Unmanned surface vehicles: An overview of developments and challenges (2023)

This paper presents wave-filtering finite-time self-learning extended state observers for robotic surface vehicles subject to unknown control gains and ocean disturbances. By incorporating wave filtering technique and concurrent learning into the extended state observer design, the low-frequency motion components and wave-frequency motion components of robotic surface vehicles can be estimated, in addition to the unknown control gains, total disturbance and unmeasured velocity. A salient feature of the proposed approach is that wave-frequency motion components are filtered from the position and yaw angle sensor measurements to avoid mechanical wear and tear of the propulsion system components caused by wave-frequency motion signals. The result is extended to a wave-filtering finite-time self-learning extended state observer which improves the estimation performance considerably. The efficacy of the proposed two wave-filtering self-learning extend state observers for robotic surface vehicles with unknown control gains is substantiated via simulations.

Unmanned surface vehicles (USVs) have shown tremendous application prospects recently. In this paper, a hierarchical two-layer framework is proposed for the cooperative path planning of multi-USV system in complex marine environments. The whole framework incorporates the low-level layer planning the optimal path for each USV, and the high-level layer assigning targets for the multi-USV system. First, to avoid collisions and access multiple targets in the optimal sequence, an improved self-organizing map (SOM) based on window update is proposed. The energy cost is calculated to evaluate the path planning results and construct a similarity graph. Then, the spectral clustering method is utilized based on the customized graph to determine the allocated targets which each USV should access in the low-level layer. Finally, a double smoothing strategy based on B-spline is proposed, and the line-of-sight (LOS) guidance method and active disturbance rejection control (ADRC) controller are used to achieve accurate tracking of paths by USV. The simulation results in various scenarios validate the feasibility and effectiveness of our method for multi-USV cooperation, as well as path traceability.

Unmanned vehicles are often required to execute critical missions in harsh environment, causing system failure which may occur during the mission execution or rescue procedure. Existing research has focused primarily on policies during mission execution to reduce failure risk. The paper investigates risk evaluation and control policies both in the mission execution and rescue phases, and proposes two-level rescue depot location policies and dynamic rescue policies including mission abort and maintenance policies for unmanned vehicle systems. Specifically, considering multi-state characteristics of unmanned vehicle systems, two-level rescue depots are introduced to satisfy maintenance demands by providing different types of maintenance. To improve survivability in the mission execution, dynamic mission abort policies are executed when the number of failed components reaches predetermined thresholds, and then a rescue procedure is initiated. During the rescue, elaborate designed rescue depots location and dynamic maintenance policies are developed to reduce the risk of failure in the rescue. After a successful rescue, unmanned vehicles can re-attempt missions. The recursive algorithm and discretization algorithm are used to derive and evaluate mission success probability, system survivability, and expected cost of losses, and optimization models based on three indicators are formulated. The superiority of the proposed policies is demonstrated by a case study of a UAV system.

This work concerns the problem of resilient state estimation for unmanned surface vehicle systems subject to integrity attacks under peak-bounded perturbations. A novel resilient remote state estimation method is proposed based on zonotopic reachability analysis. The compromised sensors are identified based on the so-called predicted output set and zonotope support strip. Then, a resilient state reachable set is obtained by using the sensor data from the remaining benign measurements. For enhancing the performance of estimation, segment minimization is introduced to optimize the obtained state reachable set. Simulation results are provided to testify the effectiveness of the proposed method.

Reliable object tracking is a key ingredient for maritime autonomous surface ship (MASS), which can perceive surrounding objects and predict their motion state. Existing tracking algorithms mainly rely on visual sensor, and their application background is predominantly concentrated in the field of unmanned vehicles. In this paper, a scheme of directly processing LiDAR point cloud is proposed to achieve accurate and stable multi-object tracking in nearshore scenario. Firstly, based on the point cloud clustering results, an object position and volume estimation method is investigated. Then, the geometric distribution and 3D shape descriptors are conceived to construct the time-varying affinity matrix. The data association results are forwarded into a Kalman Filter based tracker life management mechanism. Finally, the remaining scattered points and unqualified trackers are composed into a point set, which is then modeled by convex polygons. The real-world experiment results confirm the effectiveness of the proposed maritime perception framework in tracking objects and mapping the ambience in a bustling lake. Compared with annotated ground-truth, the average multi-object tracking precision and accuracy is 0.69m and 85%, respectively. And the average computational frequency achieves 29Hz. The proposed scheme successfully applies LiDAR to the field of sea surface object tracking, which provides a practical and meaningful reference for the application of LiDAR in MASS.

To address the challenge of local path planning in a complex, dynamic environment with multiple ships, we built an autonomous collision avoidance system based on deep reinforcement learning in open water. The system switches between path-tracking and collision avoidance modes in real time, during which any collision danger is perceived through encounter identification and risk calculation. Subsequently, the proximal policy optimization method is applied to design the state space, action space, and reward functions. Decision-making offers advantages in terms of continuous action space, perception of global navigation information, compliance with the International Regulations for Preventing Collisions at Sea (COLREGs), and smooth maneuverings. Simulations are performed under multi-ship encounter conditions, considering the ship hydrodynamic model, environmental disturbance force model, COLREGs, and good seamanship. The results indicate the effectiveness and ability of the proposed system to take appropriate action when faced with dangerous situations under rule constraints and diverse scenarios.

Information Sciences, Volumes 457–458, 2018, pp. 166-181

This paper is concerned with the output consensus problem of networked unmanned surface vehicle (USV) formation systems under a leader-follower structure. First, a 3-degrees-of-freedom motion model is established for USV systems subject to disturbances induced by wind and waves. Second, based on the motion model, both an incremental state observer and an incremental predictive controller are constructed to investigate the effects of network-induced delays and packet dropouts on the systems under study. Third, a novel incremental predictive control scheme is developed to ensure that the outputs of all USVs in the formation reach consensus asymptotically. Finally, an illustrative example is given to verify the effectiveness of the proposed incremental predictive control scheme for networked USV formation systems.

