Search

When performing complex tasks such as position transfer and material transportation, the distributed driving unmanned platform with variable configurations needs to address the challenge of multi-wheel cooperative torque distribution control to achieve high-performance differential steering and enhance vehicle dynamics. The configuration change will impact the dynamic performance of the unmanned platform, posing a challenge to the performance of the existing control strategy based on mathematical model development. In order to address the aforementioned issues, this paper analyzes the impact of changes in vehicle configuration on steering gain and proposes a hierarchical adaptive differential steering strategy based on variable vehicle configurations. Firstly, the response characteristics of the yaw angle relative to the active yaw moment under the influence of changes in wheelbase and tread are analyzed. Based on this analysis, two structural modes, maneuverable and balanced, are selected. Secondly, a localized-modelling sliding mode control method with an extended state observer is proposed to estimate the desired yaw moment in the upper controller, considering the motor's execution delay. Then, the lower controller optimizes the torque of each wheel in real-time using the whale optimization algorithm. It aims to optimize tire energy dissipation and tire load rate while ensuring driving stability and achieving differential steering. Finally, through co-simulation and experiments on a scaled prototype, the reliability of the dynamics theory and the superiority of the control algorithm are validated. This optimization has led to significant improvements in the tire dissipation energy index and tire load rate index. • An adaptive differential steering control strategy is proposed for the UGV with variable configurations. • The localized-modelling sliding mode control with extended state observer is proposed to obtain the desired yaw moment. • The vertical tire load and slip energy are optimized. • The proposed strategy is validated by co-simulation and experiment results. [ABSTRACT FROM AUTHOR]

This article studies the distributed formation control problem for multiple unmanned surface vehicles (USVs) considering uncertain coefficient matrixes, unmeasurable velocities, and time-varying disturbances. The main contributions are as follows: First, a global coordinate translation is proposed to partially linearize the nonlinear dynamic model equipped with the unmeasurable velocity. Second, based on the global coordinate translation, a novel type of fixed-time extended two-state observer (FTETSO) is developed to estimate unmeasurable velocities and total disturbances for each vehicle. Wherein, the estimation errors will converge to zero within a fixed time. Meanwhile, considering estimation accuracy, a two-state extension is proposed to replace a single-state extension. Third, using a sliding model-based control technique, an FTETSO-based distributed global output-feedback fixed-time formation controller (GOFFC) is elaborately developed. Based on the proposed controller, the fixed-time convergence of the closed-loop system is ensured. Finally, the validity and stability of the proposed control approach are verified by simulations. • A newly introduced decoupling technique can guarantee global stability. • A novel fixed-time extended two-state observer is proposed. • A distributed global output-feedback fixed-time formation control scheme is proposed. • The observation errors and tracking errors converge to zero in a fixed time. [ABSTRACT FROM AUTHOR]

During the operation of six-wheel independent drive unmanned ground vehicle (6WID UGV) in the field, the inconsistent tire contact characteristics and frequent steering maneuvers have led to increasingly prominent issues of tire excessive wear and lateral instability. Therefore, a coordinated hierarchical controller for 6WID UGV is proposed to ensure the stability of the steering process while reducing tire wear and motor energy consumption. First, a sliding mode controller (SMC) with an extended-state observer (ESO) is proposed for lateral stability control referencing the active disturbance rejection control (ADRC) technique, achieving fast response and robustness to uncertainty. Second, the lower controller constructs a Lagrangian function with tire slip energy loss and energy consumption as optimization objectives and allocates torque based on the Pareto optimal solution within the feasible domain given by the upper controller. Finally, the designed controller is tested under typical operating conditions. The results indicate that the designed coordinated controller has significant control performance and economic benefits in improving lateral stability and reducing energy loss. Compared with the torque distribution strategy based on tire vertical load, the tire slip energy is reduced by 44.8 % and 17.7 % in the process of traction/steering and braking/steering, respectively. In addition, the motor energy consumption and the friction braking energy loss are reduced by 12.1 % and 70.8 % respectively. • The hierarchical coordinated control strategy is proposed to maintain the stability with the minimum energy loss. • The extended state observer is used to eliminate the influence of uncertainty. • The torque distribution strategy is proposed to reduce tire slip energy loss and tire wear. [ABSTRACT FROM AUTHOR]

In this note, a wave simulation method based on the wave spectrum is proposed, and the wave simulation is transformed into external interference to verify the necessity of using variable encounter angle real wave interference. Firstly, A wave simulation method based on wave spectrum and equidistant method is proposed and demonstrated. Secondly, wave modeling is transformed into interference force related to the encounter angle by fully considering the real marine environment. Furthermore, a trajectory tracking controller with variable encounter angles and the actual sea state is designed using the disturbance modeling method. Finally, the necessity and authenticity of considering varying encounter angles and real sea conditions in the motion control of unmanned surface vehicles (USVs) are proved by simulation. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of guidance and control for underactuated unmanned surface vehicles (USVs) with state constraints and input saturation, in support of enabling an underactuated USV to follow a parameterized curved path in the case of unknown sideslip angle and cross-tracking error constraint. First, a cross-tracking error constraint line-of-sight (LOS) guidance law with sideslip angle compensation is originally designed to guide an underactuated USV to convergence to the desired path within a time-varying cross-tracking error constraint. Second, a novel nonlinear mapping (NM) function is first constructed to map the heading and surge control subsystems with state constraints to unconstrained nonlinear systems, transforming the constrained control problem into the unconstrained control problem. Subsequently, adaptive fuzzy control laws are designed to achieve the control objectives for the USV using the new unconstrained nonlinear systems with unknown disturbance and input saturation. Then, a series of theoretical analyses using input-to-state stability theories are presented to prove the boundness of the tracking errors for the underactuated USV during path following. Finally, numerical results obtained using a physics-based simulation model are shown to reveal the effectiveness of the guidance and control algorithms. • Design a cross-tracking error constraint LOS guidance algorithm with sideslip compensation. • Propose a novel nonlinear mapping function to deal with the constraint control for nonlinear systems. • Construct the unconstrained nonlinear system by the proposed nonlinear mapping function. • Propose adaptive fuzzy control laws with input saturation using the new unconstrained nonlinear system. [ABSTRACT FROM AUTHOR]

