Safe Navigation Research Articles

Issues of organizing vessels pilotage through the drawbridges spans in St. Petersburg

The topic of the work is an overview study of the current problem associated with the complexity of navigation of river vessels and river-sea-going vessels during their passage along the Neva River in the raised spans of St. Petersburg bridges. It is noted that when passing through the raised spans of St. Petersburg bridges in the induced state, such factor as the “surface dimension” is one of the main ones. It is emphasized that large-tonnage river and river-sea-going vessels cannot pass all the bridges of St. Petersburg when they are in the induced state, but since the bridges are drawn at night during navigation period, the height restriction is no longer so strict. Unfortunately, all bridges of St. Petersburg have only one draw span, so reverse navigation is organized through their raised spans in order, firstly, to avoid divergences of vessels in the sections between the bridges and, secondly, to enable the skipper to minimize manoeuvring when choosing the optimal path of entry into the raised span of the bridge. In addition, the attention is drawn to the fact that when entering the drawbridge span, the skipper must take into account many additional factors, including, for example, local navigation features, the actual hydro-meteorological situation and the current hydrological regime of the Neva River. It is noted in the study that the boatmaster should take into account such an important circumstance as the presence of a large number of pleasure craft used for sightseeing viewing of the process of vessel movement through the raised spans of bridges. Due to the fact that boatmasters of large-tonnage river vessels and river-sea-going vessels may experience significant difficulties in the process of organizing navigation safety when moving into the raised bridge spans on the Neva River section within the boundaries of St. Petersburg; mandatory pilotage, some features of the organization of which are considered in this work, has been established. Examples of accidents related to the procedure of bridges drawing that occurred within the boundaries of St. Petersburg and had serious consequences are analyzed. The amendments proposed to be made to the “Rules of movement and mooring of vessels in the Volga-Baltic basin of the inland waterways of the Russian Federation” in relation to the issue under consideration are considered.

Path-following control problem for maritime autonomous surface ships (MASS) in adverse weather conditions at low speeds

With the increasing popularity of autonomous vehicles, the maritime industry has focused on the development of Maritime Autonomous Surface Ships (MASS). An essential aspect of autonomous ships is their ability to follow a predetermined path at sea, as deviations from this path can jeopardize navigational safety, leading to accidents like collisions and grounding incidents. Therefore, ensuring that autonomous ships can safely navigate by following predefined routes is of utmost importance. Simultaneously, the implementation of the Energy Efficiency Design Index (EEDI) by the International Maritime Organization (IMO) has raised interest in a ship's manoeuvring performance in adverse sea conditions, aiming to reduce greenhouse gas emissions. The Marine Environment Protection Committee (MEPC) has provided guidelines to determine the minimum propulsion power required to maintain ship manoeuvrability in adverse conditions. This study investigates the path-following performance of a ship operating at low forward speeds in adverse weather conditions using a free-running Computational Fluid Dynamics (CFD) model, enabling accurate prediction of manoeuvring behaviour. The numerical results emphasise the significance of low forward speeds in enabling a ship to follow a predetermined route, offering valuable insights into path-following performance with minimum propulsion power in adverse weather. The study reveals that increasing propulsive power reduces deviations from the predetermined route when the ship encounters bow and beam waves. However, the impact of propulsion power on deviation is negligible in quartering waves during path-following control. This research contributes to improving guidelines for minimum ship powering, ensuring safe autonomous navigation in adverse weather conditions.

Spacecraft environmental path planning method based on improved artificial potential field

Spacecraft is the primary means of transportation for human exploration of outer space. With the advancement of science and technology, existing space exploration can no longer satisfy people's desire to explore, in the future, further and deeper space exploration is the goal of development. And the safety of spacecraft navigation in space requires the development of a path planning system. Although there have been many kinds of methods for path planning at this stage, all of them have their strengths and specialize in planning directions, but they also have defects. Based on this, this study improves the traditional artificial potential field method, by adjusting its repulsive field calculation and combining it with the RRT algorithm. The improved method can avoid the local minimum problem of the traditional artificial potential field and generate paths to meet the requirements of spacecraft. The effectiveness of the algorithm is verified by simulation experimental results.

