Unmanned Surface Vehicle System Research Articles

Reinforcement learning-based moving-target enclosing control for an unmanned surface vehicle in multi-obstacle environments

This paper investigates the moving-target enclosing problem in multi-obstacle environments for an unmanned surface vehicle (USV) with complex unknown factors, including target dynamics, vehicle dynamics, and disturbances. A reinforcement learning-based moving-target enclosing control scheme is proposed to ensure collision-free behavior and bolster the enclosing capability. Specifically, an extended state observer is deployed to estimate the target dynamics. Leveraging the estimated data and control obstacle functions, a virtual safety control law is formulated to dynamically harmonize obstacle avoidance and target enclosing control. Then, a novel controller is constructed to track this control law utilizing a Nussbaum-type function in conjunction with actor–critic neural networks (NNs). The actor and critic NNs are employed to approximate unknown dynamics encapsulating vehicle dynamics and disturbances, and value function, respectively. The Nussbaum-type function is embedded to adaptively identify unknown inertia mass, regulating the control input of the USV with the actor NN online. The proposed scheme effectively decouples obstacle avoidance and target enclosing control and only relies on the measurable variables. A rigorous theoretical analysis is further employed to ensure the closed-loop stability of the USV system. Eventually, Simulations are demonstrated to validate the effectiveness and superiority of the proposed scheme for the USV in multi-obstacle environments.

Probabilistic Model-Based Reinforcement Learning Unmanned Surface Vehicles Using Local Update Sparse Spectrum Approximation

This article focuses on the computational efficiency of probabilistic model-based reinforcement learning (MBRL) in unmanned surface vehicles (USV) under unforeseeable and unobservable external disturbances. A novel MBRL approach, local update spectrum probabilistic model predictive control (LUSPMPC) is proposed to fully release the superiority of the probabilistic model approximated in the frequency domain in computational efficiency while mitigating its risk of overfitting during the learning procedure. It employs a local update strategy to relieve the violation of Bochner's theory, and a frequency clipping trick to encourage the approximated model to focus on the features in the low-frequency domain. Evaluated by the position-keeping task in a real USV data-driven simulation, LUSPMPC shows its significant advantages in computational efficiency while achieving better learning capability, generalization capability and control performances in a wide range of sparse scales compared with the baseline MBRL approaches that approximate their models in sample space and frequency domain, and therefore becomes an appealing solution for MBRL USV system defending against rapidly changing ocean disturbances.

Adaptive fuzzy finite-time event-triggered formation control for unmanned surface vehicle systems

This paper studies the finite-time event-triggered fuzzy formation control problem for multiple unmanned surface vehicle (USV) system. The fuzzy state estimator is designed by intermittent output signal to estimate unmeasurable velocity and yaw velocity of the USV. The dual-channel event-triggered mechanisms (ETMs) are designed to reduce the updating times from sensor-to-actuator and controller-to-actuator channels, respectively. Based on the designed fuzzy state estimator and ETMs, a finite-time fuzzy adaptive output feedback formation control is formulated. It is proved that the controlled USV system is semi-global practically finite-time stable. Moreover, the outputs of the followers are able to track the output of the leader. Finally, the simulation and comparison results are provided to demonstrate the feasibility of the presented formation control algorithm.

IROA-based LDPC-Lévy method for target search of multi AUV–USV system in unknown 3D environment

In this study, a local dynamic predictive control framework combined with Lévy flight (LDPC-Lévy) method is proposed to assist autonomous underwater vehicles (AUV) and unmanned surface vehicles (USV) in target-search missions without prior information in unknown ocean environments. The LDPC-Lévy method allocates sub-regions to be searched for AUVs and simultaneously plans the appropriate position for USVs to ensure a reasonable communication distance while exploring the environment and searching for the targets. To solve the optimization problem in LDPC-Lévy method, an improved remora optimization algorithm (IROA) is utilized with a restart strategy based on the concept of the firework algorithm (FWA) and simulated annealing (SA). The simulation results show that the LDPC-Lévy method has significant advantages over random search and parallel line methods in terms of space exploration rate, search uniformity, and stability of the number of marked targets, while being robust against partial failure.