• An end-to-end network combining deep learning and broad learning system. • The network has an incremental learning ability. • A pose estimation method based on a cooperative mark with concentric circles. • Superior computing speed on CPU. This paper proposes an efficient relative localization and object detection network (AeroNet) based on incremental learning for minimalistic high-speed cooperative navigation of aerial-ground unmanned vehicles in cluttered environments. Due to highly limited computation capability and memory resources in micro-UAVs, YOLO series are applied as the baseline of object detection network, and a lightweight backbone is built based on the depthwise separable convolution. To improve the real-time performance, the detection head is formulated with broad learning system. Besides, 6D relative pose estimation is achieved via equation fitting of an elliptical cooperative mark. To verify the effectiveness of AeroNet, experiments are conducted on Intel NUC and NVIDIA TX2 with our self-collected dataset. Results show that AeroNet can progressively increase the accuracy of object detection to 89%, and the computational time is only 76ms on Intel NUC and 28ms on Nvidia TX2, respectively, which meet the need of real-time requirement of on-board calculation in micro-UAV avionics systems. [ABSTRACT FROM AUTHOR]

In this paper, we propose an intelligent contactless delivery scheme for unmanned vehicles based on multi-source sensing signals. Our objective is to address the problem of delivering items in special scenarios that require contactless delivery, such as hospital isolation areas and isolated hotels. Specifically, we apply the simultaneous localization and map construction (SLAM) algorithm to solve the localization and map construction problem when the unmanned vehicle moves in an unknown environment. Additionally, we improve the open-source Cartographer algorithm and use sensors such as LiDAR and depth camera to achieve localization, multi-terrain map construction, automatic navigation, and obstacle avoidance. We experimentally test the map construction, navigation, and obstacle avoidance capabilities of the smart cart in specific scenarios. Our results demonstrate that our proposed smart delivery solution works effectively in urban indoor and outdoor scenarios and can be applied to practical contactless delivery scenarios. This new non-contact delivery mode is expected to be a driving force for future development. [ABSTRACT FROM AUTHOR]

Given that the internal states of a system, such as position, velocity, acceleration, and other important factors, naturally obey the integral processes of a physical system in kinematics, this paper presents an adaptive noise filtering system that can reconstruct these system states at the kinematic level. This is done without using any prior knowledge of the statistical properties of measurement noises. In the proposed filtering system here, each noise-contaminated estimated state is filtered by an average filter to compensate for phase delay and amplitude distortion. Unlike existing model-based estimation methods, the dynamic equation is not explicitly used in the proposed method, and the uncertainties in the nonlinear dynamic equation can be isolated. Furthermore, this application is much more straightforward as there are no gains to be processed. To verify our proposed adaptive filtering system, it has been applied to a variable speed path-following control task for unmanned surface vehicles (USVs), where accurate system states must be known. In particular, this paper also proposes a state-constrained finite-time control framework to realize the path-following control objectives. The proposed controller here mainly consists of two parts, i.e., an online state-constrained polynomial planning function and an execution of an algebraic control law. Simulations and experiments have been conducted to validate the effectiveness and reliability of the proposed filtering system and the finite-time controller. The results show that the proposed filtering system considerably outperformed several of conventional observers such as the extended Kalman filter (EKF), the passive observer, as well as the high-order differentiator. • An adaptive filtering system is proposed to reconstruct a system's full states. • It is not necessary to know the statistical properties of measurement noises. • A state-constraint controller is proposed to realize the USV path-following task. • Experiments have been conducted to validate the proposed methods. [ABSTRACT FROM AUTHOR]

With the rapid development of offshore exploration, autonomous underwater vehicles (AUVs) have come in great diversities depending on their particular specifications in civil and military practices. We focus on AUV swarms in the shallow ocean for their potentialities in economic and military uses as well as in scientific investigations. Nowadays, the advanced technologies of perception, communication, and control in underwater environment give the AUV abilities to perform certain tasks in the shallow ocean. Still, many missions require the large-scale AUV swarms due to the complexities of the tasks and the uncertainties of the environment. In this paper, we start with the introduction of underwater technologies in AUVs. Then we induce the AUV swarms and present several key methods to form swarms and to keep collaboration. Finally, we propose some necessitates technological advances that can facilitate the application of the AUV swarms in the shallow ocean. [ABSTRACT FROM AUTHOR]

• A new criterion for the boundedness and asymptotic stability of NCN on time scales under impulsive control is proposed. • The results show that constrained nonlinearity plays an important role in the global boundedness of nonautonomous complex networks under impulsive control. • An application is given for the bounded driving of unmanned vehicles. This paper discusses time-scale type global boundedness of nonautonomous complex networks (NCNs) under impulsive control. By using constraint nonlinearity of NCNs, properties of exponential function and impulsive inequalities, we establish new sufficient conditions for global boundedness and asymptotic stability of NCNs on time scales, and the upper bound of the system can be calculated easily. It is shown that the constraint nonlinearity and impulse interval length will affect the estimation of state bound of NCNs under different network size. It provides a unified criteria for global boundedness of NCNs on continuous, discrete and mixed-time domains and hence improves corresponding existing ones. The nonlinear constraints studied in this paper are widely applied to Lurie systems, ball motion models and so on. Numerical examples are given to illustrate the correctness of the results. Finally, the theoretical results are applied to Lurie systems and bounded driving of unmanned vehicles. [ABSTRACT FROM AUTHOR]