TTMRN: A topological-geometric two-layer maritime route network modeling for ship intelligent navigation

The construction of maritime route networks holds significant importance for autonomous navigation of vessels. In this study, a two-layer maritime route network modeling method based on huge amounts of ship trajectory data was proposed. Firstly, we introduce a novel method for extracting nodes of the marine route network, which identifies feature points in ship trajectories through clustering. Secondly, we use a spatial computing method to transform ship trajectory data into a sequence of waypoint regions and establish a node connection matrix to realize the nodes' connection of the topological layer route network. And routes are extracted between waypoint regions to characterize the connection relationship of the geometric layer network. Finally, by connecting nodes of the topological layer with the support of the connection matrix and waypoint regions of the geometric layer with the route, the two-layer maritime route network that combines topological and geometric layers is constructed. The proposed method was applied to the waters of Vancouver, successfully constructing a topological-geometric two-layer maritime route network. Overall, the proposed method is beneficial for improving the safety and efficiency of autonomous navigation of ships, and has a positive impact on the development of smart shipping industry.

Distributed Control for Multi-Robot Interactive Swarming Using Voronoi Partioning

The problem of safe navigation of a human-multi-robot system is addressed in this paper. More precisely, we propose a novel distributed algorithm to control a swarm of unmanned ground robots interacting with human operators in presence of obstacles. Contrary to many existing algorithms that consider formation control, the proposed approach results in non-rigid motion for the swarm, which more easily enables interactions with human operators and navigation in cluttered environments. Each vehicle calculates distributively and dynamically its own safety zone in which it generates a reference point to be tracked. The algorithm relies on purely geometric reasoning through the use of Voronoi partitioning and collision cones, which allows to naturally account for inter-robot, human-robot and robot-obstacle interactions. Different interaction modes have been defined from this common basis to address the following practical problems: autonomous waypoint navigation, velocity-guided motion, and follow a localized operator. The effectiveness of the algorithm is illustrated by outdoor and indoor field experiments.

Deployment of Remote Sensing Technologies for Effective Traffic Monitoring

A rising volume of vessel traffic increases navigation density, which leads to an increasing risk of vessel collisions in navigation channels. Navigation safety issues have been widely studied with the aim of reducing such collisions. Intelligent navigation channels, which involve deploying remote-sensing radars on buoys, are an effective method of tackling vessel collisions. This paper investigates the problem of radar deployment in navigation channels, aiming to expand the radar coverage area and effectively detect vessel locations. A mixed-integer linear programming model is formulated to determine the optimal deployment of radars in navigation channels under a given budget, where radars with different coverage radii and different types of buoys are introduced. Then, sensitivity analyses involving the impacts of budgets, the coverage radii of the radars, the distance between adjacent discrete locations, and the distribution of the existing buoys on the radar deployment plan are conducted. The computational results indicate that the coverage ratio of the navigation channel can be improved by reasonably deploying the different types of radars on the existing and new buoys under a given budget.

Autonomous navigation and indoor mapping for a service robot

Abstract
 Objective: Simultaneous Localization and Mapping (SLAM) is a quite common and interesting problem in mobile robotics. It is the basis of safe autonomous navigation of mobile robots and the entrance to new combined applications with a manipulator for instance. Method: In order to find a solution to the SLAM problem, the ROS middleware and the MRPT were selected. Autonomous navigation was tested using two methods, the MRPT navigation ROS package, which is a reactive navigation method based on Trajectory Parameter Space (TP-Space) transformations, and the ROS navigation stack, a standard for differential drive and holonomic wheeled robots. Results: To validate the advantages and disadvantages of both approaches, a mobile robot with strong kinematic constraints (Ackermann-steering-type) known as Summit was used. As an additional work, an application using the mobile robot Summit and a robotic manipulator (Powerball) was carried out, with the intention of picking and placing objects of the mobile robot, a widely spread application among service robotics, especially, in the area of industrial logistics. Conclusions: Finally, it is concluded that with the tests carried out with the robot, it was possible to demonstrate autonomous navigation, using the two mentioned methods.

