Search

This paper proposes a novel solution to the problem of robust ripple‐free hybrid robust regulator ensuring the elimination of intersample ripples. The paper considers a structurally stable regulation approach in the hybrid framework. A regulator is designed using this technique under periodic sampling and is applied to the nonlinear model of a quadrotor. The control of unmanned autonomous vehicles has become a research topic that is important by itself, particularly in the case of multi‐rotor systems due to their versatility in various applications. Tracking a reference signal for such vehicles can be challenging, particularly when the frequency of communication is limited, or the control station is located far away. The proposed controller is hence tested for this challenging application. [ABSTRACT FROM AUTHOR]

Perception systems in autonomous vehicles need to accurately detect and classify objects within their surrounding environments. Numerous types of sensors are deployed on these vehicles, and the combination of such multimodal data streams can significantly boost performance. The authors introduce a novel sensor fusion framework using deep convolutional neural networks. The framework employs both camera and LiDAR sensors in a multimodal, multiview configuration. The authors leverage both data types by introducing two new innovative fusion mechanisms: element‐wise multiplication and multimodal factorised bilinear pooling. The methods improve the bird's eye view moderate average precision score by +4.97% and +8.35% on the KITTI dataset when compared to traditional fusion operators like element‐wise addition and feature map concatenation. An in‐depth analysis of key design choices impacting performance, such as data augmentation, multi‐task learning, and convolutional architecture design is offered. The study aims to pave the way for the development of more robust multimodal machine vision systems. The authors conclude the paper with qualitative results, discussing both successful and problematic cases, along with potential ways to mitigate the latter. [ABSTRACT FROM AUTHOR]

Summary: False data injection attacks can disrupt the steering control actions and make a real threat to both the security and safety of autonomous vehicles. In this paper, a secure event‐triggered lateral control approach of autonomous vehicles subject to actuator attacks is investigated. Firstly, an arbitrary unknown actuator attacks is considered in the secure lateral steering control of autonomous vehicles. Thus, to save communication resources for the limited bandwidth CAN bus, the periodic event‐triggered transmission scheme is utilized, transforming the established lateral steering control into a time‐delay system through the consideration of periodic event‐triggered sampling. Then, an adaptive control compensation scheme is developed to mitigate the malicious effects caused by actuator attacks. The proposed secure control approach is skilled in compensating the unknown attacked steering control actions in an adaptive way. The stabilization criteria under the adaptive secure control law is well derived by Lyapunov–Krasovskii method and some linear inequality matrices operations. At last, the effectiveness of the proposed secure control scheme is verified by some numerical experiments borrowed from a practical vehicle. [ABSTRACT FROM AUTHOR]

Summary: This article studies robust adaptive control for a class of autonomous vehicle platoons. In particular, two innovative adaptive control laws are proposed to address both position and velocity tracking for a vehicle platoon. In addition, it is shown that robust asymptotic string stability can be delivered by the underlying adaptive control laws for the vehicle platoon, in the sense that these adaptive control laws are capable of mitigating parameter uncertainties involved in the nonlinear vehicular dynamics and achieving truly cooperative adaptive cruise control while ensuring the required safety spacing between each neighboring vehicle pair asymptotically. It is also shown that the control performance of the vehicle platoon can be further improved if the operating equilibrium points of all vehicles can be adaptively estimated, leading to two linear time‐invariant control laws for individual vehicles under both position and velocity controls and for the vehicle platoon. Simulation studies illustrate the effectiveness of the proposed control method, validating the results obtained for the class of vehicle platoons. [ABSTRACT FROM AUTHOR]

In this article, by creating a novel distributed full‐form dynamic linearization based model‐free adaptive containment control (FFDL‐MFACC) approach, the containment control problem of networked heterogeneous autonomous surface vehicles (ASVs), suffering from complex external disturbances and unavailable kinetic model‐information, is resolved. In light of the data‐driven strategy, a full‐form dynamic linearization‐based data model is efficiently established. Then, by further deploying the commonly used rotation matrix, a distributed FFDL‐MFACC scheme is thereafter developed such that accurate tracking of a predefined convex hull spanned for all follower vehicles can be achieved. Afterwards, a disturbance observer is further designed to accurately estimate the lumped disturbances and the estimation is served as a compensation within the distributed full‐form dynamic linearization. Rigorously theoretical analysis indicates the devised distributed FFDL‐MFACC method can ensure the asymptotic containment tracking of networked heterogeneous ASVs. Finally, simulation results are illustrated to verify the advantages of the devised approach. [ABSTRACT FROM AUTHOR]

This paper presents a Youla‐Kucera based interpolation between a set of Linear Parameter‐Varying (LPV) controllers, each one being a gain‐scheduled of Linear Time‐Invariant (LTI) controllers designed separately for different operating points. The gain‐scheduling is achieved based on Youla‐Kucera (YK) parameterization. A generalized LPV‐YK control structure is designed to interpolate between various LPV controllers. The closed‐loop system is proved to guarantee the quadratic stability for any continuous/discontinuous interpolating signals in terms of a set of Linear Matrix Inequalities (LMIs). The proposed method can help multi‐variable and multi‐objective systems to achieve high performances at different operating conditions and different critical situations regardless of the interpolation rate. A numerical example is simulated to show the importance of the proposed method to achieve different objectives for lateral control of autonomous vehicles. In addition, the approach has been tested on a real Renault ZOE vehicle to validate its real performance, and compare it with a standard polytopic LPV controller. [ABSTRACT FROM AUTHOR]

This article presents a fault‐tolerant platooning control algorithm for a class of nonlinear homogeneous multi‐vehicle systems under unreliable network communication environment. The considered types of actuator failures in individual vehicle are loss‐in‐effectiveness, and bias faults. Suppose the communication network among vehicles is here described as a switching graph subject to intermittent communications. Unlike the existing results dealing with vehicle platoon under continuous communications, this article develops a hierarchical fault‐tolerant platooning control approach, under which, the multiple vehicle coordination platooning objective is ensured even in the cases of discontinuous communication faults and actuator failures. First, each following vehicle can estimate the desire reference information via cooperative adaptive virtual estimator even in intermittent communications. Second, the local fault‐tolerant controller with adaptive parameter update mechanism can guarantee the practical position and velocity of following vehicles asymptotically track the desire estimations. Finally, a simulation example of a team of autonomous vehicles is given to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Summary: In the face of external disturbances, the autonomous vehicle with a high center of gravity is exposed to the risk of roll instability during trajectory tracking. To this end, this paper aims to propose a vector‐extended‐state‐observer (VESO)‐based adaptive fixed‐time terminal sliding mode prescribed performance control strategy, which coordinates the front wheel steering angle and external roll moment to ensure the roll stability of the high center of gravity autonomous vehicle while improving the tracking dynamic and steady state performances. The VESO for estimating the external disturbance is designed to enhance the robustness outside the sliding mode surface, based on which the adaptive updating laws compensate the estimation errors to provide the control system's dynamic performance. A fixed‐time sliding mode control with prescribed performance is proposed, which combines a fixed‐time prescribed performance control method to further improve the transient performance and steady‐state accuracy. The double lane‐changing reference trajectory tracking conditions under different vehicle driving speeds and initial errors settings are verified by simulation in MATLAB/Simulink environment, and the results show that the proposed control strategy can ensure the rolling stability of the vehicle, can track the reference trajectory accurately and quickly, and has strong robustness. [ABSTRACT FROM AUTHOR]