• Teleoperation of vehicles has safety and economic benefits. • Time delay in the cellular network is a key challenge for safe teleoperation. • Effects of small delays on performance in simulated inter-urban scenarios were tested. • A 250 ms delay significantly impinged on performance relative to a 50 ms delay. • Policy makers should consider that even small delays matter. Time delay in communication networks is a major challenge in controlling vehicles from remote centers (also known as teleoperation). In the current study, we investigated the effects of time delay in controlled and partly controlled driving environments at higher driving speeds and in relatively short time delays (50 ms, 150 ms, and 250 ms) which characterise the 5G era. Participants (N = 72) faced several challenges while operating a vehicle in a simulated scenario. The challenges started with following a lead vehicle on a curve, continued with responding to a sudden brake of the lead vehicle, and concluded with highway driving among other simulated road users. The speed, the distance to other vehicles, the brake and swerving of the vehicle and the crash rate were measured during each scenario. At the end of the scenario, participants completed the NASA-TLX. We found that at a time delay of 250 ms (but not 150 ms), following a lead vehicle on a curved road was characterized by a higher standard deviation of speed and distance to the lead vehicle and stronger swerving than at the shorter time delay of 50 ms. Swerving was also stronger at the 250 ms than at the 50 ms delay on the highway. Finally, crashes, which occurred mainly on the highway and in response to the sudden brake of the lead vehicle (before the highway), were 20 % (not statistically significant) higher at the 250 ms than at the 50 ms delay. The gap in collision frequency between the 150 ms and 50 ms delay was lower (8 %) and not statistically significant. This relatively small gap corresponded with the insignificant changes between 150 ms and 50 ms delay on the other indices of driving safety that we analyzed (e.g., braking and swerving). Regarding the NASA-TLX, participants rated the 250 ms delay higher than the other delays on almost all dimensions except for effort on which they did not distinguish between the 250 ms and the 150 ms delay. Our findings expand current knowledge on the effects of time delay on teleoperation. In the Discussion section, we translate this knowledge into practical recommendations regarding possible delays in teleoperation and possible countermeasures for the time delay. [ABSTRACT FROM AUTHOR]

This analysis examined systemic causes of Uncrewed Air Vehicle (UAV) accidents identifying operator, environmental, supervisory, and organisational factors through the use of the Human Factors Analysis and Classification System (HFACS). HFACS is a system-based analysis method for investigating the causal factors associated with accidents and incidents and has previously been used to reliably and systematically identify active and latent failures associated with both military and general aviation accidents. Whilst HFACS has previously been applied to UAV accidents, the last known application was conducted in 2014. Using reports retrieved from nine accident investigation organisations' databases, causal factors were coded against unsafe acts, preconditions, and failures at the supervisory, organisational, and environmental levels. Causal factors were assessed on 77 medium or large UAV mishaps/accidents that occurred over a 12-year period up to 2024. 42 mishap reports were deemed to involve a human factor as a causal factor. A large proportion of the mishaps contained factors attributed to Decision Errors at level 1 (Unsafe Acts) which was found to be associated with both the Technological Environment and Adverse Mental State at level 2 (Pre-conditions). Causal factors were identified at each of the other 3 levels (Supervisory, Organisational and External) with a number of emergent associations between causal factors. These data provide support for the identification and development of interventions aimed at improving the safety of organisations and advice of regulators for Uncrewed Air Systems. [ABSTRACT FROM AUTHOR]

This paper proposes a distributed dynamic event-triggered control that addresses the flocking control problem with a virtual leader for multiple unmanned surface vehicle (USV) systems. Unlike existing flocking algorithms, which often result in the formation of quasi α-lattice structures, the proposed approach combines artificial potential functions (APF), directionally consistent potential functions (DCPF), and a navigation feedback term to form an α-lattice. A novel artificial potential function is developed to facilitate flocking and maintain a safe distance between USVs to avoid collisions. Additionally, a dynamic event-triggered mechanism, initially employed in flocking control, is introduced to reduce communication among USVs. Furthermore, it is demonstrated that Zeno behavior does not occur. The algorithm employs Radial Basis Function Neural Networks (RBFNNs) and adaptive algorithms to dynamically estimate and compensate for parameter uncertainties and external disturbances. Finally, the effectiveness and robustness of the proposed algorithm are verified through numerical simulation. • A distributed dynamic event-triggered control is proposed for the first time to study the flocking problem in multi-USV systems. • A smooth artificial potential function is designed to take into account the collision avoidance problem among non-pointed agents. • A smooth artificial potential function is designed to guarantee the function with a bound cut-off. [ABSTRACT FROM AUTHOR]

Lacking a long-term power supply restricts the endurance of unmanned surface vehicles (USVs) and their application in remote sea areas. To address that ptoblem, a reliable solution based on the utilisation of wave energy is proposed in this study, where a wave-excited energy harvester is integrated into the USV. A fully coupled mathematical model is established to describe the dynamics and the electricity generation performance of the integrated system, considering the coupling of the mooring system. Numerical results given by this mathematical model are validated by physical experiments. The influence of the external load, the wave height, the wave period, the pendulum length, the pendulum mass and the mooring system on the system's performance are investigated, respectively. Experimental results of two small-scale prototypes, performed in a wave flume, show that the time-averaged generated electrical power is up to 324.89 mW when the wave height is 9.00 cm and the wave period is 1.72 s , where the corresponding wave-to-wire efficiency is 9.72%. Results indicate that the pendulum length, the pendulum mass, and the configuration of the mooring system significantly influence the resonant period and bandwidth. • A new wave-powered USV based on an inertial pendulum is proposed. • The proposed wave energy harvester has the capability to tune natural frequency. • A time-averaged electric power of 324.89 mW is achieved under a flume wave height of 9 cm. • The mooring system has a significant effect on the bandwidth of the USV. [ABSTRACT FROM AUTHOR]

One of the most valuable and promising applications for Unmanned aerial vehicles (UAVs) is in natural disaster management, where these aircraft can operate autonomously without any need for human intervention during their flights. In this paper, we foster the interface of Operational Research with computer science in general and sensor networking in particular by focusing on managing a post-disaster emergency scenario where the use of a fleet of UAVs helps rescue teams identify people needing help inside an affected area. We model this situation as an original graph theoretical problem called Multi-Depot Multi-Trip Vehicle Routing Problem with Total Completion Time minimization (MDMT-VRP-TCT). The main novelty of the MDMT-VRP-TCT is the combination of the following three features: multi-depot, multi-trip, and completion time minimization. We propose a mixed-integer linear programming (MILP) formulation, develop a matheuristic framework to address large instances, and present an extended set of experiments to test the performance of the proposed matheuristic: first, we compare the matheuristic with the MILP formulation on a set of small instances (up to 30 nodes); then, we compare our matheuristic with two heuristics from networking literature, showing that it outperforms the existing algorithms. [ABSTRACT FROM AUTHOR]