Dynamic analysis of pilot transfer accidents

Marine pilot is the person who expert on a specific region and guide the ship masters for safe navigation. Pilot transfer (PT) operation is a process of embarkation or disembarkation of pilots from pilot boat to ship or viceverca which is very risky operation and accidents even cause death of the pilots sometimes happen. The nature of the operation require pilots transfer between two movement vessel relatively in open sea conditions expose to different weather environment along day and night. Given the dearth of international research on pilot transfer operations, this study seeks to combine fault tree analysis with bayesian network analysis using a fuzzy technique in order to analyze accidents that occur during pilot transfer operations. When first investigating the root causes and causal chain of the PT accidents, fault tree analysis (FTA) was used. The probability of crucial occurrences are often cloudy, but experts' judgment and imprecise ideas can help. A Bayesian network (BN) mapping is made to get around the problems caused by FTA's conditional dependencies and lack of flexibility. Sensitivity analysis is used to help BN simulate the analysis using the entire operating procedure. The study's findings highlighted the root nodes “poor condition of pilot ladder”, “lack of safety culture”, “adverse sea/swell” and “securing failure of pilot ladder on deck” as major contributors to PT accidents. The results show that the study's methodology is sound and practical, and that adding FTA-BN to an analysis of PT accidents will make a substantial contribution to the literature.

PROCESSING OF INDICATOR DIAGRAM IN THE TASKS OF CONSTRUCTING DIGITAL PROFILES OF THE WORKING PROCESS OF SHIP ENGINES

During the operation of marine internal combustion engines, the procedure for indicating the working process in certain operating modes is widely used, followed by an analysis of indicator diagrams and a comparison of the results obtained with the reference ones obtained during engine factory tests. However, the general trend in the world fleet towards a decrease in the commercial speeds of ships, on the one hand, and the use of tight traffic schedules, on the other hand, have led to the fact that in most cases it is impossible to carry out indexing according to the procedures prescribed in the rules for the technical operation of engines. Thus, the ability of maintenance personnel to objectively assess the current technical condition of the engine is lost, and to determine the necessary list of preventive measures for maintenance and repair, which, of course, affects the efficiency of engines and the safety of navigation in general. One of the effective ways to solve this problem is the use of digital profiles of engine work processes, which characterize their work in the entire range of operating modes. With the help of a digital profile, it is possible to obtain a calculated reference indicator diagram, which can be used for comparison with the one obtained during the planned indication of the engine in any mode of its operation. As a basis for building digital profiles, it is appropriate to use the results of acceptance test bench tests of the engine by the manufacturer. However, taking into account the rather long service life of marine engines, test reports usually exist only in a raster format, which greatly complicates the processing of the indication results given in them, which, most often, was performed using mechanical indicators. To use this information to build digital profiles, the authors proposed a method for processing such indicator diagrams, described in previous articles. However, the efficiency of generating digital profiles significantly depends on the quality of the basic diagrams on which these profiles are built. This article is devoted to the processing of such diagrams.

Risk-Sensitive Markov Decision Processes of USV Trajectory Planning with Time-Limited Budget.

Trajectory planning plays a crucial role in ensuring the safe navigation of ships, as it involves complex decision making influenced by various factors. This paper presents a heuristic algorithm, named the Markov decision process Heuristic Algorithm (MHA), for time-optimized avoidance of Unmanned Surface Vehicles (USVs) based on a Risk-Sensitive Markov decision process model. The proposed method utilizes the Risk-Sensitive Markov decision process model to generate a set of states within the USV collision avoidance search space. These states are determined based on the reachable locations and directions considering the time cost associated with the set of actions. By incorporating an enhanced reward function and a constraint time-dependent cost function, the USV can effectively plan practical motion paths that align with its actual time constraints. Experimental results demonstrate that the MHA algorithm enables decision makers to evaluate the trade-off between the budget and the probability of achieving the goal within the given budget. Moreover, the local stochastic optimization criterion assists the agent in selecting collision avoidance paths without significantly increasing the risk of collision.

A novel intelligent collision avoidance algorithm based on deep reinforcement learning approach for USV

Enhancing the efficiency of unmanned surface vehicles (USVs) collision avoidance can yield a significant impact, as it can result in safer navigation and lower energy consumption. This paper introduces a robust approach employing deep reinforcement learning theory to facilitate informed collision avoidance decisions within intricate maritime environments. The restrictions on USV maneuverability and international regulations for preventing collisions at sea are studied and quantified, particularly focusing on the shape and size changes of the ship’s domain caused by USV speed. Based on the deep Q network, an improved methodology is designed, incorporating a noisy network, prioritized experience replay, dueling neural network architecture, and double Q learning, resulting in a highly efficient sampling, exploration, and learning process. To curtail computational expenses associated with USVs, a novel dynamic area restriction technique is proposed. Furthermore, an innovative USV state clipping method is introduced to mitigate training complexities. By utilizing the Unity platform, a virtual environment characterized by complexity and stochasticity is constructed for training and testing the collision avoidance of USVs This novel approach surpasses the performance of the pre-improvement algorithm across multiple collision avoidance effectiveness indicators and performance metrics.