Nussbaum-type function based robust neural event-triggered control of unmanned surface vehicle subject to cyber and physical attacks

This paper mainly focuses on the path-following control of the unmanned surface vehicle (USV) with the consideration of cyber and physical attacks. The actuator of USV has fully unknown dynamics under deception attack, and the USV system consists of complex nonlinear perturbations caused by physical attack. Therefore, a Nussbaum-type function based robust neural event-triggered path-following control scheme is proposed by combining event-triggered technique with Nussbaum approach. Together with hybrid disturbances and model uncertainties, the lumped nonlinearity is online approximated by employing the robust neural damping technique. Within the backstepping framework, a Nussbaum gain function is further designed to tackle unknown control directions in the actuator system. To facilitate the implementation of the proposed algorithm, an input-based event-triggered mechanism is introduced to reduce the channels clogging and the resources wasting between controllers and actuators. Theoretical analysis reveals that all signals of the closed-loop tracking system are bounded and tracking errors can converge to an arbitrarily small neighborhood of zero. Numerical simulation is performed by employing a class of underactuated surface cable-laying vehicle. The corresponding results demonstrate the effectiveness and superiority of the proposed approach.

Event-Based Fault Detection for Unmanned Surface Vehicles Subject to Denial-of-Service Attacks

In this work, the problem of event-based fault detection is addressed for unmanned surface vehicles (USVs) under denial-of-service (DoS) jamming attacks. A fault detection filter (FDF) is deployed to generate residual for USV systems with external disturbance and system faults. A resilient event-triggered mechanism is implemented to reduce the bandwidth occupation of communication network and energy consumption of USV system as well as mitigating the influence of DoS attacks. Based on the established framework, a switched residual system is constructed and a criterion is deduced to ensure the exponential stability and weighted <inline-formula> <tex-math notation="LaTeX">$H_{\infty }$ </tex-math></inline-formula> performance of residual system via piecewise Lyapunov functional approach. The FDF and resilient event-triggered mechanism are co-designed. Simulation results are provided to testify the efficient performance of the devised resilient event-triggered fault detection method.

Design and Implementation of a UUV Tracking Algorithm for a USV

In a departure from the past, unmanned underwater vehicles (UUVs) and unmanned surface vehicles (USVs) are increasingly needed for complementary cooperation in military, scientific, and commercial applications, because this is more efficient than standalone operations. Information sharing through acoustic underwater communication is vital for complementary cooperation between USVs and UUVs. Normally, since USVs have advantages in terms of wide operational boundaries compared to UUVs, they are efficient for tracking UUVs. In this paper, we suggest a UUV tracking algorithm for a USV. The tracking algorithm’s development consists of three main software models: an estimation based on an extended Kalman filter (EKF) with a navigation smoothing method, guidance based on multimode guidance, and re-searching based on a pattern. In addition, the algorithm provides a procedure for tracking UUVs in complex acoustic underwater communication environments. The tracking algorithm was tested in a simulated environment to check the performance of each method, and implemented with a USV system to verify its validity and stability in sea trials. The UUV tracking algorithm of the USV shows stable and efficient performance.

Design and test of an improved active disturbance rejection control system for water sampling unmanned surface vehicle

Unmanned surface vehicles (USVs) have wide application prospects in military and civil fields. Motivated by the large demand for environmental protection equipment, a water-sampling USV (WS-USV) system is designed in this study. The software and hardware of the entire system are designed and developed independently. Two water sampling modes, a manual remote control mode and remote interface automatic control mode are designed for handling emergencies. The WS-USV is propelled by twin-propellers. These propellers have many input constraints owing to their inherent structure, making the design of the controller very difficult. In this study, an improved active disturbance rejection control (ADRC) method is proposed and a saturation function is introduced to design a path-following control system for the WS-USV. This enhances the anti-disturbance ability for addressing environmental disturbances by wind, waves and currents in the water sampling process. The stability of the system is improved. The feasibility, stability and performance superiority of the control system are proven by water sampling contrast experiments.

