame is proposed to improve edge transitions and preserve structural consistency in the resulting panoramic image. The experimental results demonstrate that the proposed framework achieves high robustness and accuracy under real deep-sea conditions, effectively supporting DSMV tasks such as path planning, obstacle avoidance, and simultaneous localization and mapping (SLAM), thus enabling reliable perceptual capabilities for intelligent underwater operations.
Underwater robots require fast and accurate localization results during challenging near-bottom operations. However, commonly used methods such as acoustic baseline localization, dead reckoning, and sensor fusion have limited accuracy. The use of forward-looking sonar (FLS) images to observe the seabed environment for pose estimation has gained significant traction in recent years. This paper proposes a lightweight front-end FLS odometry to provide consistent and accurate localization for underwater robots. The proposed direct FLS odometry (DFLSO) includes several key innovations that realize the extraction of point clouds from FLS images and both image-to-image and image-to-map matching. First, an image processing method is designed to rapidly generate a 3-D point cloud of the seabed using FLS image, enabling pose estimation through point cloud matching. Second, a lightweight keyframe system is designed to construct point cloud submaps, which utilize historical information to enhance global pose consistency and reduce the accumulation of image-matching errors. The proposed odometry algorithm is validated by both simulation experiments and field data from sea trials.
To address sustained deviation from coverage lanes when an unmanned surface vehicle (USV) executes a complete boustrophedon coverage path under current disturbances, this study proposes an adaptive current-aware line-of-sight (ACA-LOS) guidance method based on online current estimation. The local current is estimated online from the kinematic velocity relationship between the USV and the surrounding water, and its path-normal component is extracted. The estimated path-normal current is used both to construct a current-compensating heading correction and, together with the cross-track error, to adjust the LOS lookahead distance and generate the desired ACA-LOS heading. Complete-path simulations are conducted under constant, time-varying, and spatially varying currents with different current speeds and directions. Relative to conventional LOS, ACA-LOS reduces the mean cross-track root mean square error (RMSE) by 40.80%, increases the tolerance-band compliance rate () by 27.48 percentage points, and reduces the cumulative cross-track deviation area () by 68.68%. ACA-LOS suppresses sustained lane deviation caused by current disturbances and improves lane keeping throughout complete boustrophedon path execution. The method supports the extension of USV operation from single-trajectory tracking to long-duration, continuous coverage execution and provides a reference for unmanned and intelligent waterborne operational equipment.