Search

Navigation safety at sea is vital for each autonomous surface vehicle (ASV), which involves the problem of motion planning in dynamic environments and their robust tracking through feedback control. We present a practical path-planning method that generates smooth trajectories for a marine vehicle traveling in an unknown environment, where obstacles are detected in real time by millimetre wave (mmWave) radar. Our approach introduces a polynomial curve to describe the lateral and longitudinal trajectories in the Frenet frame, known as the 'motion primitives', whose combination ensures that the planning area is properly covered. In addition, we can select a feasible, optimal and collision-free trajectory from such a set of motion primitives that is generated by considering the vehicle dynamics and comfort. The capabilities of proposed algorithm are demonstrated in the experiment with static and dynamic obstacles. [ABSTRACT FROM AUTHOR]

This paper focuses on the intervehicle security-based robust formation control of unmanned surface vehicles (USVs) to implement the formation switch mission. In the scheme, a novel adaptive potential ship (APS)-based guidance principle is developed to prevent intervehicle collisions, which is common and threatening when maneuvering a formation switch. By employing the artificial potential field (APF), the APS can program the real-time attitude reference for USVs by using the security intervehicle distance while achieving the path-following task. As for the control part, a robust adaptive formation control algorithm is proposed to effectively stabilize the USVs to the APS via the fusion of the disturbance observer (DOB) and by using the robust neural damping technique. Regarding the merits of the improved design of the DOB, the weight compression of the neural networks can effectively simplify the structure of the DOB and enhance the observation accuracy of the external disturbance. This can facilitate the avoidance of intervehicle collisions and guarantee the application of the theoretical algorithm in engineering practice. Considerable effort has been made to obtain the semiglobally uniform ultimate bounded (SGUUB) stability via theoretical analysis. Finally, with the sailing scene in a narrow channel, the simulated experiment is illustrated to verify the security performance of the proposed strategy. [ABSTRACT FROM AUTHOR]

In this article, we present one solution to the multitask formation and moving objects interception problem of autonomous surface vehicles (ASVs) using the graph-based approach. The investigated problem includes three subtasks, i.e., to steer agents to a desired geometric pattern, to assign the ASVs for intercepting the moving attacker and forming a new formation, respectively, and to revert to original desired formation after successful interception. A switching strategy is designed to make the ASV switch between different modes. To deal with the nonlinear dynamics of ASV and improve the robustness against model uncertainties and external disturbances, the adaptive backstepping technique is incorporated. It is shown that the group of ASVs can accomplish all the tasks with different courses of attackers. The work offers a more flexible solution for the ASV group where malicious attacker exists. The effectiveness of the proposed approach is illustrated by simulations. [ABSTRACT FROM AUTHOR]

In the environment perception stage of autonomous driving, vehicles need to track its surrounding objects quickly and accurately to avoid dangerous behaviors. Therefore, visual object tracking has important practical application value in autonomous driving system. However, the performance of most hierarchical convolutional feature trackers are limited by ignoring the complex environment of autonomous driving. In this paper, a novel Siamese Attention Network to explore the rich spatial and channel information of objects was proposed. Because of the lack of important information between the channel and the spatial position, the tracking performance is reduced by the challenges of illumination change and deformation. The spatial attention block and channel attention block focus on the importance of different spatial positions and channels, respectively. The effective fusion of the two makes our tracker achieve the state-of-the art performance of 0.300 in the EAO criterion of 2017, which exceeds the baseline by 5.7%. [ABSTRACT FROM AUTHOR]

This paper deals with the reference flight trajectory generation and planning problems for quadcopter Unmanned Aerial Vehicle (UAV). The reference flight trajectory is defined as the composition of path and motion functions. Both of them are generated by using quintic B-spline functions. Based on differential flatness approach, the quadcopter dynamical constraints are satisfied instantaneously by computing the induced aerodynamical moments and lift force. The optimal reference flight trajectory, with respect to the mission requirements and imposed constraints, is reached by manipulating the control points’ vectors of B-spline functions via a nonlinear constrained optimization method. The mission requirements are defined as a set of waypoints with their respective scheduled flight timetable. A minimum-energy cost function is developed to minimize the consumed energy and induced efforts by reference flight trajectory. For the need of the optimal overfly-times schedule, the overfly times with respect to the defined constraints and performance criteria are calculated. Numerical simulation results show the feasibility and effectiveness of the proposed optimization method. [ABSTRACT FROM AUTHOR]