In this paper, an observer-based fixed-time tracking control strategy is presented for unmanned surface vehicles (USVs) with model uncertainties, external disturbances, and actuator faults. Firstly, as the theory foundation, a fast fixed-time stable system that has a shorter settling time than the existing systems is proposed. According to this system and the motion characteristics of an USV, a fast fixed-time disturbance observer is developed to obtain the unknown effects caused by lumped uncertainties. By combining the estimated knowledge and a nonsingular fast fixed-time terminal sliding surface, a robust fast fixed-time trajectory tracking controller is designed for the USV. According to Lyapunov stability theory, the fast fixed-time convergence of the proposed controller is proved. Finally, the simulation results demonstrate the effectiveness of the developed control scheme. • A fast fixed-time stable system is proposed to design a control scheme for an USV. • Based on the system, an observer is designed to estimate the lumped uncertainties. • A fast fixed-time nonsingular terminal sliding mode controller is proposed. [ABSTRACT FROM AUTHOR]

Unmanned ground vehicle (UGV) is developing towards high mobility and intelligence, where path tracking plays a particularly important role. This paper investigated the path tracking control strategy of variable-configuration unmanned ground vehicle. In order to overcome the structural and unstructured uncertainties, a model free predictive control (MFAPC) strategy using particle swarm optimization (PSO) is presented. The control scheme of MFAPC is improved by integrating vehicle state parameters. Then, the main parameters of the improved control scheme are optimized by PSO algorithm. The effectiveness of the proposed method under different operation conditions is verified by simulation. The experimental results show that the proposed scheme does not require the accurate mathematical model and can quickly track the reference path. • The path tracking control of variable configuration 6WID UGV is studied. • An improved model free predictive control scheme is proposed. • The effectiveness of the proposed scheme is validated by test. [ABSTRACT FROM AUTHOR]

The adaptive containment control problem with collision avoidance is investigated for unmanned surface vehicles (USVs). At first, the finite time disturbance observer is developed to present the estimation and compensation of external disturbance. Then, incorporating the artificial potential and radial basis function into the new containment strategy, all followers can enter the convex hull spanned by leaders while the collision is avoided. Furthermore, it is demonstrated that the error signals in the closed-loop system are boundedness by employing Lyapunov stability. Simulation studies finally manifest the effectiveness of proposed method. • The paper achieves the containment control of unmanned surface vehicles with collision avoidance. • To approximate the model uncertainties, the containment control law with neural network is developed. • The finite-time disturbance observer provides an estimation and compensation of the disturbance. [ABSTRACT FROM AUTHOR]

The issues related to the reliability of hydrogen engines of unmanned vehicles and increasing the efficiency of using hydrogen as fuel when using the method of its production during the decomposition of hydrogen-containing molecules of liquid-phase organic compounds in a plasma discharge under the action of intense ultrasonic exposure are considered. Experiments have shown that as a result of decomposition in the acoustoplasma discharge of liquid hydrocarbons, solid-phase carbon-containing products are formed, chemical transformations occur in the liquid phase and hydrogen-containing combustible gas is formed. Hydrogen-containing gas can be used as fuel immediately after synthesis, i.e. it does not require separation, since in addition to hydrogen it contains only impurities of CO 2 and water vapor. The purpose of the study is to formalize the basic conditions for tightening the control of mutual compliance with the efficiency of hydrogen engines of the same series in the conditions of their mass production. Methods of mathematical statistics and hardware-software modeling were used in the study. The term "unerroric of quality mutual compliance control" is introduced to describe a set of hardware and software tools for such control. The principle of in-depth testing of the technical condition of such engines of one series is described in a multidimensional formulation of the quality control problem for three of their operating parameters at once. The conditions for increasing the mutual correspondence of the measured values of such parameters in the conditions of serial production of hydrogen engines are formalized. [ABSTRACT FROM AUTHOR]

Unmanned surface vehicles (USVs) are gaining significant interest, particularly in support of complex maritime operations. To ensure efficient autonomous operation of the USV swarm in the case of multi-type missions, a task allocation system that combines off-line and on-line task allocation is constructed in this paper. The task set of each USV is obtained by improved genetic algorithm (GA). A distance matrix of these tasks is calculated by fast marching method (FMM) and integrated into the self-attention mechanism (SAM). The algorithm can shorten swarm's total voyage and make USVs' task load balanced. Furthermore, to accommodate the situations of task addition, deletion, and failure of USVs, an on-line task reallocation algorithm called the improved contract net protocol and vacancy chain (ICNP-VC) is developed. It unites the contract net protocol (CNP) and vacancy chain (VC) to enhance the intelligence of USVs. The ICNP-VC modifies the content of the bid and distinguishes the type of the cost. Meanwhile, the algorithm can balance the task load of the cluster and reduces the waste of resources. Through extensive simulations, demonstrate the proposed algorithms' capability to optimize task allocation and plan safe paths, leading to improved performance in complex marine scenarios. • A new off-line task allocation method for USVs swarm is proposed, which has a shorter total voyage of USVs and smaller relative time deviation and is applicable to complex environments with multiple static obstacles. • A new method is proposed to optimize the task sequence of USVs so that higher priority or time-bound tasks are processed first and is suitable for multi-type task situations. • A new on-line task reallocation algorithm is proposed to improve the performance of load balancing and reduce the waste of resources when meeting burst situations in complex scenarios. [ABSTRACT FROM AUTHOR]