Multi-Sensors System and Deep Learning Models for Object Tracking.

Autonomous navigation relies on the crucial aspect of perceiving the environment to ensure the safe navigation of an autonomous platform, taking into consideration surrounding objects and their potential movements. Consequently, a fundamental requirement arises to accurately track and predict these objects' trajectories. Three deep recurrent network architectures were defined to achieve this, fine-tuning their weights to optimize the tracking process. The effectiveness of this proposed pipeline has been assessed, with diverse tracking scenarios demonstrated in both sub-urban and highway environments. The evaluations have yielded promising results, affirming the potential of this approach in enhancing autonomous navigation capabilities.

Analysing human error contribution to ship collision risk in congested waters under the evidential reasoning SPAR-H extended fault tree analysis

Human error plays a crucial role in maritime transportation risk analysis, as a significant percentage of accidents, including collisions, groundings, capsizing, fires, and explosions, can be attributed to human errors. However, obtaining a dataset that quantifies human error probabilities for maritime risk analysis is challenging due to commercial constraints. To address this issue, this paper proposes a conceptual framework that integrates evidential reasoning (ER) and the standardized plant analysis risk-human reliability analysis (SPAR-H) method to quantify human errors, while employing fault tree analysis (FTA) to predict risk. The specific focus of this study is ship collision risk in congested waters, which serves as a demonstration case to showcase the proposed method and illustrate a detailed analysis of collision risk. The findings reveal that “inadequate watchkeeping due to sole lookout”, “improper RADAR monitoring”, and “ineffective execution of COLREG-related actions” are the most significant human errors contributing to collision risk in congested waters. The outcomes of this research provide valuable insights for ship owners, safety professionals, ship masters, inspectors, and researchers in the maritime industry. The findings can assist in minimizing collision risk and improving navigational safety in congested waters.

Pyramidal 3D feature fusion on polar grids for fast and robust traversability analysis on CPU

Self-driving vehicles and autonomous ground robots require a reliable and accurate method to analyze the traversability of the surrounding environment for safe navigation. This paper proposes and evaluates a real-time machine learning-based traversability analysis method that combines geometric features with a pyramid-polar space representation based on SVM classifiers. In particular, we show that by fusing geometric features with information stemming from coarser pyramid levels that account for a broader space portion, as well as integrating important implementation details, allows for a noticeable boost in performance and reliability. The main goal of this work is to demonstrate that traversability analysis is possible with effective results and in real-time even on cheaper hardware than expensive GPUs, e.g. CPU-only PCs. The proposed approach has been compared with state-of-the-art deep learning approaches on publicly available datasets of outdoor driving scenarios, running such algorithms both on GPU and CPU to compare runtimes. Our method can be fully executed on CPU and achieves results close to the best-in-class methods, runs faster, and requires fewer and less expensive hardware resources, consuming less than 30% electrical power with respect to deep learning models on embedded processing units. We release with this paper the open-source implementation of our method.

A wearable assistive system for the visually impaired using object detection, distance measurement and tactile presentation

With the current development of society, ensuring traffic and walking safety for the visually impaired is becoming increasingly important. We propose a wearable system based on a system previously developed by us that uses object recognition, a distance measurement function, and the corresponding vibration pattern presentation to support the mobility of the visually impaired. The system recognizes obstacles in front of a user in real time, measures their distances, processes the information, and then presents safety actions through vibration patterns from a tactile glove woven with shape memory alloy (SMA) actuators. The deep learning model is compressed to achieve real-time recognition using a microcomputer while maintaining recognition accuracy. Measurements of the distances to multiple objects are realized using a stereo camera, and vibration patterns are presented through a tactile glove in response to these distances. Experiments are conducted to verify the system performance to provide safe navigation depending on the positions and the distances of multiple obstacles in front of the user.

