Underwater acoustic communication, characterized by limited bandwidth, high latency, and low reliability, poses significant challenges for data exchange in bathymetric collaborative simultaneous localization and mapping (CSLAM). In this paper, we introduce a novel vector quantization (VQ) method called ID(O) for mapping data compression in bathymetric CSLAM. ID(O) encodes the map into an index map ($\mathbb {I}$), a central depth map ($\mathbb {D}$), and an orientation map ($\mathbb {O}$). To accommodate strict communication constraints, orientations can be partially or fully excluded from transmission, and we propose a method to estimate these orientations during map restoration. Moreover, we integrate ID(O) within a feature-based bathymetric CSLAM framework named TTT CSLAM. Extensive experiments on two large-scale sea trial datasets demonstrate that ID(O) achieves about 40$\%$higher restoration accuracy than the baseline method using principal component analysis. TTT CSLAM with ID(O) can match that with lossless compression regarding mapping accuracy and efficiency, and it is robust against 40$\%$packet loss and large dead reckoning drift errors across diverse environments. To the best of our knowledge, ID(O) is the first VQ method for bathymetric data compression, and TTT CSLAM with ID(O) is the first bathymetric CSLAM tested within an underwater communication network employed by acoustic modems.

In this study, we introduce an innovative algorithm for enhanced navigational scene understanding in complex maritime environments by utilizing large language models (LLM) and visual language models (VLM) to achieve autonomous maritime situational awareness. The proposed algorithm interprets the meanings of various features and marks on detected objects in maritime contexts. By combining this information with radar and camera data, the algorithm generates cost maps for safe navigation. This approach offers two key benefits: (1) the ability to identify navigable areas considering obstacles, maritime marks, rules, and ship intentions, and (2) decision-making support based on reasoning, bridging the information gap between human operators and perception results. The performance of the proposed approach is demonstrated using a real-world dataset. The detailed information can be found at: https://yeongha-shin.github.io/vlmllm-maritime/

Abstract We introduce DBANet, a dual-branch aggregation network designed for efficient and real-time semantic segmentation of omnidirectional images in maritime environments. To support research and evaluation in this area, we also present the maritime omnidirectional semantic segmentation dataset, which fills the gap in maritime omnidirectional image segmentation. While omnidirectional vision systems are increasingly popular for their 360-degree perception capabilities, their large field of view imposes significant computational demands, and comprehensive evaluation methods for semantic segmentation in such scenarios remain limited. Our approach addresses these challenges by providing a robust and computationally efficient solution applicable to intelligent perception for maritime surface vehicles. Experimental results highlight the performance of DBANet, achieving 92.36 mIoU at 4.94 FPS on the MODSS dataset and 85.08 mIoU at 30.25 FPS on the MaSTr1325 dataset, outperforming state-of-the-art models in both accuracy and efficiency.

Determining the position of obstacles is crucial for unmanned vehicles, and, to achieve this, cameras and radar sensors are widely utilized. However, establishing correlation between two or more sensors proves challenging in the dynamically changing maritime environment. To solve these issues, we propose the AnytimeFusion algorithm. The key innovation of AnytimeFusion lies in the utilization of a parameter-free method that does not require accurate sensor alignment and calibration. The algorithm consists of the following four stages. First, calibration targets are selected in the maritime environment based on segmentation images. Second, radar and camera data are pre-fused to model the correlation of azimuth information. After completing the auto-calibration stages, Inverse Perspective Mapping (IPM) is employed to integrate the coordinate systems of the two sensors. To determine the parameters for this integration, optimization based on the Particle Swarm Optimization (PSO) method is employed. Finally, an Error Polygon for the positions of the camera and radar is generated, and sensor fusion is carried out based on this information. We validated our method through experiments conducted on real ships in complex maritime environments, achieving an average accuracy of 95.7%.

Ship collisions are major types of maritime accidents which may involve the loss of life and significant damage to property and the environment. Although many automatic ship collision avoidance algorithms have been suggested, most of them are only applicable to a single ship-to-ship encounter situation. Also, although there exist some studies on collision avoidance for multiple agent systems, maritime traffic rules have not been systematically incorporated in the algorithms which limit their practical applicability to real maritime traffic situations. In this study, we propose a rule-compliant automatic ship collision avoidance method that can be applied not only to single ship-to ship situations, but also to multiple-ship encounter situations with consideration of prediction uncertainty. In order to select appropriate evasive actions, a symmetric role-classification criterion is proposed by refining the current maritime traffic rules, and an efficient collision avoidance algorithm based on the probabilistic velocity obstacle method is applied. To verify and demonstrate the performance and practical utility of the proposed algorithm, Monte-Carlo simulations were conducted and the results are presented in this article.