Summary: In this article, the problem of fixed‐time distributed optimization is researched for third‐order fully heterogeneous nonlinear connected and autonomous vehicles. To address this problem, a fixed‐time distributed optimization algorithm is proposed via a two‐step strategy. First, an optimization algorithm is proposed to generate a virtual reference signal that can converge to the optimal solution. Then, we further construct an adaptive tracking controller to track the virtual signal based on the first step. In the design process of the controller, the virtual control variables and the actual control input are obtained by using the backstepping technique. Furthermore, a fast fixed‐time filter is introduced to avoid the issue of discontinuous gradient functions. Fuzzy logic systems are employed to address the unknown part of the nonlinear function. By using tools from the fixed‐time stability criterion, convex optimization theory, and Lyapunov stability theory, it can be demonstrated that the provided strategy drives all optimization variables to the optimal solution within a fixed time and guarantees the closed‐loop system signals are bounded. Finally, the effectiveness of control strategy is verified via a numerical simulation. [ABSTRACT FROM AUTHOR]

Summary: The advancement in technology and the adoption of innovative developments have made our lives easier. Every industry, from agriculture to transport, has experienced this advancement. The entire transportation system is in the process of becoming intelligent. Smart mobility of autonomous vehicles is an important part of the upcoming smart cities. The autonomous vehicle provides functionalities for safety and convenience. It has been an emerging field with a lot of attention and still under advancement and requires a thorough study and solutions for potential challenges and opportunities. Despite impressive advantages, it has some security vulnerabilities which could lead to life‐threatening consequences. Though they could prevent road accidents by eliminating human errors from the driving process, they also create the possibility of cyber‐physical attacks on the vehicular controlling system. For this, many researchers have focused on the security attacks and defenses in autonomous vehicular systems. A 360‐degree research has been undertaken to understand the concept of autonomous vehicles entirely, such as history, social impacts, difficulties and challenges, current product developments, and security aspects. Also, a vehicular architecture is proposed by integrating various technologies such as 5G, SDN, cloud, and so forth, its possible security attacks are mentioned. [ABSTRACT FROM AUTHOR]

Imaging through scattering media is widely studied in various applications including industrial inspection and autonomous driving. Most existing image sensors always suffer from the aliasing effect that generates a diffused image, leading to an extremely challenging problem in recovering targets of high quality, especially for 3D imaging. In this study, a scanning‐driven photon‐counting 3D imaging system through scattering media is proposed via asynchronous polarization modulation. To eliminate the aliasing effect, we utilize a point‐to‐point scanning strategy is used to illuminate the target and a photon‐counting detector to perceive weak echo signals passing through scattering media. Then, an asynchronous polarization‐modulated ranging method is proposed innovatively based on the Gamma pulse model to calculate the relative depth of the target for 3D imaging with the consideration of scattering media's difference. Therefore, the accuracy of the calculated depth and the generalization capability of the proposed method in real applications can be significantly improved. In addition, a time reshaping method is proposed to cope with the depth ambiguity caused by asynchronous measurements. In the experiment, a variety of strong scattering media is used to verify the excellent imaging capability of the proposed method. [ABSTRACT FROM AUTHOR]

The Internet of Vehicles (IoV) autonomous driving technology based on deep learning has achieved great success. However, under the tunnel environment, the computer vision‐based IoV may fail due to low illumination. In order to handle this issue, this paper deploys an image enhancement module at the terminal of the IoV to alleviate the low illumination influence. The enhanced images can be submitted through IoT to the cloud server for further processing. The core algorithm of image enhancement is implemented by a dynamic graph embedded transformer network based on federated learning which can fully utilize the data resources of multiple devices in IoV and improve the generalization. Extensive comparative experiments are conducted on the publicly available dataset and the self‐built dataset which is collected under the tunnel environment. Compared with other deep models, all results confirm that the proposed graph embedded Transformer model can effectively enhance the detail information of the low‐light image, which can greatly improve the following tasks in IoV. [ABSTRACT FROM AUTHOR]

Semantic segmentation from a three‐dimensional point cloud is vital in autonomous driving, computer vision, and augmented reality. However, current semantic segmentation does not effectively use the point cloud's local geometric features and contextual information, essential for improving segmentation accuracy. A semantic segmentation network that uses local feature fusion and a multilayer attention mechanism is proposed to address these challenges. Specifically, the authors designed a local feature fusion module to encode the geometric and feature information separately, which fully leverages the point cloud's feature perception and geometric structure representation. Furthermore, the authors designed a multilayer attention pooling module consisting of local attention pooling and cascade attention pooling to extract contextual information. Local attention pooling is used to learn local neighbourhood information, and cascade attention pooling captures contextual information from deeper local neighbourhoods. Finally, an enhanced feature representation of important information is obtained by aggregating the features from the two deep attention pooling methods. Extensive experiments on large‐scale point‐cloud datasets Stanford 3D large‐scale indoor spaces and SemanticKITTI indicate that authors network shows excellent advantages over existing representative methods regarding local geometric feature description and global contextual relationships. [ABSTRACT FROM AUTHOR]