Multi object tracking (MOT) is a key research technology in the environment sensing system of automatic driving, which is very important to driving safety. Online multi object tracking needs to accurately extend the trajectory of multiple objects without using future frame information, so it will face greater challenges. Most of the existing online MOT methods are anchor-based detectors, which have many misdetections and missed detection problems, and have a poor effect on the trajectory extension of adjacent object objects when they are occluded and overlapped. In this paper, we propose a discrimination learning online tracker that can effectively solve the occlusion problem based on an anchor-free detector. This method uses the different weight characteristics of the object when the occlusion occurs and realizes the extension of the competition trajectory through the discrimination module to prevent the ID-switch problem. In the experimental part, we compared the algorithm with other trackers on two public benchmark datasets, MOT16 and MOT17, and proved that our algorithm has achieved state-of-the-art performance, and conducted a qualitative analysis on the convincing autonomous driving dataset KITTI. [ABSTRACT FROM AUTHOR]

This paper studies a time-varying formation control problem of a swarm of autonomous surface vehicles (ASVs) with prescribed constraints. Every ASV suffers from unavailable velocities, saturated inputs, internal uncertainties, and external disturbances. A distributed finite-time performance-prescribed time-varying formation control method is proposed for ASVs. Specifically, an adaptive fuzzy state observer (AFSO) is firstly proposed to recover the unavailable velocity by using saturated inputs and estimated disturbances from the fuzzy logic system. Secondly, a tunnel prescribed performance (TPP) function is designed to limit tracking errors with a concise form and smaller overshoot. At the kinematic level, with TPP-based error transformation, a C 1 finite-time time-varying guidance law is proposed by using the smooth switch functions and recovered velocities. Next, a finite-time command filter based on Levant differentiator is presented to smooth the guidance signals. At the kinetic level, a C 1 finite-time saturated control law is developed with the estimated velocities and disturbances. Then, it proves that tracking errors of the proposed closed-loop system converge into a small neighborhood around the equilibrium within finite time while evolving under TPP constraints regardless of saturated inputs. Finally, comparison results are provided to demonstrate the effectiveness of the proposed distributed finite-time performance-prescribed time-varying formation control method. • Distributed finite-time performance-prescribed formation control method is proposed for ASVs. • The TPP with a concise form is developed to achieve smaller overshoot in a positive manner. • An adaptive fuzzy state observer is designed to recover unavailable velocities. [ABSTRACT FROM AUTHOR]

This paper is concerned with a coordinated search and rescue problem of heterogeneous ocean vehicle cluster composed of autonomous surface vehicles (ASVs) and autonomous underwater vehicles (AUVs) subject to model uncertainties and ocean disturbances. Firstly, a three dimensions (3D) cross domain kinematic controller with auto-stop function at the rescue points is designed for the coordinated ASV-AUV system by using a line-of-sight guidance law. Secondly, an event-triggered based communication mechanism is constructed to ensure that the ASV-AUV system can broadcast information at its trigger moments except to the auto-stop points. Finally, an adaptive motion control law based on a low-frequency learning fuzzy predictor is designed, which is able to filter out the high-frequency components of uncertainties and disturbances. The stability of the closed-loop system is proven by employing input-to-state stability and cascade stability analysis. Simulation results and numerical analysis show the effectiveness of the proposed 3D heterogeneous cross domain coordinated path following controller with auto-stop function for marine search and rescue. • In contrast to the existing coordinated path following controllers which applicable to a two-dimensional or three-dimensional coordinated control in the same domain, a three-dimensional cross domain coordinated controller with auto-stop function applicable to sea surface and underwater scenarios are constructed. • In contrast to the existing communication that cannot stop during the whole control period, a predictor-based event-triggered communication mechanism is proposed such that the narrow network band could be effectively alleviated, and the communication will be suspended at the rescue points. • In contrast to the existing predictor design methods, a low-frequency learning fuzzy predictors are presented not only to filter out high-frequency components of non-linearities uncertainties and unmodeled random external disturbances, but also to achieve fast adaptation. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of finite-time trajectory tracking for fully actuated autonomous surface vehicles without the velocity measurements, in the presence of uncertain parameters and complex environmental disturbances. Firstly, a generalized nonlinear finite-time extended state observer is proposed to recover the velocities and synthetic disturbances simultaneously. The generalized structure can further enhance the estimation accuracy and the observation errors are proved to be finite-time uniformly ultimately bounded stable. Then, a two-loop control law is developed by using virtual velocity command and fast non-singular integral terminal sliding controller. The observer is integrated with the controller to overcome the problem of unavailable surge, sway, yaw velocities and to rapidly reject disturbances, thereby contributing to fast and accurate trajectory tracking of the vehicle. Theoretical analysis for finite-time stability of the closed-loop system is rigorously derived through the Lyapunov's stability theory. Finally, comparative simulation results are given to illustrate the effectiveness and superiority of the proposed control approach. • A GNFTESO is proposed to observe the velocities and external disturbances accurately. • The GNFTESO can estimate the unavailable information in body-fixed frame using the position-heading measurements of the inertial frame. • Tracking errors of the ASV are forced to enter a small neighborhood of the origin in a finite time. • High accuracy, faster convergence, and continuous structure are remarkable features. [ABSTRACT FROM AUTHOR]