Reinforcement learning-based finite-time tracking control of an unknown unmanned surface vehicle with input constraints

In this paper, subject to completely unknown system dynamics and input constraints, a reinforcement learning-based finite-time trajectory tracking control (RLFTC) scheme is innovatively created for an unmanned surface vehicle (USV) by combining actor-critic reinforcement learning (RL) mechanism with finite-time control technique. Unlike previous RL-based tracking which requires infinite-time convergence thereby rather sensitive to complex unknowns, an actor-critic finite-time control structure is created by employing adaptive neural network identifiers to recursively update actor and critic, such that learning-based robustness can be sufficiently enhanced. Moreover, deduced from the Bellman error formulation, the proposed RLFTC is directly optimized in a finite-time manner. Theoretical analysis eventually shows that the proposed RLFTC scheme can ensure semi-global practical finite-time stability (SGPFS) for a closed-loop USV system and tracking errors converge to an arbitrarily small neighborhood of the origin in a finite time, subject to optimal cost. Both mathematical simulation and virtual-reality experiments demonstrate remarkable effectiveness and superiority of the proposed RLFTC scheme.

Multiple Task Assignment and Path Planning of a Multiple Unmanned Surface Vehicles System Based on Improved Self-Organizing Mapping and Improved Genetic Algorithm

This paper addresses multiple task assignment and path-planning problems for a multiple unmanned surface vehicle (USVs) system. Since it is difficult to solve multi-task allocation and path planning together, we divide them into two sub-problems, multiple task allocation and path planning, and study them separately. First, to resolve the multi-task assignment problem, an improved self-organizing mapping (ISOM) is proposed. The method can allocate all tasks in the mission area, and obtain the set of task nodes that each USV needs to access. Second, aiming at the path planning of the USV accessing the task nodes, an improved genetic algorithm (IGA) with the shortest path is proposed. To avoid USV collision during navigation, an artificial potential field function (APFF) is proposed. A multiple USV system with multi-task allocation and path planning is simulated. Simulation results verify the effectiveness of the proposed algorithms.

Enhanced Target Ship Tracking With Geometric Parameter Estimation for Unmanned Surface Vehicles

Autonomous collision detection and avoidance is a crucial requirement for the safe navigation of unmanned surface vehicles (USVs) in maritime traffic situations. Automatic identification system (AIS) is used to obtain the motion information of surrounding ships and their dimensional specifications. With AIS information, appropriate collision risk assessment between two ships can be performed; further, collision avoidance can be achieved by defining a safe radius of avoidance, which can be determined considering the shape parameters of a target ship. However, AIS data are often unreliable and some commercial fishing vessels intentionally turn off the public tracking system to hide their location. Under these circumstances, marine radars are used to detect and estimate the motion information of nearby ships. However, most existing target tracking studies model the target as a point object without any spatial extent, and thus, its physical dimensions cannot be identified. In this paper, a target tracking method that uses a marine radar is proposed to simultaneously estimate the motion states (i.e., position, course, and speed) of a target ship and its geometric parameter (length) in the framework of an extended Kalman filter (EKF). The proposed approach enhances collision avoidance by providing the kinematic and length parameters to evaluate collision risk and generate an appropriate collision-free path. Real-sea experiments using a developed USV system were conducted to verify and demonstrate the feasibility of the proposed algorithm; the results are presented and discussed in this paper.