Traditional mapping of bedforms in submarine canyons relied on vessel‐mounted and towed sensors, but their fine‐scale geomorphology and shallow structure requires higher resolution datasets. This study utilizes a high‐resolution dataset obtained from an autonomous underwater vehicle, combined with seismic reflection profiles and sediment cores, to analyse bedform sets within a 25.6 km long submarine canyon (canyon C14) in the northern South China Sea. A train of crescent‐shaped axial steps, indicative of cyclic steps formed by supercritical turbidity currents, is imaged along the canyon. Axial steps in the upper course show erosional truncations and sub‐horizontal reflectors on the lee and stoss sides, respectively, pointing to erosional–depositional cyclic steps formed by confined flows with high erosional capacity. This is facilitated by canyon narrowness and steeper axial gradient. After a transition segment, the lower course widens, with a gentler axial gradient, resulting in increased asymmetry and wavelength of axial steps. Backset bed deposits on the stoss sides of these steps indicate depositional cyclic steps with higher aggradation. Sediment filling, almost padding each cyclic step associated scour suggests the reworking of previously formed bedforms by gravity flows fed by destabilization processes on the canyon sidewalls and upstream lee faces and, possibly, by shelf‐edge and uppermost slope spillover into the canyon. At the lowermost course, cyclic steps transition to a furrow field, likely associated with flow velocity reduction facilitated by canyon floor widening and a further decrease in slope gradient. Flow braiding and re‐convergence, related to the erosion of fine‐grained deposits within the canyon floor, should have played a role to produce furrows under supercritical conditions. This work enhances our understanding of the detailed morphology and shallow relief configuration of bedforms in deep‐water submarine canyons, providing insights into their causative processes and evolution. [ABSTRACT FROM AUTHOR]

This paper presents a novel detection and rerouting mechanism for distributed adaptive platoon control of non‐linear autonomous connected vehicles under denial of service (DoS) attacks. DoS attacks can cause delays or losses of data packets due to blocked communication channels, leading to reducing platoon performance or even collisions among vehicles. To tackle this issue, the proposed mechanism detects and reroutes communication topology depending on the real‐time topology and the number of link failures. Real‐time detection divides the scenario of DoS attacks into three parts. According to the different scenarios, rerouting mechanisms will be utilized. A controller adapted to real‐time variable communication topology is also designed in this scheme. The adjacency matrix of the real‐time communication topology generated by the rerouting mechanism is used to update the controller so that the platoon can remain in a stable state without being affected by DoS attacks. In addition, the sliding mode controller and the observer are designed by solving linear matrix inequalities, and the platoon stability and internal stability are proven. Numerical simulation studies demonstrate that the proposed mechanism and control design can reduce the vehicle state estimate error and platoon‐tracking error to ideal states under DoS attacks. The proposed method solves the problem that the existing methods have not considered the number of link failures and the inability to restore communication when the communication topology is paralyzed. [ABSTRACT FROM AUTHOR]

This article considers a path tracking control problem for autonomous vehicles constrained to maintain a safe distance from the next vehicle in the lane. The control design problem is solved by considering a mathematical model of the vehicle that jointly describes the lateral and longitudinal dynamics. Specifically, the ℒ2$$ {\mathcal{L}}_2 $$ optimal controller is designed aimed at minimizing the orientation and position tracking errors with respect to a given reference path. Moreover, the controller is able to ensure that the vehicle can both follow a speed profile and automatically adjusts the vehicle speed to maintain a proper distance from the next vehicle. The lateral dynamic is regulated by a 2‐DOF feedforward/feedback controller, where the feedforward law is implemented by exploiting an inverse kinematic model of the vehicle. On the other side, the feedback action, along with the action of the controller in charge to regulate the longitudinal dynamics, is the ℒ2$$ {\mathcal{L}}_2 $$ optimal gain‐scheduling state‐feedback controller. In particular, a parameter‐dependent quadratic Lyapunov function approach is used to reduce the conservativeness of the solution and a suitable convex LMI optimization problem is formulated for the synthesis. The vehicle is described by a seven‐degrees‐of‐freedom (7DOF) full‐car model, with the tire‐generated forces described by the classical Pacejka's Magic Formula. In order to assess the performance of the proposed control strategy, simulations have been undertaken in Matlab/Simulink by considering an autonomous vehicle driving into an urban scenario. [ABSTRACT FROM AUTHOR]

Summary: Industrial transport system refers to the movement of goods, raw materials, and finished products within and between industrial facilities such as factories, warehouses, and distribution centers. It includes a variety of modes of transport such as trucks, forklifts, conveyor belts, and automated guided vehicles (AGVs). Context‐aware route service management refers to system that can dynamically manage and optimize the routes taken by vehicles in transportation system based on contextual information. Our proposed framework for industrial transport systems and smart intelligent autonomous vehicles utilizes cluster‐based context‐aware routing (CCAR), which includes several significant contributions. Firstly, modified elephant herding optimization (MEHO) algorithm is used to efficiently group autonomous vehicles for routing. Secondly, an improved gravitational search (IGS) algorithm is used for cluster head (CH) selection responsible for transferring context information between vehicles (V2V). Thirdly, a deep hybrid multi‐graph neural network (DHMG‐NN) is designed for optimal neighboring roadside unit (RSU) node selection through different design constraints to ensure data dissemination between vehicles and infrastructure (V2I). Finally, we validate the effectiveness of our CCAR framework using various simulation scenarios. Our framework achieves a reduction of up to 78% in computation time and an improvement of up to 25% in customer satisfaction ratio and 15% higher than the overall performance ratio compared to the existing frameworks. [ABSTRACT FROM AUTHOR]

Pilots use their senses and training to generate situational awareness (SA). They then use this SA to make sound aeronautical decisions. Autonomous vehicles, by contrast, cannot rely on pilot expertise in off‐nominal situations. They must rely on their onboard sensors to build SA of the environment. As these sensors degrade, it is hypothesized that a point exists where the SA generated by these sensors is inadequate to allow the autonomous vehicle to make sound aeronautical decisions. In previous work, a point was defined based on broad assumptions within a modeling and simulation environment (i.e., the error within each sensor was known and not random). This research used a larger data set that contained random errors within the sensors. The data was then used to build predictive equations through a Monte Carlo simulation in the same simulation environment as previous work. While the data showed there was a statistically significant relationship between the error values in each sensor and the fused distance value, the resulting predictive equations were not able to provide adequate SA to make sound aeronautical decisions. This research highlights multiple issues the test and evaluation community will face when trying to develop new techniques for the verification and validation of autonomous systems. [ABSTRACT FROM AUTHOR]