The instability of vehicle attitude and wheel slippage during turning on complex roads are key factors affecting the operational efficiency and accuracy of a variable wheelbase six-wheel independent drive unmanned ground vehicle (6WID UGV), posing a serious threat to driving safety. This article proposes a hierarchical coordinated controller to improve the attitude stability of a 6WID UGV equipped with interconnected active hydro pneumatic suspension (IAHPS) and reduce tire slip energy loss. Firstly, an integral sliding mode controller with adaptive high-order coupling factor (AHOCF-ISMC) is designed to determine the active anti roll torque required for stable roll attitude. An adaptive high-order coupling factor is introduced in the controller framework to couple physical components with different properties, avoiding overshoot and oscillation caused by integral saturation of the controller. Secondly, based on satisfying the stability of the roll attitude, the lateral stability and longitudinal traction characteristics of the vehicle are constrained and controlled. An optimization function was established to minimize tire slip energy loss within the feasible range of wheel torque determined by lateral and longitudinal control objectives. Thirdly, the particle swarm optimization algorithm was improved (IPSO) by designing adaptive weighting factors and learning factors, and is used to optimize the wheel torque distribution scheme under composite constraint conditions. Finally, the effectiveness of the coordinated controller was tested and validated in different scenarios. The results show that the designed controller has good control performance and robustness without the need to establish an accurate mathematical model, and performs well in terms of economic benefits and application prospects. • AHOCF-ISMC with good control performance is proposed for roll attitude control. • IPSO is used to determine torque allocation that satisfies the minimum slip energy loss. • Hierarchical coordinated control framework is used to handle multiple control subsystems. [ABSTRACT FROM AUTHOR]

This paper proposes a learning-based hyper-heuristic algorithm for the coverage path planning problem of multiple unmanned surface vehicles (USV). The makespan and coverage of the USVs are considered simultaneously. The proposed method does not need to specify the location of the mapping task points in advance; instead, the task allocation and path planning can be realized only based on the parameter information of the USV and the watershed. Considering the uncertainty in the actual mapping process, the triangular fuzzy numbers are used to represent the mapping time and mapping radius of USVs. In order to solve the multi-USV scheduling problem efficiently, this paper proposes an NSGA-II based on dueling double deep Q-network called NSGA-II-DQN. NSGA-II-DQN integrates ten effective global search operators and five local search operators, which can achieve a good balance between exploration and exploitation. Experiment results in various scenarios demonstrate that NSGA-II-DQN can efficiently search for travel paths covering the entire water area for multiple USVs in a short planning time. • Triangular fuzzy numbers are used to represent the mapping time and mapping radius. • A multi-layer encoding is designed to optimize makespan and coverage of multiple USVs. • A local search operator based on shortest distance prioritization is designed. • Ten global operators and five local operators are adopted as a pool of candidate operators. • The dueling double deep Q-network is adopted to learn and select the optimal operator. [ABSTRACT FROM AUTHOR]

In maritime search and rescue (SAR), the boat swarm mode can greatly improve the success rate, but because of the influence of the curvature of the earth, the communication distance on the ground is short. Relay communication using unmanned surface vehicles (USVs) is the main means of maritime SAR, but communication speed and reliability are the core difficulties. To solve the problem, this paper proposes a trajectory planning aided unmanned surface vehicle optimization communication method with hierarchical reinforcement learning (TP–OC–HRL), which introduces relay USVs into the maritime SAR system and uses trajectory planning and the adaptive orthogonal frequency-division multiplexing (OFDM) technology as variables to optimize the communication rate of the SAR system. The paper proposes a communication optimization scheme based on hierarchical reinforcement learning, which divides the modulation coding scheme and the trajectory planning of the USVs into two hierarchical subproblems to improve the communication rate of the maritime SAR system through reinforcement learning. The experimental verification in the island area of the South China Sea shows that the TP–OC–HRL algorithm proposed in this paper has a faster convergence speed compared with that of the existing relay communication optimization methods, and can improve the communication rate of the maritime SAR system under the condition of meeting the reliability. • We established a high-speed maritime search and rescue communication method utilizing USV relays. • We established a surface USV communication optimization scheme based on hierarchical reinforcement learning. • Our method can adjust the MCS in real time based on the motion status of the USV, effectively improving the communication speed. [ABSTRACT FROM AUTHOR]

In the presence of global positioning system signal rejection, the low-cost inertial navigation system exhibits a significant cumulative error, leading to poor positioning accuracy of slave unmanned surface vehicles (SUSVs) in the cooperative navigation (CN) system for leader-slave. To improve the positioning accuracy of SUSVs, the extended Kalman filter (EKF) is augmented with distance information from external distance sensors. However, in the CN system of single leader unmanned surface vehicle, there may be a weaker observability, resulting in suboptimal estimated effects of the EKF. For the first time, the CN algorithm with observability and trilateral positioning method (TPM) is proposed to compensate the estimated position errors for EKF. An event trigger constructed from observability is used to assign the base stations and tags of the TPM. Then, the estimated positions of the tags are obtained by EKF when observability becomes weaker and the estimated positions are corrected by the measurements from TPM. Finally, more accurate estimated positions are obtained by weighted mean and the weights of compensation are automatically adjusted with observability. The results of the validation experiments and simulations show that the estimated positional accuracy of the proposed CN algorithm has improved by 40–50% compared to EKF. • Trilateral positioning method and observability are first offered to compensate the estimated position errors for EKF when observability becomes weaker in the cooperative navigation system of unmanned surface vehicles. • In order to improve the operational efficiency of the proposed collaborative navigation algorithm, event trigger is constructed based on observability to selectively compensate the estimation errors from the EKF. Finally, estimated positions with higher accuracy are achieved by obtaining automatically varying compensation weights through observability. • The experimental results and simulations show that the positional accuracy of the algorithm proposed in this paper is improved by 40–50% compared to EKF. [ABSTRACT FROM AUTHOR]