GPU-Accelerated Interaction-Aware Motion Prediction

Before their massive deployment, autonomous vehicles need to prove in complex scenarios such that they can reach human driving proficiency while guaranteeing higher safety levels. One of the most important human traits to negotiating traffic is the ability to predict the future behavior of surrounding vehicles as a basis for agile and safe navigation. This capability is particularly challenging for an autonomous system in highly interactive driving situations, such as intersections or roundabouts. In this paper, a set of techniques to bring a computationally expensive state-of-the-art motion prediction algorithm to real-time execution are presented with the goal of meeting a standard motion-planning algorithm execution frequency of 5 Hz, which is the primary consumer of motion predictions. This is achieved by applying novel and existing parallelization algorithms that take advantage of graphic processing units (GPUs) through the compute unified device architecture (CUDA) programming language and managing to produce an average 5× speedup over raw C++ in the cases studied. The optimizations are then evaluated in public datasets and a real vehicle on a test track.

Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions

ABSTRACT Due to the growing volume of remote sensing data and the low latency required for safe marine navigation, machine learning (ML) algorithms are being developed to accelerate sea ice chart generation, currently a manual interpretation task. However, the low signal-to-noise ratio of the freely available Sentinel-1 Synthetic Aperture Radar (SAR) imagery, the ambiguity of backscatter signals for ice types, and the scarcity of open-source high-resolution labelled data makes automating sea ice mapping challenging. We use Extreme Earth version 2, a high-resolution benchmark dataset generated for ML training and evaluation, to investigate the effectiveness of ML for automated sea ice mapping. Our customized pipeline combines ResNets and Atrous Spatial Pyramid Pooling for SAR image segmentation. We investigate the performance of our model for: i) binary classification of sea ice and open water in a segmentation framework; and ii) a multiclass segmentation of five sea ice types. For binary ice-water classification, models trained with our largest training set have weighted F1 scores all greater than 0.95 for January and July test scenes. Specifically, the median weighted F1 score was 0.98, indicating high performance for both months. By comparison, a competitive baseline U-Net has a weighted average F1 score of ranging from 0.92 to 0.94 (median 0.93) for July, and 0.97 to 0.98 (median 0.97) for January. Multiclass ice type classification is more challenging, and even though our models achieve 2% improvement in weighted F1 average compared to the baseline U-Net, test weighted F1 is generally between 0.6 and 0.80. Our approach can efficiently segment full SAR scenes in one run, is faster than the baseline U-Net, retains spatial resolution and dimension, and is more robust against noise compared to approaches that rely on patch classification.

WIND AND WAVE TRAINED ARTIFICIAL NEURAL NETWORKS FOR THE FORECASTING OF WAVE CLIMATE IN HARBOUR AREA

Nowadays, maritime transportation has expanded rapidly, involving the need to enhance several navigation-related issues, particularly concerning the safety of navigation, which is significantly impacted by weather conditions. In this regard, creating a wave forecasting system could facilitate vessel movement at the harbour entrance or inside the sheltered area. Wave characteristics are usually estimated using numerical models, which generally require high computational costs, making them inadequate for nowcasting and forecasting wave climate. The current study describes the implementation of a forecasting methodology for the port area of Augusta (Sicily) based on an Artificial Neural Network (ANN) that attempts to deliver a trustworthy response and the numerical model but with a significant reduction in the computational time.

Safe Navigation and Obstacle Avoidance Using Differentiable Optimization Based Control Barrier Functions

Safe Navigation and Obstacle Avoidance Using Differentiable Optimization Based Control Barrier Functions

Potential of marine organic waste: chemical characteristics of compost from marine organic waste Kuala Indah Beach, North Sumatra

Marine debris was a direct threat to marine habitats, human health, and navigational safety, resulting in serious socio-economic losses. Marine organic waste management can be done by turning it into compost that can be used as a nutrient addition. It can also be used as a solution to be diminished marine waste considering that the sea had many roles to support the lives of living things and maintain ecosystems. This study aimed to examined some characteristics of compost from marine organic waste and gave information on waste management for sustainable agriculture. This study was carried out at Kuala Indah Beach, Sei Suka District, Batu Bara Regency, Indonesia. The composting process was carried out at the Faculty of Agriculture, Universitas Sumatera Utara. The analysis was carried out at the Research and Technology Laboratory of the Faculty of Agriculture, Universitas Sumatera Utara. The composting process used the Berkeley method with the addition of EM4. The results showed that the chemical characteristics of marine organic waste compost by Indonesian National Standard (SNI 19-7030-2004) with a macronutrient content of 2.40% Nitrogen; Phosphorus 0.53%; and Potassium 0.45% with a pH of 6.95 (neutral) and a compost C/N ratio of 17.33.