Current surveys indicate limited public and individual trust in autonomous vehicles despite a long tradition to ensure their (technical) trustworthiness in informatics and systems engineering. To address this trust gap, this article explores the underlying reasons. The article elaborates on the gap between trust understood as a social phenomenon and, in contrast, the research tradition aimed at guaranteeing (technical) trustworthiness. It discusses to what extent those research traditions in the social sciences and humanities have been recognized and reflected in systems engineering research to date. Trust, according to the current state of research in the social sciences and humanities, heavily relies on individual assessments of an autonomous vehicle's abilities, benevolence and integrity. By contrast, technical trustworthiness is defined as the sum of intersubjective, measurable, technical parameters. They describe certain abilities or properties of a system, often according to respective technical standards and norms. This article places the “explainability” of autonomous systems in a bridging role. Explainability can help to conceptualize an integrative trust layer to communicate a system's abilities, benevolence and integrity. As such, explainability should respect the individual and situational needs of users, and should therefore be responsive. In conclusion, the results demonstrate that “learning from life” requires extensive interdisciplinary collaboration with neighboring research fields. This novel perspective on trustworthiness aligns existing research areas. It delves deeper into the conceptual “how”, dives into the intricacies and showcases (missing) interconnectedness in the state of research. [ABSTRACT FROM AUTHOR]

As an anthropologist, I have worked with people in both developing new technologies and managing existing ones. Based on this experience, I suggest that although anthropologically informed perspectives can contribute to technology development—from providing insights on particular cases to raising broader questions about a product's impact on society—the route to doing so is sometimes indirect. In this endeavor, anthropology matters by engaging not just the finished product, when critique is so easily possible, but the process of development, as the work is yet underway. Such engagement is enabled by how people leverage their commitments, stances, and manner of being there along the way and over time. To better enable the impact of anthropology in this work, anthropologists would be well served by engaging more with these kinds of applied questions as a part of their training and knowledge production. [ABSTRACT FROM AUTHOR]

Perspective‐taking (PT) accessibility has been recognized as an important factor in affecting moral reasoning, also playing a non‐trivial role in moral investigation towards autonomous vehicles (AVs). A new proposal to deepen this effect leverages the principles of the veil of ignorance (VOI), as a moral reasoning device aimed to control self‐interested decisions by limiting the access to specific perspectives and to potentially biased information. Throughout two studies, we deepen the role of VOI reasoning in the moral perception of AVs, disclosing personal and contingent information progressively throughout the experiment. With the use of the moral trilemma paradigm, two different VOI conditions were operationalized, inspired by the Original Position theory by John Rawls and the Equiprobability Model by John Harsanyi. Evidence suggests a significant role of VOI reasoning in affecting moral reasoning, which seems not independent from the order in which information is revealed. Coherently, a detrimental effect of self‐involvement on utilitarian behaviours was detected. These results highlight the importance of considering PT accessibility and self‐involvement when investigating moral attitudes towards AVs, since it can help the intelligibility of general concerns and hesitations towards this new technology. [ABSTRACT FROM AUTHOR]

Conventional RGB‐T salient object detection treats RGB and thermal modalities equally to locate the common salient regions. However, the authors observed that the rich colour and texture information of the RGB modality makes the objects more prominent compared to the background; and the thermal modality records the temperature difference of the scene, so the objects usually contain clear and continuous edge information. In this work, a novel mirror‐complementary Transformer network (MCNet) is proposed for RGB‐T SOD, which supervise the two modalities separately with a complementary set of saliency labels under a symmetrical structure. Moreover, the attention‐based feature interaction and serial multiscale dilated convolution (SDC)‐based feature fusion modules are introduced to make the two modalities complement and adjust each other flexibly. When one modality fails, the proposed model can still accurately segment the salient regions. To demonstrate the robustness of the proposed model under challenging scenes in real world, the authors build a novel RGB‐T SOD dataset VT723 based on a large public semantic segmentation RGB‐T dataset used in the autonomous driving domain. Extensive experiments on benchmark and VT723 datasets show that the proposed method outperforms state‐of‐the‐art approaches, including CNN‐based and Transformer‐based methods. The code and dataset can be found at https://github.com/jxr326/SwinMCNet. [ABSTRACT FROM AUTHOR]

This study is the first in the literature to examine the Braess paradox considering parking behavior in the autonomous vehicle (AV) environment, based on which the network design problem for the autonomous transportation system (NDP‐ATS) is modeled. First, we introduce the AV commuting pattern considering the self‐driving process for the parking purpose. We then illustrate the existence of two distinct Braess paradoxes that can occur in AV traffic networks with regards to parking space addition and network capacity expansion. They show that these two types of "improvement" measures might deteriorate the network system performance in an AV situation. Second, motivated to avoid the deterioration due to the introduced Braess paradoxes, we develop a bi‐level programming model for NDP‐ATS. The lower‐level program addresses the network‐equilibrium traffic assignment for AVs. The upper‐level program aims to minimize the network‐wide travel cost considering both occupied and empty AV trips by selecting the optimal design option accounting for road capacity enhancement and parking facility deployment simultaneously. To solve the developed bi‐level model, the simplicial homology global optimization algorithm is employed along with the Frank–Wolfe algorithm and the CPLEX. Finally, the efficacy of the modeling framework is validated through case studies on the Sioux Falls city network and the Anaheim network. The results show that the developed methodology is capable of producing high‐quality solutions with respect to savings in system‐level travel costs for AV traffic. The results also highlight the impacts of parking fees on the system performance for the optimized network. Additionally, it is found that the two objectives, which minimize the total system travel cost and minimize that for empty AV trips only, are conflicting for certain scenarios. The methodological approach introduced in this work serves as a critical modeling device for infrastructure development and policy assessment for AV traffic. [ABSTRACT FROM AUTHOR]

The flexoelectric phenomenon, which occurs when materials undergo mechanical deformation and cause strain gradients and a related spontaneous electric polarization field, can result in wide variety of energy‐ and cost‐saving mechano‐opto‐electronics, such as night vision, communication, and security. However, accurate sensing of weak intensities under self‐powered conditions with stable photocurrent and rapid temporal response remains essential despite the challenges related to having suitable band alignment and high junction quality. Taking use of the flexoelectric phenomena, it is shown that a centrosymmetric VO2‐based heterojunction exhibits a self‐powered (i.e., 0 V), infrared (λ = 940 nm) photoresponse. Specifically, the device shows giant current modulation (103%), good responsivity of >2.4 mA W−1, reasonable specific detectivity of ≈1010 Jones, and a fast response speed of 0.5 ms, even at the nanoscale modulation. Through manipulation of the applied inhomogeneous force, the sensitivity of the infrared response is enhanced (> 640%). Ultrafast night optical communication like Morse code distress (SOS) signal sensing and high‐performing obstacle sensors with potential impact alarms are created as proof‐of‐concept applications. These findings validate the potential of emerging mechanoelectrical coupling for a wide variety of novel applications, including mechanoptical switches, photovoltaics, sensors, and autonomous vehicles, which require tunable optoelectronic performance. [ABSTRACT FROM AUTHOR]