This paper investigates a parameterized path-guided following/maneuvering control problem of an autonomous surface vehicle (ASV) subject to actuator faults via a noncooperative game strategy. Unlike the existing path maneuvering control methods, the noncooperative game of this paper includes two sub-games. On one hand, the path update is considered to be against the effort of kinematic control. On the other hand, the kinetic control is considered to be against the total disturbances consisting of actuator faults and external disturbances. A robust adaptive fault-tolerant path maneuvering controller is designed based on a noncooperative game approach. Specifically, we design a kinematic control law using an improved dynamic surface control approach to achieve the geometric objective. An improved neural predictor is constructed, in which a concurrent learning-based adaptation is designed to identify unknown fault coefficients. A path update law and a kinetic control law are calculated to cover noncooperative games by using an adaptive dynamic programming approach. Theoretical analysis shows that the closed-loop system is input-to-state stable, and the proposed method can meet the geometric objective, the dynamic objective, and the fault-tolerant objective. Finally, simulation results demonstrate the efficacy of the proposed robust adaptive fault-tolerant control method for path maneuvering. • A noncooperative game-based variable tuning law is proposed for path update. • A fault-tolerant control method is developed using a noncooperative game strategy. • An improved neural predictor is designed for identifying fault coefficients. [ABSTRACT FROM AUTHOR]

This paper proposes a guidance strategy and a controller based on end-to-end deep reinforcement learning (DRL) to address the problem of unmanned surface vehicles (USVs) interception and obstacle avoidance. A deep deterministic policy gradient (DDPG) algorithm is introduced to generate the interception strategy, a reward function with multiple objectives is designed. The artificial potential field (APF) method is used to obtain an evasion strategy for target USVs, enabling the target USVs to perform evasive actions in reaction to the interception. To find a trade-off between the time consumption and the safety of obstacle avoidance, a multi-objective equilibrium method is proposed. An incremental proportion regulator based on prior knowledge is used to dynamically modify the reward function. Besides, a virtual-reality 3D simulator based on ROS and Gazebo is constructed to present the process of interception. To demonstrate the effectiveness of the proposed method, simulation results are presented. Compared to the original DDPG algorithm, the proposed multi-objective equilibrium method shortens the interception path while ensuring the safety of obstacle avoidance. Compared to the traditional model-based approach, the DRL-based controller shows better performance in interception missions, and the robustness of the proposed controller for dynamic obstacles are shown in multiple tests. • End-to-end learning is used to obtain a strategy that can intercept evading targets. • Achieve both interception and avoidance, as shorten the interception path. • Trade-off between interception and avoidance based on multi-objective equilibrium. • A virtual-reality 3D simulator is constructed by using ROS and Gazebo. [ABSTRACT FROM AUTHOR]