This study addresses the problem of path optimization for conducting a mapping mission using a multi-robot system with limited sensing capability, which aims to ensure efficient mapping with emphasis on the cooperative aspect of the mission. To achieve the cooperative mapping, a new path planning algorithm is proposed which can take advantage of the multi-robot system while dealing with the lack of observability due to the nature of bearing-only or range-only sensing. The Fisher information matrix is used to estimate the mapping uncertainty affected by the robots’ geometric configuration. Also, a simple method to predict the convergence rate of the uncertainty over a short time horizon is presented for efficient path planning. The performance of the proposed algorithm is shown through simulations and compared with other path planning algorithms.

This paper addresses a vehicle localization method that fuses aerial maps and lidar data in urban canyon environments where global positioning system (GPS) signals are inaccurate. The boundaries of buildings are extracted from the aerial map and they are matched to point cloud data provided by the lidar. However, most aerial maps contain perspective projection distortions which can be significant in urban canyons with tall buildings. In this study, a new method to correct such projection distortion is proposed and it is applied to precise localization by fusing the corrected map and lidar data. In order to achieve this, the semantic segmentation of an aerial image is performed using a convolutional neural network, and the mutual information between the lidar measurements and the building boundaries is obtained to measure their similarity. A particle filter framework is employed to localize the vehicle and match the map using the mutual information as the weight of a particle. An experimental dataset is then used to validate the feasibility of the proposed method.

This paper addresses a computationally efficient approach to localization and mapping in an indoor parking garage in the context of simultaneous localization and mapping. A parameterized map-building approach is introduced and implemented to represent the surrounding structures using a small number of geometric parameters. These parameters are obtained from horizontally and vertically ordered 3D LIDAR measurements and incorporated into an online filter to simultaneously estimate the map parameters and localize the vehicle. This approach enables the high-precision navigation and memory-efficient map representation of an environment with man-made structures with no need of global positioning system or external position fixes. Driving experiments were performed in indoor parking garages to verify and demonstrate the performance of the proposed localization and mapping approach.

This paper proposes a method for jointly estimating road layout and segmenting urban scenes semantically by applying a relative location prior. The proposed method is based on the conjecture that some relevant elements in urban environments tend to be located in a predictable manner. This belief can be modeled as a location prior to help a segmentation algorithm infer latent labels in images more accurately. In order to apply these structural characteristics, a set of special coordinates, referred to as road-normal coordinates, are defined which are perpendicular to the road. These coordinates are determined by estimating the most fittable road layout based on a marginal probability obtained from an existing segmentation algorithm. All possible segments in an image are projected into the road-normal coordinates with the aid of depth information from sensor measurements, and the pre-trained location prior is applied to each segment as an additional potential of a conditional random field (CRF) model. The proposed method is evaluated on the publicly available KITTI dataset including images and corresponding 3D point clouds.

This paper addresses the issue of developing a robust and efficient controller for a manipulator for underwater applications by proposing a terminal sliding mode control scheme along with a disturbance observer and incorporating the same for 3-RRR serial spatial manipulator to ensure finite time convergence as asymptotic convergence in undesirable in underwater tasks like positioning and tracking of a trajectory. The performance of the proposed scheme is studied using extensive numerical simulations depicting practical circumstances with external disturbances and parameter uncertainties within the system. The capability of the control scheme to overcome hydrodynamic forces and moments including added mass effects, damping effects are extensively studied and validated for the control scheme. The dynamic modelling is done using the Euler-Lagrangian approach involving the energy associated with the system. The results are presented after analyzing the trajectory tracking capabilities of the manipulator in the presence of external disturbances and model uncertainties.

This study addresses three-dimensional (3D) reconstruction of bridge structures over water by fusing sensor measurements from inertial sensors, cameras and lidars mounted on an unmanned surface vehicle (USV). While the accurate navigation capability is strongly required for successful 3D reconstruction, global positioning system (GPS) signals which are essential for accurate navigation are severely deteriorated near the bridge structures or almost completely blocked underneath the bridge decks. In this study, a parameterized feature map is introduced by augmenting the map state with the geometric parameters of the detected bridge piers, and relative navigation is performed with respect to this map in the framework of simultaneous localization and mapping (SLAM). This parameterized SLAM approach allows for high-precision navigation and mapping with no need of GPS fixes. The feasibility of the proposed algorithm was demonstrated through field experiments.

Mobile underwater networks with acoustic communications are confronted with several unique challenges such as long propagation delays, high transmission power consumption, and node mobility. In particular, slow signal propagation permits multiple packets to concurrently travel in the underwater channel, which must be exploited to improve the overall throughput. To this end, we propose the delay-aware opportunistic transmission scheduling (DOTS) protocol that uses passively obtained local information (i.e., neighboring nodes' propagation delay map and their expected transmission schedules) to increase the chances of concurrent transmissions while reducing the likelihood of collisions. Our extensive simulation results document that DOTS outperforms existing solutions and provides fair medium access even with node mobility.