The complexity of vehicular interactions at the merging and diverging sections is more severe due to the multiple decisions the driver has to make in a short time. The present study investigates and quantifies the driving behavior at the toll plaza's merging and diverging sections. High-quality trajectory data for more than 7500 vehicle trajectories was derived from traffic video footage recorded by two Unmanned Aerial Vehicles (UAVs) operating concurrently upstream and downstream of the toll plaza. The data was extracted at 5 Hz, generating more than 5 million data points for the study. This approach facilitated a comprehensive and simultaneous capture of traffic dynamics. Various macroscopic and microscopic traffic parameters, like lateral and longitudinal speeds, following time, perception time, longitudinal standstill distance, and lateral clearance in the upstream and downstream sections, have been determined under weak lane disciplined traffic conditions. The mean speed in the merging section is 33.13 % lower than in the diverging section. Additionally, the average lateral speed in the merging section is 1.65 km/h, in contrast to 2.08 km/h in the diverging section, reflecting a 26 % increase. The lane changing and merging is prominent only up to 120 m to 140 m from the toll plaza in the merging section, and for diverging, 100 m to 200 m towards the toll plaza. The average following time in the diverging section is 5.7 s; for the merging section, it is 6.94 s, which is 13.86 % higher. The average perception time for the diverging section is 15.32 s; for the merging section, it is 13.13 s, which is 14.29 % lower. It has been observed that lateral clearance has a concave relationship with the speed in the merging section, whereas a convex relationship is in the diverging section due to the geometrical changes. The results presented in the study are expected to imitate heterogeneous traffic conditions observed in the field more realistically and will accelerate the understanding of behavioral aspects in complex interactive environments like that at merging and diverging sections of toll plazas. • UAV based high-quality trajectory data to study merging and diverging sections. • Behavioral analysis for six vehicle classes with varying static and dynamic characteristics. • Study of advanced driving behavior parameters like following and perception time. • Lateral speeds, Lateral clearance, and lane change behavior are analyzed. • Longitudinal standstill distance maintained among different vehicles is studied. [ABSTRACT FROM AUTHOR]

This paper investigates the defense penetration problem for unmanned surface vehicle (USV) with limited detection range under unknown defenders. A novel end-to-end defense penetration strategy is proposed for the USV based on modified soft actor–critic (MSAC). Specifically, the state–action space of the attacker is designed by combining the maneuvering model of USV and detection information. To guide the USV to reach the target area under the interception of defenders, the penetration reward is constructed. Then, the long short-term memory network (LSTM) is applied in the actor–critic network design. A dynamic training mechanism is proposed by combining curriculum learning and multi-memory pools, which aims to improve the success rate of defense penetration. Finally, simulation results validate the effectiveness and superiority of the proposed defense penetration method for the USV suffering from unknown defenders. The higher success rate can be guaranteed by using MSAC compared to the previous methods. • The defense penetration strategy for the USV under unknown defenders is proposed. • The proposed strategy has strong adaptability due to the long short-term memory network. • A higher defense penetration success rate can be guaranteed due to the dynamic training mechanism. [ABSTRACT FROM AUTHOR]

Robust control of Unmanned Surface Vehicles (USVs) is crucial for their safe and reliable navigation. The control methods of USV generally regard the results of pose estimation (such as GNSS/INS) as an accurate reference, but GNSS/INS is usually fluctuating and uncertain in the open water, which easily leads to large tracking errors or even control failure of USV. To this end, a robust sliding mode control of USV considering the active compensation of pose estimation uncertainty is innovatively presented, which can ensure the stability and accuracy of USV's control. The distinctive features of the proposed method are twofold: (i) To improve the pose estimation accuracy and obtain accurate uncertainty evaluation, an improved adaptive Kalman filtering considering the time-varying solution state is presented, which utilizes the convergence characteristics of INS and the time-varying features of GNSS solution state; (ii) By integrating pose estimation uncertainty assessment and active compensation, a Robust Finite-Time Sliding Mode Control (RFT-SMC) for a twin-propeller unmanned surface vehicle is developed to enhance tracking accuracy and anti-disturbance capability, and its convergence is established using a Lyapunov function, ensuring reliable operation of the USV even in the presence of uncertain pose estimation. Finally, verification experiments are offered to verify the effectiveness of the presented RFT-SMC method. • An innovative integrated control-perception scheme of USV is proposed. • An improved adaptive Kalman filtering considering the time-varying solution state is proposed. • Robust finite-time sliding mode control with pose estimation uncertainty assessment and compensation is developed. [ABSTRACT FROM AUTHOR]

Unmanned surface vehicles (USVs) are increasingly appealing for gathering metocean data, including directional sea spectra. This paper presents new developments towards estimating the response amplitude operators (RAOs) of surface vehicles equipped with inertial sensors. The novel approach undertakes the data-driven estimation of vehicle models of the wave-induced heave, roll, and pitch motion dynamics, as required to perform subsequent seakeeping computations. Specifically, a genetic algorithm executes the calibration of available closed-form RAOs for a simplified geometry. The algorithm makes a population of model-fitting parameters evolve towards minimising discrepancies between the predicted and measured response spectra in stationary operational conditions. Trust in the model is eventually increased by screening and merging the best-fitting solutions. Resulting response predictions using high-resolution spectral wave data for the AutoNaut USV demonstrate satisfactory accuracy and robustness in heave and pitch but a worse fidelity in roll, thereby motivating follow-up studies to improve the estimation of roll RAOs. • Inertial motion measurements are collected on board an autonomous marine vehicle. • Directional wave spectra are obtained by dynamical downscaling of hindcast data. • Parameters of the vehicle's seakeeping model are estimated using an elitist genetic algorithm. • Outliers of parameter values are identified and screened out, increasing model robustness. • Resulting predictions of the vehicle's wave-induced heave and pitch responses are accurate. [ABSTRACT FROM AUTHOR]

Numerical investigation of the water-entry impact performance of a bionic unmanned aerial–underwater vehicle (UAUV) is performed. According to the modified SST turbulent model method and volume of fluid (VOF) model, a robust solution procedure for a numerical method is described, and a verification study is conducted on water-entry cases of a cone, hemisphere, and gannet. Biological observation of flying fish has led to the proposal of this three-dimensional modelling approach for water entry processes of bionic UAUVs. The influence of the water-entry velocity and angle on the impact characteristics of a bionic UAUV is numerically investigated by this proposed numerical method. The impact pattern for different water-entry states is used to evaluate the correlation between impact acceleration and the water-entry state. The results indicate the feasibility of investigating the water-entry impact performance of bionic UAUVs in detail. The maximum axial impact acceleration is less than 2.58 g when the water-entry angle is θ ≤ 30° and the velocity is V ≤ 10 m/s. A quadratic relationship exists between the maximum impact acceleration and the initial water-entry velocity, and an approximate cubic relationship exists between the maximum impact acceleration and water-entry angle. The UAUV water entry at too large an angle and too high a velocity should be avoided to avoid a significant impact load.The impact rule investigation of numerical simulation can provide a feasible analysis strategy and a bionic efficient design configuration for UAUV. • The robust solution procedure of numerical method is described and conducted on verification study of water-entry cases. • Three-dimensional bionic modeling and water-entry numerical simulation are proposed to determine the best water-entry mode. • The impact rule investigation provides a feasible analysis strategy and a bionic efficient design configuration for UAUV. [ABSTRACT FROM AUTHOR]