This paper presents an adaptive event-triggered control algorithm for sail-assisted unmanned surface vehicle (USV) under nonlinear modified logic virtual ship (LVS) guidance, which addresses the issues of communication load and input saturation constraint. In guidance module, the reference signal generated by LVS guidance is further processed by nonlinear modification rules. That can effectively remove the abrupt phenomenon of actuators. In the control module, a robust adaptive control technique for sail-assisted USV is proposed by fusing adaptive compensation technology and hybrid threshold event-triggered. Unnecessary transmission is reduced between controller and actuator by constructing hybrid threshold event-triggered mechanism. Different from most existing event-triggered mechanism with fixed threshold parameters, threshold parameters in hybrid threshold event-triggered are dynamically adjusted according to the demands of the controller. Furthermore, the compensation effect of sail on the dynamic mechanism is considered. Adaptive parameters of rudder and propeller are constructed to improve the robustness of the closed-loop system. Finally, the theoretical stability of the proposed method is proved by Lyapunov stability theorem, and the control performance is evaluated by simulation platform, which verifies that the scheme has reliable tracking accuracy under time-varying disturbances. • The nonlinear modified LVS principle is proposed to improve sail acting performance. • The hybrid threshold parameter setting can obtain satisfactory resource efficiency. • It can be effectively released the coupling effect of sail force on power mechanism. • The triggered state variables are semi-globally uniform ultimate bounded stable. [ABSTRACT FROM AUTHOR]

A crucial and challenging issue in path following control of the autonomous surface vehicle (ASV) is input constraint and communication burden. In this paper, an intervened logic virtual ship (ILVS) guidance is developed to generate the reference signal, and further to tackle the input saturation constraint by employing the dynamic feedback evaluation rule. The main superiority of this design is to intervene the logic virtual ship (LVS) guidance principle to avoid the persistent large stabilization error. Associated with ILVS guidance framework, a robust adaptive neural event-triggered algorithm is proposed for the ASV by fusing the adaptive technique and the multiport event-triggered approach. The constrains of the model nonlinear term and the uncertain actuators gain are released by constructing online learning parameters. Furthermore, the channel resource from the sensor to the controller (SC) as well as the controller to the actuator (CA) is reduced for merits of the multiport event-triggered approach. The feedback error signals and the control inputs will be updated while the triggered condition is occurred. That also can eliminate the low frequency disturbance, caused by marine environment, to improve the robustness of the closed-loop system. Through the Lyapunov stability criterion, all state variables in the triggered point and triggered interval are achieved semi-global uniform ultimate bounded (SGUUB) stability. Finally, the control performance of the proposed method is evaluated on simulation platform, showing the satisfied tracking accuracy with the low transmission load. • The robust adaptive neural event-triggered control algorithm is proposed for the autonomous surface vehicle (ASV). • The developed intervened logic virtual ship (ILVS) guidance can generate the reference signal, and further to tackle the input saturation constraint. • The computing resource from the sensor to the controller, the transmission load from the controller to the actuator are reduced simultaneously. • All the state variables in the triggered point and triggered interval are achieved semi-global uniform ultimate bounded (SGUUB) stability. [ABSTRACT FROM AUTHOR]

This article investigates the trajectory tracking control of fully actuated unmanned surface vehicles (USVs) in the presence of lumped system uncertainty and input saturation. To address this problem, an output feedback scheme, which combines the saturated adaptive super twisting algorithm and non-singular fast terminal sliding mode (SASTA-NFTSM) technique, is proposed. First, the velocities and lumped system uncertainty including external disturbances and model uncertainties, are estimated by a finite-time extended state observer (FTESO), simultaneously in finite time. Second, to deal with the saturation constraints on actuators, a novel sliding mode reaching law scheme, namely SASTA, that consists of an anti-windup compensator and a super twisting algorithm based on switching logic adaptive gains is proposed. Finally, the trajectory tracking control of USVs is solved with the non-trivial combination of SASTA and NFTSM. The chattering phenomenon can be effectively attenuated by virtue of the continuous control laws compared with the traditional NFTSM control (NFTSMC) approaches. The tracking errors are guaranteed to converge to zero in finite time. Comparative simulation results demonstrate the effectiveness and advantage of the proposed scheme. • A novel sliding mode reaching law, namely SASTA, that consists of an improved anti-wind auxiliary system and a switching logic based ASTA, is proposed. • A sliding mode control scheme combining the NFTSM and SASTA is designed. Both finite-time convergence to the manifold and the equilibrium point on the sliding surface can be achieved. • A finite-time output feedback based on SASTA-NFTSM is designed for trajectory tracking system of USVs, with excellent anti-chattering ability. [ABSTRACT FROM AUTHOR]