IFAC-PapersOnLine, Volume 49, Issue 23, 2016, pp. 121-126

The C-Enduro Unmanned Surface Vehicle (USV) is designed to operate at sea for extended periods of time (up to 3 months). To increase the endurance capability of the USV, an energy efficient path planning algorithm is developed. The proposed path planning algorithm integrates the Voronoi diagram, Visibility algorithm, Dijkstra search algorithm and takes also into account the sea current data. Ten USV simulated mission scenarios at different time of day and start/end points were analysed. The proposed approach shows that the amount of energy saved can be up to 21%. Moreover, the proposed algorithm can be used to calculate a collision free and energy efficient path to keep the USV safe and improve the USV capability. The safety distance between the USV and the coastline can also be configured by the user.

Energy, Volume 148, 2018, pp. 362-372

Although fossil fuels are the world's most abundant, economical, and reliable way for energy production, long-lasting usage, would cause serious issues and it is well established in scientific circles as a serious event. On the other hand, renewable energies play a key role as a substitute for energy production. The environmental issues and depletion of fossil fuels have paved opportunities to electric and hybrid vehicles, which use renewable resources, especially in transportation. This study examines solar power importance for energy system of an unmanned surface vehicle titled Morvarid, which is expected to do the bathymetry tasks autonomously. Before description major parts of Morvarid's energy system, the most important and related studies are reviewed. This is followed by selecting the most suitable components for Morvarid's energy system by numerical examination and modeling. A Plug-in hybrid management system with an 8 KWh capacity lithium-ion battery was proposed. The PV array area was modeled for the whole year and resulted that an array with 8 m² surface is the best option. The last section contains power management reliability and energy safety of the boat by experimental tests. The experimental test at Chitgar-lake revealed that the Morvarid's power generating system, which uses sun tracker, can produce about 5.8 KWh energy per day. The proposed energy management system optimizes the available energy usage to enable the boat to do its tasks up to 7 h per day during three cloudy days without charging. When using energy just for daily tasks, the boat does not even need plug-in charge at sunny days.

Ocean Engineering, Volume 106, 2015, pp. 496-514

The performance of four automatically-generated path planning behaviors is evaluated through field-testing. Experiments were conducted using a model-referenced trajectory planner, which was implemented on unmanned surface vehicles (USVs) of different size, thrust, and maneuverability characteristics. The planner combines a local search based on the Velocity Obstacles (VO) concept with a global, lattice-based search for a dynamically feasible trajectory (determined using models of the nonlinear dynamics, nonholonomic constraints, and low-level control of each system). Multiple low-level USV heading and speed controllers, varying in complexity from proportional control to nonlinear backstepping control, were tested with the planner. High planning performance is achieved by searching within a resolution-adaptive space of the USV׳s candidate motion goals. Sampling is constrained to ensure that the International Regulations for the Prevention of Collisions at Sea (COLREGs) are followed. Prior to on-water implementation, the system was fine-tuned in simulation. Four automatically-generated USV behaviors were demonstrated in on-water tests within a complex, static obstacle field: 1) Approach (USV approaches a fixed target); 2) Follow (USV approaches a moving target); 3) Single COLREGs-Compliant Crossing (USV approaches a fixed target while avoiding another vessel); and 4) Multiple COLREGs-Compliant Crossings (USV approaches a fixed target while avoiding an interference vessel multiple times).

Expert Systems with Applications, Volume 55, 2016, pp. 106-117

Trajectory tracking control for unmanned marine surface vessels (USV) is quite complex because of the strongly non-linearity of the system and the presence of uncertainties and environmental changing conditions. To face those issues, in this paper intelligent and conventional strategies are used as the main control framework for the rudder angle of an USV. The guidance law calculates the desired angle and estimates the trajectory based on the dynamic model of the autonomous ship, which has been generated from real data obtained from experiments with a scale prototype. The model accounts for the physical limitations of both the rudder and the ship propulsion system. An adaptive control law is first proposed which is suitable for any different trajectory and can deal with varying path shapes. This gain scheduling approach utilizes PID controllers whose tuning parameters have been optimized by genetic algorithms (GA) for the different operation points (GS-PID-GA). Besides, a fuzzy logic controller (FLC) is designed to deal with the uncertainties of the dynamics and to include the expertise of an operator. Simulations validate the effectiveness of the proposed control approaches that have been compared with conventional control.

Neurocomputing, Volume 182, 2016, pp. 255-266

A great amount of effort has been devoted to the study on Unmanned Surface Vehicles (USV) due to an increasing demand for their use in a variety of maritime applications. Real-time autonomous collision avoidance system is the pivotal issue here, in which reliable collision risk detection and the adoption of a plausible collision avoidance maneuver play a key role. Existing studies on this subject seldom integrate the COLREGS guidelines, however, and in order to ensure maritime safety, it is of fundamental importance that they should be obeyed at all times. In this paper, we presented an approach to real-time collision avoidance that complies with the COLREGS rules for USV. The Evidential Reasoning (ER) theory is employed to evaluate the collision risks with obstacles encountered and trigger a prompt warning of a potential collision. Then, we extend and adopt the optimal reciprocal collision avoidance (ORCA) algorithm so as to determine a collision avoidance maneuver that is COLREGS compliant. The proposed approach takes into consideration the fact that other obstacles also sense their surroundings and react accordingly, conforming to a practical marine situation when making a decision concerning collision-free motion. A number of simulations have been conducted in order to confirm the validity of the theoretic results obtained.