This article researches the problem of trajectory tracking for unmanned marine vehicles (UMVs) under disturbances and denial‐of‐services (DoS) attacks in the wireless channel. An equivalent data‐driven model of UMVs with ocean disturbances is established by using partial form dynamic linearization algorithm. The disturbances and the input of UMVs have different pseudo partitioned Jacobean matrix, and the disturbances are estimated by using extended state observer, which improves the immunity of UMVs to disturbances in the environment. It is the first time that the DoS attacks are considered under the data‐driven model for UMVs, and a novel data‐driven adaptive trajectory tracking control framework is constructed. The article proposes an attack predictive compensation mechanism to mitigate their effects of DoS attacks, which follows the Bernoulli distribution. Based on it, the data‐driven adaptive trajectory tracking controller is designed such that the error of trajectory tracking is convergent under DoS attacks and external disturbances. Finally, the effectiveness of the proposed data‐driven control scheme and the predictive compensation mechanism is validated through the simulations. [ABSTRACT FROM AUTHOR]

Future connected and autonomous vehicles (CAVs) must be secured against cyberattacks for their everyday functions on the road so that safety of passengers and vehicles can be ensured. This article presents a holistic review of cybersecurity attacks on sensors and threats regarding multi‐modal sensor fusion. A comprehensive review of cyberattacks on intra‐vehicle and inter‐vehicle communications is presented afterward. Besides the analysis of conventional cybersecurity threats and countermeasures for CAV systems, a detailed review of modern machine learning, federated learning, and blockchain approach is also conducted to safeguard CAVs. Machine learning and data mining‐aided intrusion detection systems and other countermeasures dealing with these challenges are elaborated at the end of the related section. In the last section, research challenges and future directions are identified. This article is categorized under:Commercial, Legal, and Ethical Issues > Security and PrivacyTechnologies > Machine LearningTechnologies > Internet of Things [ABSTRACT FROM AUTHOR]

The prediction of surrounding agent trajectories in heterogeneous traffic environments remains a challenging task for autonomous driving due to several critical issues, such as understanding social interactions among agents and the environment, handling multiclass traffic movements, and generating feasible trajectories in accordance with real‐world rules, all of which hinder prediction accuracy. To address these issues, a new multimodal trajectory prediction framework based on the transformer network is presented in this study. A hierarchical‐structured context‐aware module, inspired by human perceptual logic, is proposed to capture contextual information within the scene. An efficient linear global attention mechanism is also proposed to reduce the computation and memory load of the transformer framework. Additionally, this study introduces a novel auxiliary loss to penalize infeasible off‐road predictions. Empirical results on the Lyft l5kit data set demonstrate the state‐of‐the‐art performance of the proposed model, which substantially enhances the accuracy and feasibility of prediction outcomes. The proposed model also possesses a unique feature, effectively dealing with missing input observations. This study underscores the importance of comprehending social interactions among agents and the environment, handling multiclass traffic movements, and generating feasible trajectories adhering to real‐world rules in autonomous driving. [ABSTRACT FROM AUTHOR]

This perspective discusses the challenges and opportunities of single‐photon LiDAR and Raman LiDAR systems. Typical uses of LiDAR and Raman LiDAR include autonomous vehicles, mapping and surveying, environmental monitoring, archeology, and cultural heritage, meteorology and weather forecasting, defense and security, natural resource management, and infrastructure inspection. Key directions of development include sensitivity and range, spatial resolution, speed and efficiency, integration with other sensors, miniaturization and portability, and cost reduction. With a market value of 1.5 billion US$ in 2021, LiDAR systems are projected to grow to 4.83 billion US$ by 2030, at a CAGR of 13.8% during the forecast period. [ABSTRACT FROM AUTHOR]

With the wide application of vision‐based autonomous driving and mobile robots, the impact of frequent sand‐dust weather on computer vision applications in landlocked countries during spring and autumn has also attracted more and more attention. Although there has been a lot of research on sand‐dust image enhancement, no research has been conducted on how to improve the positioning accuracy of vision‐based autonomous driving or mobile robots in sand‐dust environments, especially because there is currently a lack of dataset to evaluate visual positioning in sand‐dust weather. Therefore, a complete set of visual positioning dataset construction methods in sand‐dust weather is proposed to fill the gap in the evaluation dataset of application fields such as autonomous driving or mobile robot attitude estimation in sand‐dust weather. At the same time, this method is also suitable for the construction of visual positioning dataset under haze and other similar weather. In addition, this paper further demonstrates to readers how to use the converted dust visual positioning dataset to conduct positioning evaluation experiment of automatic driving in sand‐dust weather. [ABSTRACT FROM AUTHOR]

In the systems of industrial robotics and autonomous vehicles, instance segmentation is widely employed. However, manually labelling an object outline is time‐consuming. In order to reduce annotation costs, we present a weakly supervised instance segmentation method in this article. A deeply convolutional network is first used to construct multi‐scale feature maps for each object in the input image. After that, the encoder‐decoder framework with dynamic convolution is utilised to enhance model capacity and efficiency, while avoiding the issues of anchor design, proposal selection, and RoIAlign implementation. In particular, Dynamic Heads are used in the encoder to create dynamic convolution kernels, while Instance Heads are used in the decoder to provide the global feature map. With dynamic convolution, each instance can be segmented independently, reducing interference with other instances and improving segmentation accuracy. Under the supervision of projection loss and pixel point colour pairing loss, the contours of each object are finally outlined. On the PASCAL VOC and MS COCO datasets, the proposed method is competitive with more sophisticated approaches. In the VOC dataset, segmentation performance achieved 37.6% average precision with ResNet‐101 and FPN networks. The extensively visualised results demonstrate the effectiveness of the proposed encoder‐decoder framework with dynamic convolution. [ABSTRACT FROM AUTHOR]

Scene understanding of mobile laser scanning (MLS) point clouds is vital in autonomous driving and virtual reality. Most existing semantic segmentation methods rely on a large number of accurately labelled points, which is time‐consuming and labour‐intensive. To cope with this issue, this paper explores a weakly supervised learning (WSL) framework for MLS data. Specifically, a category balanced random annotation (CBRA) strategy is employed to obtain balanced labels and enhance model performance. Next, based on KPConv‐Net as a backbone network, a WSL semantic segmentation framework is developed for MLS point clouds via a deep consistency‐guided self‐distillation (DCS) mechanism. The DCS mechanism consists of a deep consistency‐guided self‐distillation branch and an entropy regularisation branch. The self‐distillation branch is designed by constructing an auxiliary network to maintain the consistency of predicted distributions between the auxiliary network and the original network, while the entropy regularisation branch is designed to increase the confidence of the network predicted results. The proposed WSL framework was evaluated on the WHU‐MLS, NPM3D and Toronto3D datasets. By using only 0.1% labelled points, the proposed WSL framework achieved a competitive performance in MLS point cloud semantic segmentation with the mean Intersection over Union (mIoU) scores of 60.08%, 72.0% and 67.42% on the three datasets, respectively. [ABSTRACT FROM AUTHOR]