Real-time and accurate detection of sea surface objects has become an important research topic for unmanned surface vehicles (USVs). During the execution of tasks, USVs sometimes need to upgrade their model to detect new categories, and the initial data is often limited. This requires quick adaptation to new categories under few-shot scenarios. We propose a lightweight neural network for detecting small sea surface objects named Shuffle-High-Resolution-Net (SHRDet), which integrates the enhanced Shuffle Block based on High-Resolution-Net (HRNet), lightweight feature fusion module, and Focal Efficient Intersection over Union loss. Based on SHRDet, a fast adaptation method named SHRDet-N for incremental few-shot categories is proposed. It generates category enhancement features through a cross-attention mechanism, and introduces elastic weight consolidation and feature distance to solve catastrophic forgetting when learning incremental few-shot categories. The algorithms have been applied to an intelligent USV platform for various surface missions, such as security patrol, ocean investigation, and marine engineering. The experimental results on public datasets indicate that SHRDet achieves 80.7 % mean Average Precision (mAP) on the Water Surface Object Detection Dataset (WSODD) with only 0.69 M parameters and less calculation quantity, and SHRDet is significantly superior to state-of-the-art methods in terms of lightweight and accuracy. Moreover, SHRDet-N effectively solves the learning problem of incremental few-shot categories. When the sample number of a new category is set to 20, the mAP of the base categories is 82.5 % and that of the new category is 63.8 %, which is 2.8 % and 4.2 % higher than that of state-of-the-art models like Sylph. • Lightweight small object detection model is designed by spatial attention and fusion. • Fast adaptation method for new few-shot categories is proposed for feature learning. • Field experiment was conducted to verify the rapid adaptation and effective detection. • SHRDet-N is significantly superior in terms of lightweight, accuracy, and adaptation. [ABSTRACT FROM AUTHOR]

This paper introduces a distributed containment control strategy for multiple unmanned surface vehicles (USVs) under the unknown external disturbances. The communication network of the USVs is a fixed, directed topology and only a part of the follower USVs can read the states of leader USVs. To guarantee the transient and steady-state performance of the system, the tracking errors are converted into new error functions. By utilizing the disturbance observer, the external disturbances are effectively estimated. According to the new group of errors, a distributed containment controller is proposed with the estimated external disturbances. Furthermore, using graph theory and Lyapunov approach, it is proved that all variables of the multiple USV systems are bounded and the tracking errors can be confined within the specified performance ranges. Finally, simulation results illustrate the effectiveness of the designed distributed containment controller. • A control scheme is proposed for with multiple leader in a distributed network. • A specific performance controller is proposed by changing the synchronization error. • A distributed controller for multi-USVs based on disturbance observer is designed. [ABSTRACT FROM AUTHOR]

This paper investigates the formation control of nonholonomic unmanned ground vehicles via unscented Kalman filter-based sensor fusion approach. According to the kinematic model of single unmanned ground vehicle, the formation model of multiple unmanned ground vehicles is established. Note that the physical leader is considered instead of a virtual leader, which is more realistic. The formation control problem is converted to the stability problem of an error dynamic system. An asymptotic stability condition of the error dynamic system is derived by designing an appropriate Lyapunov function. The leader-following formation is well formed through designing effective control vectors and utilizing unscented Kalman filter-based state estimation algorithm for each follower. Some simulation examples are provided to verify the effectiveness of the proposed formation control algorithm. • The framework of leader-following formation control of multiple nonholonomic UGVs with a physical leader is proposed. problem. • Both of velocity and angular velocity controller are designed for achieving formation control of multiple UGVs. • UKF-based approach is utilized to obtain the accurate pose of each UGV by fusing the information obtained from kinematics equation and measurement equation. [ABSTRACT FROM AUTHOR]

This paper focuses on the path following problem of unmanned surface vehicles (USVs) with unknown velocities, model uncertainties, and actuator saturation. To steer a USV rapidly and accurately follow the desired parameterized path, a line-of-sight (LOS)-based finite-time path following scheme is constructed in which the finite-time technique can ensure the fast error convergence, such that some intelligent operations, including patrolling, fuel supplying, and formation control, can be promptly performed. First, USV kinematic and kinetic models are established, and finite-time observers are subsequently employed to identify the unmeasured USV velocities and model uncertainties. Then, an LOS guidance law is designed to achieve the finite-time convergence of the position errors. In addition, an optimized look-ahead distance is developed using a fuzzy algorithm. Meanwhile, the control subsystem is designed at the kinetic level by combining the backstepping sliding mode method and a novel auxiliary dynamic system, where the auxiliary system is applied to address actuator saturation. Subsequently, theoretical analysis is conducted to verify that the entire system is uniformly global finite-time stable (UGFTS). Finally, the simulation studies confirms the availability of the developed method. [Display omitted] • The finite-time technique is applied in guidance and control loop, simultaneously. • A novel fuzzy rule for the look-ahead distance is developed. • A novel auxiliary dynamic system is proposed to solve the saturation problem. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

