Unmanned Surface Vehicle Navigation Research Articles

ROTracker: a novel MMW radar-based object tracking method for unmanned surface vehicle in offshore environments

Unmanned surface vehicles (USVs) offer significant value through their capability to undertake hazardous and time-consuming missions across water surfaces. Recently, as the application of USVs has been extended to nearshore waterways, object tracking is vital to the safe navigation of USVs in offshore scenes. However, existing tracking systems for USVs are mainly based on cameras or LiDAR sensors, which suffer from drawbacks such as lack of depth perception or high deployment costs. In contrast, millimeter-wave (MMW) radar offers advantages in terms of low cost and robustness in all weather and lighting conditions. In this work, to construct a robust and low-cost tracking system for USVs in complex offshore scenes, we propose a novel MMW radar-based object tracking method (ROTracker). The proposed ROTracker combines the physical properties of MMW radar with traditional tracking systems. Specifically, we introduce the radar Doppler velocity and a designed motion discriminator to improve the robustness of the tracking system toward low-speed targets. Moreover, we conducted real-world experiments to validate the efficacy of the proposed ROTracker. Compared to other baseline methods, ROTracker achieves excellent multiple object tracking accuracy in terms of 91.9% in our collected dataset. The experimental results demonstrated that the proposed ROTracker has significant application potential in both accuracy and efficiency for USVs, addressing the challenges posed by complex nearshore environments.

Design and Implementation of a Low-Cost Intelligent Unmanned Surface Vehicle

This article describes the design and construction journey of a self-developed unmanned surface vehicle (USV). In order to increase the accessibility and lower the barrier of entry we propose a low-cost (under EUR 1000) approach to the vessel construction with great adaptability and customizability. This design prioritizes minimal power consumption as a key objective. It focuses on elucidating the intricacies of both the design and assembly processes involved in creating an economical USV. Utilizing easily accessible components, the boat outlined in this study has been already participated in the 1st Aegean Ro-boat Race 2023 competition and is tailored for entry into similar robotic competitions. Its primary functionalities encompass autonomous sea navigation coupled with sophisticated collision avoidance capabilities. Finally, we studied reinforcement learning strategies for constructing a robust intelligent controller for the task of USV navigation under disturbances and we show some preliminary simulation results we have obtained.

Research on the Vanishing Point Detection Method Based on an Improved Lightweight AlexNet Network for Narrow Waterway Scenarios

When an unmanned surface vehicle (USV) navigates in narrow waterway scenarios, its ability to detect vanishing points accurately and quickly is highly important for safeguarding its navigation safety and realizing automated navigation. We propose a novel approach for detecting vanishing points based on an improved lightweight AlexNet. First, a similarity evaluation calculation method based on image texture features is proposed, by which some scenarios are selected from the filtered Google Street Road Dataset (GSRD). These filtered scenarios, together with the USV Inland Dataset (USVID), compose the training dataset, which is manually labeled according to a non-uniformly distributed grid level. Next, the classical AlexNet was adjusted and optimized by constructing sequential connections of four convolutional layers and four pooling layers and incorporating the Inception A and Inception C structures in the first two convolutional layers. During model training, we formulate vanishing point detection as a classification problem using an output layer with 225 discrete possible vanishing point locations. Finally, we compare and analyze the labeled vanishing point with the detected vanishing point. The experimental results show that the accuracy of our method and the state-of-the-art algorithmic vanishing point detector improves, indicating that our improved lightweight AlexNet can be applied in narrow waterway navigation scenarios and can provide a technical reference for autonomous navigation of USVs.