By using kinematic state information obtained through vehicle‐to‐vehicle communications, connected autonomous vehicles (CAVs) can drive cooperatively to alleviate shockwave propagation associated with traffic disturbances. However, during the transition to full autonomy, CAVs and human‐driven vehicles (HDVs) will coexist on the road, creating mixed‐flow traffic. The inherent heterogeneity and randomness in human driving behavior can generate additional disturbances in the traffic flow. Further, HDVs without communication functionality (unconnected HDVs) can cause the control performance of CAVs to degrade by negatively impacting platoon formation. To proactively mitigate the negative impacts of HDVs in mixed‐flow traffic, this study proposes a cooperative control strategy with three components for platoons consisting of CAVs and unconnected HDVs: (i) a number estimator for estimating the number of HDVs between two CAVs, (ii) a kinematic state predictor for predicting the kinematic states of HDVs, and (iii) a multi‐anticipative car‐following controller (i.e., control strategy using kinematic state information of multiple preceding vehicles) for CAVs to maintain string stability and desired time headway. To initialize the proposed strategy, the number estimator is developed using a deep neural network (DNN). Then, a DNN‐based kinematic state predictor predicts the kinematic states of HDVs for CAVs to enable multi‐anticipative car‐following control. The multi‐anticipative car‐following controller is implemented using an extended intelligent driver model‐guided deep deterministic policy gradient algorithm, which ensures safety, string stability, and traffic efficiency. The effectiveness of the proposed control strategy is validated through numerical experiments using NGSIM data. Results indicate that the proposed strategy can produce accurate estimations of the number and the kinematic states of HDVs between CAVs. Further, it can achieve string stability while maintaining smaller time headways, compared to car‐following models used for training guidance under different market penetration rates of CAVs, which significantly improves traffic smoothness and mobility. [ABSTRACT FROM AUTHOR]

Car‐following prevails in daily traffic under various scenarios. However, most connected automated vehicle (CAV) car‐following algorithms in the literature only apply to one‐dimensional CAV control, which limits the application scenarios. This paper presents a two‐dimensional (2D) CAVs car‐following strategy on curved roads in the spatial domain with vehicle‐to‐vehicle and vehicle‐to‐infrastructure communication to expand the car‐following application scenarios. This control strategy constructs a 2D car‐following equilibrium policy by extending the simplified Newell's car‐following model. Based on that, a constrained optimal CAV car‐following control in the spatial domain is constructed to maintain the inter‐vehicle spacing and speed difference while regulating the lane deviation and avoiding work zones. As demonstrated by numerical results, our proposed algorithm maintains a high degree of consistency between equilibrium spacing and vehicle speed while duplicating the trajectory of the leading vehicle, implying empirical string stability. The results also suggest the robustness of handling different scenarios. [ABSTRACT FROM AUTHOR]

From automated to autonomous cars, a higher and higher reliability of the electrical components is required, while on the other hand the number of electrical components is continuously increasing in modern cars. Therefore for these components the estimation of a mean‐time‐to‐failure (MTTF) and a failure rate, a so‐called failure‐in‐time (FIT) rate, and the quantification of the corresponding uncertainties is crucial. The verification of the required FIT rates of less than one failure in one billion hours of lifetime is a challenge. Risk estimates have to be determined before and within the development process of future automated/autonomous cars. However, tests in real time take too long and are too expensive. As the next step, the uncertainty quantification of networks of components as in the vehicle electric system or a battery (with cells and management systems) are to be considered as well. This paper discusses several options for the determination of these failure rates. Following an overview we focus on the approach of experimental overstress tests and the combination of overstresses varying in time. Mathematically, the latter means a switching between different probability distributions in time. We state how to combine probability distributions that are typical for MTTF. Results for step functions in time as well as continuous changes in time of the probability distribution are presented. The main result is that the order of the temporal stresses is essential. This calls into question whether the common practice using temperature collectives is applicable here. [ABSTRACT FROM AUTHOR]

This paper is concerned with tele‐presence and tele‐operation of autonomous vehicles over the Additive White Gaussian Noise (AWGN) channel. This wireless communication channel is subject to transmission noise and transmission power constraint. An encoder, decoder and controller are proposed by implementing a novel linearization method for linearizing the nonlinear dynamic systems at operating points. For the linearized systems, the encoder, decoder and controller are implemented that were previously proposed for output tracking as well as stability of linear dynamic systems. Two novel linearization methods are proposed and their satisfactory performances are proved for output tracking as well as stability of nonlinear dynamic system. The first method is based on the fixed linearization rate and the second one is based on the variable (optimal) linearization rate. The decoder that is based on the second method is in fact the extended Kalman filter with the optimal linearization rate. The performances of these two methods are compared with each other and the other proposed methods by implementing them to the problems of the tele‐presence and tele‐operation of autonomous vehicles over the AWGN channel. Their satisfactory performances are illustrated. It is illustrated that the second method has higher computational complexity with slightly better performance and is applicable to a larger class of reference trajectories. [ABSTRACT FROM AUTHOR]

Connectivity is a key element enabling intelligent vehicles to communicate with each other and the Smart Road. In general, the connectivity is allowed by an On-Board Unit enabling the Vehicle to Everything communication. This paper proposes an innovative unit acting not only as a device allowing connectivity but also as an intelligent electronic control unit to perform advanced and adaptive control strategies able to give reference trajectories and actuator set-points to the low-level control systems of power-train and vehicle dynamics. In particular, based on a cascade model predictive control, an adaptive control strategy is proposed, considering time-varying parameters and information related to vehicle kinematics and dynamics. Such a strategy allows the vehicle to follow a certain origin-destination path in the inertial frame, based on an upper controller that considers a vehicle kinematic model so as to give speed references and target values for the steering angle at thewheels to the inner predictive control loop acting on both longitudinal and lateral vehicle dynamics. To check the effectiveness of the proposed approach, a comparison is made with existing cascade control strategies. The results show better safety and lane-keeping performance. Then, using Hardware-In-the-Loop testing for the proposed Intelligent On-Board Unit, the considered approach demonstrates robustness against parametric variations, signal delay and noise both in the Global Positioning System and in the yaw rate sensor. The achieved results show good robustness properties, safety performances and confirm the real-time execution of the cascade control strategy, paving the way to future developments necessary before tests in a real road scenario. [ABSTRACT FROM AUTHOR]