• In water disaster, remote controlled vehicles which work for disaster recovery have to run in water environment. • Since underwater ground is likely to be soft, the vehicle has a risk of stuck. • We have to make a method for judging whether to run or not the vehicle in underwater ground. • We must quantitatively clarify the relationship between the trafficability and the strength, bearing capacity, etc. of underwater ground. In recent years, water disasters have increased in Japan. In water disaster, remote controlled vehicles which work for disaster recovery must run in water environment. Since underwater ground is likely to be soft, the vehicle has a risk of stuck. If a vehicle gets stuck at disaster sites, rescue work is difficult because it is not easily to access to that area. We must make a method for judging whether to run or not. For this purpose, we must quantitatively clarify the relationship between the trafficability and the strength, bearing capacity, etc. of underwater ground. We measured the cone index of underwater ground. From results, we confirmed that fragile layer was formed on the surface layer in underwater ground. We measured drawbar pull of a tracked carrier in test field. As a result, maximum drawbar pull of underwater ground was lower than on the ground. After slip occurs, drawbar pull of underwater ground was smaller than ground significantly. [ABSTRACT FROM AUTHOR]

• SVM's do a good job at classifying the difference between snow and pavement. • ROS and Pixhawk controllers together make a good inexpensive vehicle controller. • Artificial Intelligence algorithms can be trained from simple vehicle models. The US Army must update its vehicle fleet to be better equipped for potential future military conflicts in northern climates (US Army, 2017). This process involves considering manned, optionally manned, and unmanned vehicles as viable options in the future. Optionally manned and unmanned vehicles in the armed forces have substantial benefits because they can operate without direct driver input or are able to perform missions deemed too dangerous for troops. Optionally manned vehicles allow the driver to shift some, or all, focus away from the task of driving the vehicle. In some cases, these autonomous vehicles may perform better than a human driver by rapidly sensing and reacting to terrain changes. Onboard sensing and decision making are equally applicable to both fully autonomous and teleoperated vehicles. This work will focus on the terrain sensing, waypoint navigation, and teleoperation potential of an optionally manned or unmanned vehicle. Results from a vehicle demonstration on two different terrain conditions will provide the basis for additional terrain sensing and autonomous vehicle development work in the coming year. [ABSTRACT FROM AUTHOR]

To solve the problem of path discontinuity and tracking difficulty in unmanned surface vehicle path planning, this paper introduces the Minimum Snap algorithm to optimize the trajectory, and makes some improvements to the Minimum Snap algorithm to address the problem of imperfect paths caused by uneven time allocation. The concept of a safe corridor is introduced to optimize the Minimum Snap algorithm. In response to the problem of excessive deviation from the reference value in some areas of the optimized path, a guidance function is added to make the path closer to the original trajectory. In the simulation, the proposed improved Minimum Snap is compared with Bezier curve and B-spline curve, the results show that the improved Minimum Snap can enable unmanned surface vehicle to complete turns and other actions with minimal energy consumption while driving safely, without experiencing severe acceleration and Jerk, laying the foundation for subsequent path tracking control. • The Minimum Snap algorithm is introduced to optimize the trajectory of USV to ensure path continuity. • A secure corridor is introduced into Minimum Snap algorithm to solve uneven time allocation. • A guiding function is added to make the path closer to the original trajectory and ensure smaller path deviation. [ABSTRACT FROM AUTHOR]

The paper is based on experiments within a project to prepare tutorial tasks on a training centre for testing radiation detectors fixed on unmanned aerial vehicles (UAVs) and in unmanned ground vehicles. The paper reports on a small UAV with NaI(Tl) 2" x 2" detector for radiation monitoring in an emergency event and for radioactive source chasing and detection. The paper is focused on some special cases with the possibility to determine local air kerma rates and the activities of point sources. The detector was calibrated for air kerma rates from 5 nGy h−1 to 20 μGy h−1. The verified model of the NaI(Tl) 2″ x 2″ detector including the electronic module assembled on a UAV was designed in a Monte Carlo simulation. The model was used for calculating the air kerma rates at various altitudes above the ground both for a natural background and for selected point sources. The response functions for 137Cs, 131I, 192Ir, 60Co and 99Mo point sources were calculated by the Monte Carlo simulation to estimate their activities. Experiments were carried out with an NaI(Tl) 2" x 2" detector fixed on a Robodrone UAV and flying over 60Co and 137Cs point sources over the airfield area and the local air kerma rates and the activities of the point sources were calculated with the AGAMA post-processing program. In addition, the response functions for 137Cs distributed uniformly on the surface were calculated by Monte Carlo simulation for future emergency purposes. The detection limits of selected man-made nuclides (point sources) were calculated. • Small detectors, for example NaI(Tl) 2" x 2" or 3" x 3", are able to detect changes in air dose rates at the level of natural background. • Air dose rates of natural background and from surface contamination can be well converted from values at flight altitudes to a height of 1 m above the ground. • Use of non-negative least square method using the response matrices of individual nuclides allows estimation of the activity of point sources, "small hot spots" or surface activity. • Detection limits for small detectors NaI(Tl) are usually in a range of tens of MBq for flight level of 10 m for usual sealed point sources, and hundreds of MBq for flight levels higher than 20 m. [ABSTRACT FROM AUTHOR]

This research presents a novel method for energy-efficient path planning, aiming to enhance the endurance of unmanned surface vehicle (USV). The proposed method combines the locking sweeping (LS) method, gradient descent method, coastline expansion method, and energy consumption functions. The efficiency of constructing the energy consumption potential map was improved by optimising the LS structure. Moreover, maintaining a user-configurable distance between the USV and the coastline ensures safe paths with minimal energy consumption. The performance of the proposed method was evaluated using multiple simulations involving high-resolution electronic nautical charts and a historical time-variant sea current dataset. The results demonstrate the practicality of the method, and effectively address path planning challenges in a time-variant maritime environment. • Locking sweeping, gradient descent, coastline expanding methods are integrated for USV path planning with complex maritime environments. • High-resolution and complex electronic nautical charts dataset and historic time-varying sea current dataset are used. This feature can improve the practicability of the method. • Adjustable sweep initial point, sweep area and gradient descent step size are proposed as part of locking sweeping method. It can improve the path search efficiency in a time-variant maritime environment. • The proposed method was compared with the three related methods and showed the best performance in energy efficiency. • The research included an analysis of computational time, showcasing its scalability and practicality for real-world applications. [ABSTRACT FROM AUTHOR]