GBM-ILM: Grey-Box Modeling Based on Incremental Learning and Mechanism for Unmanned Surface Vehicles

Unmanned surface vehicles (USVs) have garnered significant attention across various application fields. A sufficiently accurate kinetic model is essential for achieving high-performance navigation and control of USVs. However, time-varying unobservable internal states and external disturbances pose challenges in accurately modeling the USV’s kinetics, and existing methods face difficulties in accurately estimating unknown time-varying disturbances online while ensuring precise mechanism modeling. To address this issue, a novel grey-box modeling method based on incremental learning and mechanisms (GBM-ILM) is proposed. Its union structure combines the advantages of both incremental learning networks and physical mechanisms for estimating the USV’s full kinetics. Depending on the linear parameter-varying (LPV) mechanism, it not only adheres to physical laws but also calculates the unstructured model errors. An incremental learning network is implemented to continuously refine model errors, by accounting for the USV’s time-varying characteristics and iteratively updating the network parameters and structures to adapt to different USV states and environmental disturbances. To validate this method, we developed the ‘Salmon’ USV and conducted identification experiments in a lake. Compared to tests of other state-of-the-art methods, our method has better adaptability, with 46.34%, 14.86%, and 6.87% accuracy improvements when estimating the USV’s forward, turning, and sideslip dynamic model, respectively.

Efficient multi-branch segmentation network for situation awareness in autonomous navigation

Real-time and high-precision situational awareness technology is critical for autonomous navigation of unmanned surface vehicles (USVs). In particular, robust and fast obstacle semantic segmentation methods are essential. However, distinguishing between the sea and the sky is challenging due to the differences between port and maritime environments. In this study, we built a dataset that captured perspectives from USVs and unmanned aerial vehicles in a maritime port environment and analysed the data features. Statistical analysis revealed a high correlation between the distribution of the sea and sky and row positional information. Based on this finding, a three-branch semantic segmentation network with a row position encoding module (RPEM) was proposed to improve the prediction accuracy between the sea and the sky. The proposed RPEM highlights the effect of row coordinates on feature extraction. Compared to the baseline, the three-branch network with RPEM significantly improved the ability to distinguish between the sea and the sky without significantly reducing the computational speed.

Numerical Computation of Restoring Time and Prediction of Self-Righting Process

Excellent self-righting performance is important to guarantee the normal navigation of Unmanned Surface Vehicles (USVs) after overturning, and the restoring time is an important index in design requirements. Traditionally, the static stability method and experiments on full-scale vehicles were used to analyze the large-angle stability of the USV. However, when it comes to the analysis of self-righting performance, the traditional static stability method will cause improper integration, and experiments are not convenient. To solve these problems, an improved static stability method was proposed, and a whole self-righting process simulation of a physical model was finished. The numerical simulation method was used to predict the self-righting process of a USV under four working conditions. Firstly, a midpoint average method based on the static stability theory was adopted to compute the static restoring time, and the results were compared with the results of the references, which verifies the effectiveness of the midpoint average method. Also, the midpoint average method is convenient because it only needs the restoring arm curve, the width and the gravity center height. Then, a numerical simulation of a physical model in static water was finished, and an experiment for a physical model in a towing tank was conducted. Comparing the restoring time of the midpoint average method, the numerical simulation and the experiment, the results show that the numerical simulation has high accuracy. Moreover, the numerical simulation was used to predict the self-righting process and analyze the self-righting performance of a USV under four working conditions.

Path Following Control for Unmanned Surface Vehicles: A Reinforcement Learning-Based Method With Experimental Validation.

In this article, a reinforcement learning (RL)-based strategy for unmanned surface vehicle (USV) path following control is developed. The proposed method learns integrated guidance and heading control policy, which directly maps the USV's navigation states to motor control commands. By introducing a twin-critic design and an integral compensator to the conventional deep deterministic policy gradient (DDPG) algorithm, the tracking accuracy and robustness of the controller can be significantly improved. Moreover, a pretrained neural network-based USV model is built to help the learning algorithm efficiently deal with unknown nonlinear dynamics. The self-learning and path following capabilities of the proposed method were validated in both simulations and real sea experiments. The results show that our control policy can achieve better performance than a traditional cascade control policy and a DDPG-based control policy.