The previous point cloud compression methods only consider reducing the amount of data. However, in applications such as autonomous driving, the compression methods not only require smooth transmission, but also ensure the efficiency of downstream tasks. To this end, a task‐driven sampling network based on graph convolution is proposed to achieve point cloud compression and recovery. First, a downsampling network is presented to simplify and compress the point cloud, in order to optimize the compressed point cloud for downstream tasks, the task loss is added to loss function for end‐to‐end training. Then, an upsampling network with residual correction unit is presented to recover and reconstruct the point cloud. Experiments for point cloud classification task on ModelNet40 dataset show that the compressed point cloud obtained through our network can achieve higher classification accuracy compared to other similar methods, and the reconstructed point cloud can further improve classification accuracy. [ABSTRACT FROM AUTHOR]

The malicious physical attacks from both sensor and actuator sides make real threats to the security and safety of autonomous ground vehicles (AGVs). This paper focuses on the problem of neural‐network‐based event‐triggered adaptive security control (ET‐ASC) scheme for path following of AGVs subject to arbitrary abnormal actuator signal. First, we assume that an arbitrary abnormal signal is caused by arbitrary malicious attacks or disturbances from actuators. Then, radial basis function neural network (RBF‐NN) is used to reconstruct such abnormal actuator signal. Second, modelling issues on security path following control of AGVs with Sigmoid‐like ETC scheme are shown when the AGV is suffering from abnormal actuator signal. In what follows, an ET‐ASC scheme is developed to mitigate the adverse effects of abnormal actuator signal with the reconstructed abnormal signal based on a novel Sigmoid‐like event‐triggered communication scheme. By using the proposed RBF‐NN‐based ET‐ASC scheme, H∞$$ {H}_{\infty } $$ control performance can be guaranteed under arbitrary malicious actuator signal rather than such attacks following a specific probability distribution. Final, some simulation experiments are provided to verify the effectiveness of proposed ET‐ASC scheme. [ABSTRACT FROM AUTHOR]

The detection of river boundaries is a crucial branch of the intelligent perception of unmanned surface vehicles (USVs), it can be used to determine the driving areas of USVs, and also to ensure driving safety by limiting the effective drivable areas of USVs in the river areas. Aiming to detect the boundaries of incompletely structured river channels, this study proposes a real‐time detection method for river boundaries based on a Light Detection and Ranging (LiDAR) sensor. The point clouds that are disturbed by the water surface noise are filtered firstly, and then the spatial and geometric features are extracted separately from the point cloud detected above the water surface. To prevent the error detection and missing detection, the boundary point information is predicted and calibrated in real time by Extended Kalman Filter (EKF). A planning track generation algorithm for coastal autonomous cruise without relying on high‐precision maps, and a heading and distance adaptive control method by Proportional‐Integral‐Derivative (PID), and different driving line generation methods for driving along the narrow river and wide river are proposed respectively. The experimental data verification of river boundary detection shows that the algorithm is accurate, real‐time, and robust. [ABSTRACT FROM AUTHOR]

This study provides a signal timing model for isolated intersections under the mixed traffic environment consisting of connected and human‐driven vehicles (CHVs) and connected and automated vehicles (CAVs). Different from existing studies, CAVs are not controlled by traffic controllers and conduct trajectory planning themselves, which are called self‐organizing CAVs (SOCAVs). The specific trajectory planning strategies of SOCAVs are not accessible to traffic controllers either. The signal optimization problem is formulated as a mixed integer linear programming (MILP) model for total vehicle delay minimization. The states of SOCAVs and CHVs passing the stop bar are predicted without prior information of the trajectory planning strategies of SOCAVs. SOCAVs can lead approaching platoons to pass the intersection effectively, and such "leading effects" of SOCAVs are utilized. Phase sequence and duration are optimized with the "structure‐free" phasing scheme. A parallel particle swarm optimization algorithm with a grouping strategy is designed to solve the optimization model at a reduced scale for computational efficiency. Numerical studies validate that (1) the proposed algorithm significantly outperforms the benchmark method, which directly solves the proposed MILP model using the solver Gurobi 9.0, under medium and high traffic demand; and (2) the proposed model significantly outperforms fixed‐time and vehicle‐actuated signal control in terms of vehicle delay and throughput. Sensitivity analysis shows that the SOCAV penetration rate of 30% is sufficient to guarantee satisfactory performance of the proposed signal timing model. [ABSTRACT FROM AUTHOR]

Over the past ten years, autonomous driving has garnered a great deal of interest from both the scientific community and business. Strong technological advancements have made automated driving more practical because human driving abilities seem limited in terms of driving experience, reaction time, and the effectiveness of real‐time decisions. The development of highly autonomous driving algorithms is inextricably tied to planning and changing a vehicle path that must be user‐acceptable, efficient, and collision‐free. Path planning for road vehicles is a difficult problem due to the high speed involved and the requirement to assure passenger safety. Here, a new path‐planning method is developed for both connected and disconnected automatic road vehicles on multilane highways. This paradigm states that the right phrases to describe the objectives of vehicle improvement, passenger comfort, prevention of vehicle‐to‐vehicle collisions and road deviations are included in the objective function. Hunger Games improved Archimedes optimization (HGE‐ARCO) is used to optimize the paths for achieving better‐planned outcomes. At the 100th penetration rate, the HGE‐ARCO scheme reached a top speed of about 99 km/h. The results shows unmistakably that the proposed HGE‐ARCO produces a time of 12.3021 s, which is less than other conventional methods. [ABSTRACT FROM AUTHOR]

The article discusses critical barriers and make recommendations how to make semi-automated vehicles (AV) accessible to older drivers with mobility needs. Topics covered include ways on how AV manufacturers can gain the trust of older adults with AV technology, design and adjustments to AV vehicles needed to accommodate older drivers with visual, cognitive and/or motor impairments, and the need to revise fitness-to-drive procedures to ensure they meet the basic requirements of driving an AV.