Development and Field Test of Unmanned Marine Vehicle (USV/UUV) With cable

This paper presents the system, controller, and field test results of an unmanned marine vehicle (UMV) developed to acquire real-time ocean exploration information. The system consists of an unmanned surface vehicle (USV), an unmanned underwater vehicle (UUV), and an underwater cable. The developed platform is a research platform for ocean exploration and was proposed to compensate for the shortcomings of the existing USV, UUV, and towing system. This paper describes the proposed UMV, including the design considerations such as electronics architecture, data management, sensors, and actuators and explains the path control algorithm and controller used to follow the specified path for ocean exploration. In order to confirm the performance of the developed platform and control algorithm, a way-point tracking experiment was performed, and the results are shown.

Development and path planning of a novel unmanned surface vehicle system and its application to exploitation of Qarhan Salt Lake

Development and path planning of a novel unmanned surface vehicle system and its application to exploitation of Qarhan Salt Lake

Collision Avoidance Using Finite Control Set Model Predictive Control for Unmanned Surface Vehicle

In recent years, with the development of unmanned platforms, unmanned surface vehicles (USV) are attracting more and more attention. Compared to ordinary ships, USV have a smaller volume and faster speed, so their collision avoidance system (CAS) should have better responsiveness and stability. The paper describes a method that is based on finite control set model predictive control (FCS-MPC). A finite control set is generated by more practical control commands: the thruster speed and propulsion angle of the USV. The method is conceptually and computationally simple and yet quite versatile, as it can account for the dynamics of the USV, steering and propulsion system. Based on the theory of FCS-MPC, a safe and fast CAS is proposed, and it is verified in different static and dynamic environments. The real environment model for collision avoidance is established by extracting the environment data from the electronic chart. The result shows that the method is effective and can control the USV to sail safely and quickly in complex real scenarios with multiple dynamic obstacles.

Speed and Heading Control of an Unmanned Surface Vehicle Based on State Error PCH Principle

This paper proposes a novel nonlinear control scheme based on energy-shaping (ES) principle and state error port-controlled Hamiltonian (PCH) systems for unmanned surface vehicles (USV) system. The PCH model of three degrees of freedom for USV kinetics system is established. By the ES principle, interconnection assignment and damping injection method is applied to the speed and heading control of the closed-loop USV system to realize an overall stability of control mechanism. Simulation results show that the validity and stability of control algorithm can be satisfied with the performance in speed and heading tracking of which the high simplification and portability make it applicable to the various region.

Nonlinear Modeling for a Water-Jet Propulsion USV: An Experimental Study

Although unmanned surface vehicles (USVs) have been extensively researched and applied to many typical scenarios, high-performance autonomous control is still an open problem. One of their major problem stems from the difficulty in constructing a sufficient accurate and sufficient simple control-oriented dynamics model. Owing to the highly complicated physical mechanisms of hydrodynamics, USV systems possess strong nonlinearities and coupling, which make it exceptionally difficult to develop an accurate model structure. In real applications, extensively existing uncertainties, such as external disturbances due to wind, wave, current, and measurement noise in the onboard sensor, will unavoidably influence identification precision with respect to the parameters in the USV's model. Thus, in this paper, a new kind of nonlinear modeling scheme—the active modeling enhanced quasi-linear parameter-varying (qLPV) model—is proposed for a water-jet propulsion USV system. First, a qLPV-structured model is derived by simplifying the real dynamics model, which has a simple quasi-linear structure and can approximate the nonlinearities of the hydrodynamics. Subsequently, a nonlinear version of the Kalman filter-based active modeling method is proposed to provide online estimates of the unstructured model to eliminate the errors due to the structure inaccuracy between the qLPV-structured model and the real system. Finally, the newly proposed modeling scheme is tested on a real USV system and its superiority is shown through comparisons to some other traditional modeling methods.

Effective Waterline Detection of Unmanned Surface Vehicles Based on Optical Images.