Path planning of USV based on improved PRM under the influence of ocean current

Multi-extensibility and flexibility of unmanned surface vehicles (USVs) allow them perform many different tasks, further path planning technology is crucial to the safety, autonomy, and intelligent navigation of USVs. Firstly, this paper analyzes the impact of ocean currents and risk constraints on USV based on the electronic chart. Then take the optimal sailing time as the objective function and design a path planning algorithm based on an improved probabilistic roadmap (PRM) algorithm, in which a Gaussian space sampling algorithm based on edge detection is introduced. After building the network topology environment through improved PRM, then a Dijkstra algorithm based on great circle distance is used to solve the optimal path. Finally, the simulation experiment is designed through the MATLAB platform. By comparing the average and the three quartile lengths of the planned paths under three environments, the values of the designed Edge-Gaussion (E-G) PRM algorithm are smaller than Lazy PRM and Gaussian PRM algorithm, which shows that the improved PRM algorithm has better performance. When planning the USV path under the influence of current, compared with traditional length optimal path planning, although the navigation length planned by the designed algorithm is shorter by 972 m, sailing time is improved by 110 s, which efficiency shows the better application on the sea.

Non-parametric dynamics modeling for unmanned surface vehicle using spectral metric multi-output Gaussian processes learning

High-precision dynamic models are crucial for various marine missions and the control and navigation of unmanned surface vehicles. However, the nonlinear, strong coupling, complex structure of these vehicles poses challenges in building such models. Traditional single-output models have limitations in data utilization and high computational complexity. Therefore, this paper proposes a spectral metric multi-output Gaussian process for continuous-time dynamic modeling of unmanned surface vehicles. Specifically, a spectral covariance matrix is constructed in this scheme to establish a spectral metric multi-output Gaussian processes learning model that captures correlations under different degrees of freedom. Meanwhile, an improved particle swarm optimization algorithm is used to dynamically tuning the correlation matrix for improved model accuracy, and utilizing a subspace index to enhance computational efficiency in multi-output Gaussian processes learning. Moreover, the scheme can conduct real-time simulation under environmental disturbances. Finally, the proposed scheme is applied to an unmanned surface vehicle, and the results demonstrate that the scheme is an effective modeling tool for multi degree-of-freedom coupled dynamics.

Real-Time Obstacle Detection for Unmanned Surface Vehicle Maneuver

The rapid advancement and increasing demand for Unmanned Surface Vehicle (USV) technology have drawn considerable attention in various sectors, including commercial, research, and military, particularly in marine and shallow water applications. USVs have the potential to revolutionize monitoring systems in remote areas while reducing labor costs. One critical requirement for USVs is their ability to autonomously integrate Guidance, Navigation, and Control (GNC) technology, enabling self-reliant operation without constant human oversight. However, current study for USV shown the use of traditional method using color detection which is inadequate to detect object with unstable lighting condition. This study addresses the challenge of enabling Autonomous Surface Vehicles (ASVs) to operate with minimal human intervention by enhancing their object detection and classification capabilities. In dynamic environments, such as water surfaces, accurate and rapid object recognition is essential. To achieve this, we focus on the implementation of deep learning algorithms, including the YOLO algorithm, to empower USVs with informed navigation decision-making capabilities. Our research contributes to the field of robotics by designing an affordable USV prototype capable of independent operation characterized by precise object detection and classification. By bridging the gap between advanced visualization techniques and autonomous USV technology, we envision practical applications in remote monitoring and marine operations with object detection. This paper presents the initial phase of our research, emphasizing significance of deep learning algorithms for enhancing USV navigation and decision-making in dynamic environmental conditions, resulting in mAP of 99.51%, IoU of 87.80%, error value of the YOLOv4-tiny image processing algorithm is 0.1542.