Semantic segmentation is a fundamental technology for autonomous driving. It has a high demand for inference speed and accuracy. However, a good trade‐off between accuracy and latency is yet not present in existing semantic segmentation approaches. Due to the limitation of speed, the authors cannot increase the number of network layers without limit and cannot design modules like in the networks without real‐time. It is a challenging problem how to design a model with good performance under limited resources. To alleviate these issues, in this study, the authors propose a refinement co‐supervision network (RCNet), which is real‐time on a high‐resolution image (1024×2048). The authors first construct the context refinement module, which can provide low computation cost way for obtaining the large receptive field and context information. Furthermore, a boundary co‐supervision mechanism is proposed. It strengthens the optimisation of easily neglected boundaries and small targets. Experimental results reveal that the proposed RCNet outperforms seven representative semantic segmentation methods. [ABSTRACT FROM AUTHOR]

Accurate and efficient point cloud registration is essential in various fields, such as robotics, autonomous driving and medical imaging. The size of point clouds presents a significant challenge for existing registration methods. In this paper, a novel point cloud sampling method to improve the performance of the point cloud registration process is proposed. Instead of geometric feature preservation, which is preferred in most existing sampling methods, our approach scales every point and groups the scaled points into clusters to generate a histogram for the point cloud. The histogram is then used to identify the most significant regions of the point cloud to create the downsampled output data. Experimental results demonstrate that the proposed method improves accuracy and is robust against noise. Registration errors are reduced by up to 7% in rotation and 116% in translation. Additionally, the proposed method filtered out up to 98% of noise from the point cloud that was uniformly distributed at a rate of 25%. [ABSTRACT FROM AUTHOR]

As unmanned vehicles become smaller and more autonomous, it is becoming feasible to use them in large groups with comparatively few human operators. Design and analysis of such distributed systems are complicated by the many interactions among agents and phenomena of human behavior. In particular, human susceptibility to fatigue and cognitive overload can introduce errors and uncertainty into the system. In this paper, we demonstrate how advanced computational tools can help to overcome these engineering difficulties by optimizing multirobot, multioperator surveillance systems for cost, speed, accuracy, and stealth according to diverse user preferences in multiple case studies. The tool developed is a graphical user interface that returns the optimal number and mix of diverse agent types as a function of the user's trade‐off preferences. System performance prediction relies on a multiagent simulation with submodels for human operators, fixed‐wing unmanned aerial vehicles (UAVs), quadrotor UAVs, and flapping wing UAVs combined in different numbers. [ABSTRACT FROM AUTHOR]

Trajectory planning is a core technology for autonomous vehicle directlyreflecting the driving safety and efficiency. In this paper, a spatial‐speed decoupled planning method is studied for real‐time trajectory generation in the on‐road environment. The proposed approach mainly includes two parts: optimization‐based lateral planning and selection‐based longitudinal speed planning. The optimization‐based lateral planning is employed to generate an optimal collision‐free and smooth path by solving a quadratic programming problem. Specifically, the lateral planning first constructs a safe corridor by integrating obstacles and initial risky corridor together in the Frénet frame. The safe corridor is useful for quadratic programming problem formulation. The selecting‐based longitudinal speed planning is proposed to generate a suitable and continuous velocity trajectory. The novel speed selector considering four cases is designed to select a more suitable reference velocity in different lane situations. The continuous velocity trajectory is obtained by solving piecewise continuous quartic polynomial. As a result, the combination of the spatial path and the velocity trajectory is the final planning result. The proposed algorithm is tested extensively in a simulation environment. Experimental results demonstrate that the proposed algorithm has good real‐time property and practical validity. [ABSTRACT FROM AUTHOR]

A novel approach is presented here to solve the problem of motion occlusion and motion edge blurring in the existing scene flow estimation. First instance segmentation and superpixels are combined to segment the target and other regions in fusion segmentation. The pixels in each block are then redistributed by the optical flow to ensure the motion of pixels in the subblocks is consistent. Moreover, the 3D motion of subblocks with sufficient pixels is estimated by the energy function, and the others are considered outliers. Finally, the Driving and the KITTI benchmarks are used to evaluate the proposed method. The results demonstrated that the fusion of segmentation and redistribution is positive for the estimation, and this method outperforms the other state‐of‐the‐art methods both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

Semantic segmentation is a critical topic in computer vision, and it has numerous practical applications, including mobile devices, autonomous driving, and many other fields. However, in these application scenarios, it is often essential for the segmentation models to achieve a balance between efficiency and performance. A lightweight attention‐guided redundancy‐reuse network (LARNet) was proposed to address this challenge in this paper. Specifically, the multi‐scale asymmetric redundancy reuse (MAR) module was designed as the main component of the encoder for dense encoding of contextual semantic features. Furthermore, the efficient attention fusion (EAF) module was established for multi‐scale information fusion via the channel and spatial attention mechanisms in the decoder. A series of experiments were conducted to verify the proposed network. The results of tests on multiple datasets suggest that the network has higher accuracy and faster speed than the existing real‐time semantic segmentation methods. [ABSTRACT FROM AUTHOR]

This study proposes a reconfigurable fault‐tolerant control method using an adaptive fault identification technique with application to an unmanned surface vehicle with consideration of environmental disturbances and system constraints, including both second‐order input operations (actuator magnitude and rate faults) and multi‐classification fault modeling features (lock‐in‐place or hard‐over, and loss of effectiveness). To begin with, unknown parameter compensator‐based observers with adaptive projection laws are designed for the respective double‐parameter and single‐parameter adaptive fault identification cases, and it is proved that the actual input estimation and fault parameter estimation errors are bounded. Then, double‐parameter and single‐parameter adaptive reconfigurable fault‐tolerant controllers are synthesized by combining the finite‐time baseline tracking control and terminal sliding‐mode mechanism to guarantee the second‐order dynamical tracking errors converge to the origin for the proper unmanned surface vehicle operation regardless of actuator magnitude and rate faults. Finally, simulation results and comparisons demonstrate the effectiveness and superiority of the proposed reconfigurable fault‐tolerant control algorithm. [ABSTRACT FROM AUTHOR]

Summary: This paper investigates the surge speed tracking control of an autonomous surface vehicle (ASV) subject to fully unknown internal dynamic, external disturbance, and unknown control input gain. An adaptive anti‐disturbance sampling control method is proposed for an ASV without using any model parameters. Specifically, by utilizing real‐time and historical data, discrete‐time reduced‐order and full‐order concurrent learning extended state observers (CLESOs) are designed to estimate the unknown ASV model parameters and ensure estimation convergence without requiring persistent excitation. Then, a surge speed tracking control law is designed based on the discrete‐time full‐order CLESO. Through Lyapunov stability analysis, the closed‐loop system is proven to be stable, and the estimation and tracking errors are bounded. Simulation and hardware‐in‐loop experimental results validate the effectiveness of the proposed discrete‐time CLESOs for the surge speed tracking of an ASV with fully unknown dynamic model. [ABSTRACT FROM AUTHOR]