Real-time and accurate detection of the sailing or water area will help realize unmanned surface vehicle (USV) systems. Although there are some methods for using optical images in USV-oriented environmental modeling, both the robustness and precision of these published waterline detection methods are comparatively low for a real USV system moving in a complicated environment. This paper proposes an efficient waterline detection method based on structure extraction and texture analysis with respect to optical images and presents a practical application to a USV system for validation. First, the basic principles of local binary patterns (LBPs) and gray level co-occurrence matrix (GLCM) were analyzed, and their advantages were integrated to calculate the texture information of river images. Then, structure extraction was introduced to preprocess the original river images so that the textures resulting from USV motion, wind, and illumination are removed. In the practical application, the waterlines of many images captured by the USV system moving along an inland river were detected with the proposed method, and the results were compared with those of edge detection and super pixel segmentation. The experimental results showed that the proposed algorithm is effective and robust. The average error of the proposed method was 1.84 pixels, and the mean square deviation was 4.57 pixels.

Development of an Unmanned Surface Vehicle System for the 2014 Maritime RobotX Challenge

This paper addresses the development of an unmanned surface vehicle (USV) system by Team Angry-Nerds from KAIST for the inaugural Maritime RobotX Challenge competition, which was held on October 20-26, 2014, in Marina Bay, Singapore. The USV hardware was developed on a catamaran platform by integrating various system components, including propulsion, sensors, computer, power, and emergency systems. The competition comprised five mission tasks: 1) navigation and control, 2) underwater search and report, 3) automatic docking, 4) buoy search and observation, and 5) obstacle detection and avoidance. Onboard intelligence was a key factor for all of the mission tasks which needed to be performed autonomously with no human intervention. Software algorithms for vehicle autonomy were developed, and executable computer codes were implemented and integrated with the developed USV hardware system. This paper describes the development process of the USV system and its application to the competition mission tasks.

Precision navigation and mapping under bridges with an unmanned surface vehicle

Navigation relative to the surrounding physical structures and obstacles is an important capability for safe vehicle operation. This capability is particularly useful for unmanned surface vehicles (USVs) operating near large structures such as bridges, waterside buildings, towers and cranes, where global positioning system signals are restricted or unavailable due to the line-of-sight restrictions. This study proposes a high-precision navigation technique using dead-reckoning sensors and lidars, which enables building a parameterized map of artificial bridge structures and estimating the vehicle's position relative to the parameterized map simultaneously. Also, three-dimensional reconstruction of the surrounding structures is carried out by fusing camera and lidar measurements for realistic 3D visual mapping which may facilitate automated surveys and inspection of structural safety. Field experiments using a newly developed USV system in a real-world bridge environment were performed to verify and demonstrate the performance of the proposed navigation and mapping algorithms. The field test results are presented and discussed in this paper.

Intelligent Control for USV Based on Improved Elman Neural Network with TSK Fuzzy

In recent years, based on the rising of global personal safety demand and human resource cost considerations, development of unmanned vehicles to replace manpower requirement to perform high-risk operations is increasing. In order to acquire useful resources under the marine environment, a large boat as an unmanned surface vehicle (USV) was implemented. The USV is equipped with automatic navigation features and a complete substitute artificial manipulation. This USV system for exploring the marine environment has more carrying capacity and that measurement system can also be self-designed through a modular approach in accordance with the needs for various types of environmental conditions. The investigation work becomes more flexible. A catamaran hull is adopted as automatic navigation test with CompactRIO embedded system. Through GPS and direction sensor we not only can know the current location of the boat, but also can calculate the distance with a predetermined position and the angle difference immediately. In this paper, the design of automatic navigation is calculated in accordance with improved Elman neural network (ENN) algorithms. Takagi-Sugeno-Kang (TSK) fuzzy and improved ENN control are applied to adjust required power and steering, which allows the hull to move straight forward to a predetermined target position. The route will be free from outside influence and realize automatic navigation purpose.