A Fuzzy Dempster–Shafer Evidence Theory Method with Belief Divergence for Unmanned Surface Vehicle Multi-Sensor Data Fusion

The safe navigation of unmanned surface vehicles in the marine environment requires multi-sensor collaborative perception, and multi-sensor data fusion technology is a prerequisite for realizing the collaborative perception of different sensors. To address the problem of poor fusion accuracy for existing multi-sensor fusion methods without prior knowledge, a fuzzy evidence theory multi-sensor data fusion method with belief divergence is proposed in this paper. First of all, an adjustable distance for measuring discrepancies between measurements is devised to evaluate the degree of measurement closeness to the true value, which improves the adaptability of the method to different classes of sensor data. Furthermore, an adaptive multi-sensor measurement fusion strategy is designed for the case where the sensor accuracy is known in advance. Secondly, the affiliation function of the fuzzy theory is introduced into the evidence theory approach to assign initial evidence of measurements in terms of defining the degree of fuzzy support between measurements, which improves the fusion accuracy of the method. Finally, the belief Jensen–Shannon divergence and the Rényi divergence are combined for measuring the conflict between the evidence pieces to obtain the credibility degree as the reliability of the evidence, which solves the problem of high conflict between evidence pieces. Three examples of multi-sensor data fusion in different domains are employed to validate the adaptability of the proposed method to different kinds of multi-sensors. The maximum relative error of the proposed method for multiple sensor experiments is greater than or equal to 0.18%, and its error accuracy is much higher than the best result of 0.46% among other comparative methods. The experimental results verify that the proposed data fusion method is more accurate than other existing methods.

NMPC-based UAV-USV cooperative tracking and landing

The study aims to solve the problem of real time tracking and precise landing of unmanned aerial vehicle (UAV) during unmanned surface vehicle (USV) navigation. In this paper, a UAV-USV cooperative tracking and landing control strategy based on nonlinear model predictive control (NMPC) is proposed. Firstly, the UAV-USV heterogeneous intelligent body collaborative system is constructed based on the mathematical model of UAV and USV; secondly, the tracking controller is designed based on NMPC algorithm to ensure that the UAV can track the USV in real time; finally, a UAV-USV cooperative landing control strategy is proposed to realize the heave motion of the USV to the peak vertex, thus, the UAV completes the precise landing with the minimum impact. As the simulation experimental results show, the UAV-USV cooperative tracking and landing control scheme proposed in this paper can provide effective solution against real time tracking and accurate landing of UAV during the navigation of USV.

Unmanned surface vehicle navigation through generative adversarial imitation learning

In the artificial intelligent and big data technology era, the marine industry among others is inevitably developing in this direction, aiming at becoming autonomous and completing tasks without relying on human involvement while providing safety. The technology of small unmanned surface vehicles (USVs) is relatively mature but with a large development potential and wide research interest expecting significant benefits such as safety and high efficiency in shipping and transportation systems. This article addresses these issues and utilizes an imitation learning algorithm to resolve autonomous navigation for USVs even in complex environmental conditions. We formulate the trajectory modeling as a data-driven imitation learning problem where we employ a state of the art imitation learning algorithm. Experiments are performed in a particular simulated environment tailored to match the specific weather conditions of the local area. The simulation results show the potential of the proposed imitation learning scheme to create advanced intelligent agents for USVs under real-world environmental settings, and USV actuation constraints that allow to predict trajectories with high accuracy and safety.In addition, we evaluated the method’s robustness in generating successful trajectories under environmental conditions that differed from those encountered during training, thereby promoting knowledge reusing without the need for retraining.

Research on a Horizon Line Detection Method for Unmanned Surface Vehicles in Complex Environments

A critical step in the visual navigation of unmanned surface vehicles (USVs) is horizon line detection, which can be used to adjust the altitude as well as for obstacle avoidance in complex environments. In this paper, a real-time and accurate detection method for the horizon line is proposed. Our approach first differentiates the complexity of navigational scenes using the angular second moment (ASM) parameters in the grey level co-occurrence matrix (GLCM). Then, the region of interest (ROI) is initially extracted using minimal human interaction for the complex navigation scenes, while subsequent frames are dynamically acquired using automatic feature point matching. The matched ROI can be maximally removed from the complex background, and the Zernike-moment-based edges are extracted from the obtained ROI. Finally, complete sea horizon information is obtained through a linear fitting of the lower edge points to the edge information. Through various experiments carried out on a classical dataset, our own datasets, and that of another previously published paper, we illustrate the significance and accuracy of this technique for various complex environments. The results show that the performance has potential applications for the autonomous navigation and control of USVs.