This paper presents a cooperative vector field approach for synchronized path following of multiple autonomous surface vehicles (USVs) with limited communication resources. First, a cooperative vector field is proposed by introducing a path coordination design into a three-dimensional vector field. Based on the cooperative vector field, concise guidance laws of surge speed and angular rate are derived for synchronized path following. In order to reduce communication times among USVs, an event-triggered cooperative vector field is next proposed. Specifically, a predictor is devised to predict the current path variables by using the last transmitting ones, and an event-triggered mechanism is developed based on the predicted path variables. Then, a self-triggered cooperative vector field is developed to avoid continuous listening. A self-triggered mechanism is designed such that each USV predicts its next triggering time and broadcasts it to its neighbors at the current triggering time. The stability of the three cooperative vector fields is analyzed, and Zeno behavior is excluded. Finally, both simulation and experiment results are provided to illustrate the efficacy of the proposed continuous, event-triggered, and self-triggered cooperative vector fields for resource-aware synchronized path following. [ABSTRACT FROM AUTHOR]

This paper investigates a novel robust adaptive fault-tolerant control algorithm for the path-following activity of the unmanned surface vehicle (USV) via the multiplied event-triggered mechanism. An improved multiplied event-triggered condition is designed by employing the estimate model with a concise form. Thus, the burden-some problem is released, especially for the channel from sensors to the controller. Besides, two discrete adaptive parameters are constructed to stabilize the perturbation caused by the gain constraint and actuator faults. The model uncertainties and the practical disturbance are compensated by utilizing neural networks (NNs) approximation, in which the weight updating is reduced with the robust neural damping technique. With the direct Lyapunov theorem, the semi-global uniformly ultimately bounded (SGUUB) stability can be guaranteed for the closed-loop system. Finally, both the simulation and the physical vehicle-based experiments are illustrated to verify the effectiveness of the algorithm. • A robust fault-tolerant control algorithm is proposed for unmanned surface vehicle. • The adaptive parameters are updated online to compensate for unknown actuator faults. • An improved multiplied event-triggered condition is designed with a concise form. • It can evade the unnecessary information transmission of the onboard control network. [ABSTRACT FROM AUTHOR]

This paper investigates a performance-guaranteed formation tracking problem of autonomous surface vehicles (ASVs) under uncertain environments. Especially, model uncertainties, external disturbances and actuator faults exist simultaneously. Based on graph theory and adaptive techniques, a novel two-layer robust adaptive fault-tolerant formation scheme is developed. In kinematic layer, a transformation is made to get a performance unconstrained problem and an adaptive control strategy is incorporated to stabilize transformed errors. In kinetic layer, two types of robust adaptive fault-tolerant formation controllers, i.e. the fault-based one and the fault-unknown one, are designed for different fault scenarios. These controllers share the same structure of single-parameter updating laws to adjust adaptive parameters. It is shown that: 1) using the proposed formation scheme with either designed fault-tolerant controller, desired formation configurations of ASVs are achieved if the interaction topology is connected and control parameters satisfy given conditions; 2) prescribed formation tracking performance can be ensured and all error signals are guaranteed to be uniformly ultimately bounded; 3) a trade-off between two designed controllers exists, that is although the assumption for fault-unknown controller is weaker, larger control parameters are required to behave like fault-based one. Simulations and comparisons are provided to illustrate the effectiveness of theoretical results. • A novel formation scheme is designed with an adaptive strategy in kinematic layer. • Two adaptive fault-tolerant formation controllers are designed in proposed scheme. • A general structure of single-parameter adaptive laws is given for both controllers. • Parameter selection is analyzed and a trade-off between two controllers is observed. [ABSTRACT FROM AUTHOR]