LWDNet-A lightweight water-obstacles detection network for unmanned surface vehicles

Water-obstacles detection based on semantic segmentation is an essential part of autonomous navigation of unmanned surface vehicles (USV). However, it is difficult for existing methods to ensure the real-time of water-obstacles recognition and high detection accuracy. To address this issue, we proposed novel network architecture, a lightweight water-obstacles detection network (LWDNet). In LWDNet, we adopt a novel backbone, bottleneck structure with attention block, the former decrease the model size, the latter obtain more semantic information, and then the dilated convolution has been used in depthwise separable (DW) convolution to enforce the extraction of feature information. Additionally, by using improved focal loss (weight the main and auxiliary focal loss), the water-obstacles detection accuracy increased. In order to test the real-time performance and detection accuracy of LWDNet, we use the most challenging dataset, Multi-modal Marine Obstacle Detection Dataset 2 (MODD2) dataset, for experimental validation. The experimental results show that, compared with the state-of-the-art detection methods, such as WasR and ShorelineNet, the LWDNet maintains a much faster speed of images inference (62 frames-per-second on an NVIDIA RTX 2080Ti), and at the same time, the obstacles detection performance is equally high (87.5% F-measure, 77.8% IOU). Therefore, the LWDNet is an efficient network in water-obstacles detection, making the autonomous navigation of USV more reliable.

Object Extraction Algorithm for the First-Frame Image of Unmanned Surface Vehicles Based on a Radar-Photoelectric System

The radar-photoelectric system is a perception system to detect the surrounding environment based on marine radar and a photoelectric device. Mast obscuration, green water, and multi-object scenes are special scenes that appear in the first-frame image during the navigation of unmanned surface vehicles. The perception system cannot accurately obtain the object information in mast obscuration and green water scenes. The radar-guided object cannot be stably extracted from the first-frame image in multi-object scenes. Therefore, this paper proposes an object extraction algorithm for the first-frame image of unmanned surface vehicles based on a radar-photoelectric system. The algorithm realizes the field-of-view adaptation to solve the problem that the features of the radar-guided object are incomplete in the first-frame image and improve the detection accuracy of the local features by 16.8%. The algorithm realizes the scene recognition of the first-frame image to improve the robustness of object tracking. In addition, the algorithm achieves the stable extraction of the radar-guided object in multi-object scenes.

Decision-making for the autonomous navigation of USVs based on deep reinforcement learning under IALA maritime buoyage system

It is extremely challenging to carry out an advanced adaptive navigation system in the complex environment of a port. Especially in the waters that are about to be berthed, the unmanned surface vehicles (USVs) should autonomously identify and avoid dense buoys according to the rules. Each country has corresponding mandatory documents that strictly regulate the shape, color and orientation of water buoys in coastal and estuary channels. Aiming at the problem of USV collision avoidance navigation under the constraints of the IALA (International Association of Marine Aids and Lighthouse Authorities) Maritime buoyage system, this paper designs a mixed environment model including multiple ocean buoys according to this rule. By using the deep neural network to extract the state features of the target, and setting the reward function reasonably, the USV can not only navigate to the target autonomously, but also identify the corresponding buoy and give the corresponding decision. Using different DQN optimization algorithms to conduct comparative experiments, the stability of the algorithm's learning of the optimal strategy is improved. The results show that the algorithm can accurately avoid obstacles ahead, identify buoys effectively, and realize effective autonomous collision avoidance decision-making in complex environments with static obstacles and buoys with indicating function. This research can provide theoretical basis and method reference for USV's autonomous navigation in port.

Dynamic Navigation and Area Assignment of Multiple USVs Based on Multi-Agent Deep Reinforcement Learning.

The unmanned surface vehicle (USV) has attracted more and more attention because of its basic ability to perform complex maritime tasks autonomously in constrained environments. However, the level of autonomy of one single USV is still limited, especially when deployed in a dynamic environment to perform multiple tasks simultaneously. Thus, a multi-USV cooperative approach can be adopted to obtain the desired success rate in the presence of multi-mission objectives. In this paper, we propose a cooperative navigating approach by enabling multiple USVs to automatically avoid dynamic obstacles and allocate target areas. To be specific, we propose a multi-agent deep reinforcement learning (MADRL) approach, i.e., a multi-agent deep deterministic policy gradient (MADDPG), to maximize the autonomy level by jointly optimizing the trajectory of USVs, as well as obstacle avoidance and coordination, which is a complex optimization problem usually solved separately. In contrast to other works, we combined dynamic navigation and area assignment to design a task management system based on the MADDPG learning framework. Finally, the experiments were carried out on the Gym platform to verify the effectiveness of the proposed method.

USV Dynamic Accurate Obstacle Avoidance Based on Improved Velocity Obstacle Method

Unmanned surface vehicle (USV) path planning is a crucial technology for achieving USV autonomous navigation. Under global path planning, dynamic local obstacle avoidance has become the primary focus for safe USV navigation. In this study, a USV autonomous dynamic obstacle avoidance method based on the enhanced velocity obstacle method is proposed in order to achieve path replanning. Through further analysis of obstacles, the obstacle geometric model set in the conventional velocity obstacle method was redefined. A special triangular obstacle geometric model was proposed to reconstruct the velocity obstacle region. The collision time was predicted by fitting the previously gathered data to the detected obstacle’s distance, azimuth, and other relevant data. Then, it is combined with the collision risk to determine when obstacle avoidance should begin and end. In order to ensure safe driving between path points, the international maritime collision avoidance rules (COLREGs) are incorporated to ensure the accuracy of obstacle avoidance. Finally, through numerical simulations of various collision scenarios, it was determined that, under the assumption of ensuring a safe encounter distance, the maximum change rates of USV heading angle are optimized by 17.54%, 58.16%, and 28.63% when crossing, head-on, and overtaking, respectively. The results indicate that, by optimizing the heading angle, the enhanced velocity obstacle method can avoid the risk of ship rollover caused by an excessive heading angle during high-speed movement and achieve more accurate obstacle avoidance action in the event of a safety encounter.

Improved Dynamic Window Approach for Unmanned Surface Vehicles' Local Path Planning Considering the Impact of Environmental Factors.

The aim of local path planning for unmanned surface vehicles (USVs) is to avoid unknown dynamic or static obstacles. However, current relative studies have not fully considered the impact of ocean environmental factors which significantly increase the control difficulty and collision risk of USVs. Therefore, this work studies two ocean environmental factors, namely, wave and current, given that they both have a significant impact on USVs. Furthermore, we redesign a kinematic model of an USV and the evaluation function of a classical and practical local path planning method based on the dynamic window approach (DWA). As shown by the results of the simulations, the path length was impacted mainly by the intensity of the environmental load and slightly by the direction of the environmental load, but the navigation time was significantly influenced by both. Taking the situation in still water as a benchmark in terms of the intensity and direction of the environmental factors, the maximum change rates of the path length were 8.6% and 0.6%, respectively, but the maximum change rates of the navigating time were 17.9% and 25.6%, separately. In addition, the average calculation time of each cycle was only 0.0418 s, and the longest time did not exceed the simulation time corresponding to a single cycle of 0.1 s. This method has proven to be a good candidate for real-time local path planning of USVs since it systematically considers the impact of waves and currents on the navigation of USVs, and thus ensures that USVs can adjust to the planned path in time and avoid obstacles when navigating in the real ocean environment.