The development of physically assistive robots capable of providing eating assistance holds tremendous potential in improving the quality of life for seniors and individuals with disabilities. However, autonomous feeding depends on accurate eating intention inference. Unfortunately, most existing methods fall short in investigating human intention and the dynamic variability of human behavior during eating. This article proposes an eating intention inference method for assistive robots in human–robot interaction by combining the Residual Network (ResNet) and long short-term memory (LSTM), facilitating autonomous feeding by robotic arms. Taking inspiration from observable facial movements during eating, we extract crucial features, including facial landmarks and the amplitude of the chin-to-nose distance computed from them, which clearly reflects human eating intention. Considering the noise and data corruption present in the input sequences, we employ the Gaussian function as the convolutional kernel within the ResNet architecture. Furthermore, we incorporate an aggregated variance attention mechanism in the LSTM hidden layer to better capture the dynamic changes in the input data. Experimental results demonstrate the strong performance of our method, achieving an accuracy of 98.0% on a self-collected dataset and outperforming other approaches. Real-world experiments with a robotic arm and an RGB camera verify the efficacy and real-time predictive performance of the proposed method.

Electric vertical takeoff and landing (eVTOL) aircraft are anticipated to become a cornerstone of future urban air mobility (UAM) and intelligent three-dimensional transportation systems in smart cities. Enhancing passenger comfort is crucial for improving public acceptance of eVTOLs. However, motion sickness (MS) monitoring and mitigation pose key challenges in this context. This paper presents a comprehensive review of MS research for eVTOL applications, focusing on mixed MS induced by the combined effects of physical motion and visual stimuli in intelligent eVTOL cockpits. The underlying theories and MS-related eVTOL characteristics are first examined, based on which the technologies capable of quantifying and estimating mixed MS are then reviewed. The usage of multi-modal visual and physiological signals combined with classical MS theories is highlighted. Subsequently, the methods for MS alleviation in eVTOLs are investigated. Lastly, this work delineates critical challenges stemming from eVTOL feature complexity, eVTOL-specific MS data scarcity, intricate mixed MS modeling, and its neglect in intelligent flight systems. A potential monitoring and mitigating framework for MS in eVTOL is proposed to bridge these gaps and advance practical development.

Deep Reinforcement Learning (DRL) based navigation methods have demonstrated promising results for mobile robots, but suffer from limited action flexibility in confined spaces. Conventional DRL approaches predominantly learn forward-motion policies, causing robots to become trapped in complex environments where backward maneuvers are necessary for recovery. This paper presents MAER-Nav (Mirror-Augmented Experience Replay for Robot Navigation), a novel framework that enables bidirectional motion learning without requiring explicit failure-driven hindsight experience replay or reward function modifications. Our approach integrates a mirror-augmented experience replay mechanism with curriculum learning to generate synthetic backward navigation experiences from successful trajectories. Experimental results in both simulation and real-world environments demonstrate that MAER-Nav significantly outperforms state-of-the-art methods while maintaining strong forward navigation capabilities. The framework effectively bridges the gap between the comprehensive action space utilization of traditional planning methods and the environmental adaptability of learning-based approaches, enabling robust navigation in scenarios where conventional DRL methods consistently fail.

This work focuses on enhancing the generalization performance of deep reinforcement learning-based robot navigation in unseen environments. We present a novel data augmentation approach called scenario augmentation, which enables robots to navigate effectively across diverse settings without altering the training scenario. The method operates by mapping the robot’s observation into an imagined space, generating an imagined action based on this transformed observation, and then remapping this action back to the real action executed in simulation. Through scenario augmentation, we conduct extensive comparative experiments to investigate the underlying causes of suboptimal navigation behaviors in unseen environments. Our analysis indicates that limited training scenarios represent the primary factor behind these undesired behaviors. Experimental results confirm that scenario augmentation substantially enhances the generalization capabilities of deep reinforcement learning-based navigation systems. The improved navigation framework demonstrates exceptional performance by producing near-optimal trajectories with significantly reduced navigation time in real-world applications.

This paper proposes a whole process method of multi-quadrotors from detecting and locating to encircle and track targets. The reconnaissance quadrotor realizes accurate target detection based on the one-stage target detector of convolutional neural network. Then, based on a pinhole camera projection model, the target is located from the 2D pixel coordinates to 3D North East Down(NED) coordinates world. Finally, the hunter quadrotors realize the target encircling and the time-varying formation tracking based on the consensus theory. At the same time, we prove the stability of the time-varying formation tracking control. We built a multiple quadrotors platform composed of one reconnaissance quadrotor and four hunter quadrotors, and deployed the method on the platform to conduct a series of experiments with a minibus as the target for validation. The results indicate that reconnaissance quadrotor can accurately detect target and have small localization errors in the north and east directions. Hunter quadrotors can encircle and track targets in time-varying formation based on target information provided by reconnaissance quadrotor. Experiments have demonstrated that the method achieves high-speed and accurate target encirclement.

Multi-object tracking (MOT) plays a pivotal role in the field of autonomous driving, where the objective is to track multiple objects across consecutive video frames while maintaining their identities. While existing tracking methods have made significant progress, they still face challenges in handling rapid or non-linear object movements and inaccuracies in object detection. The performance of MOT algorithms, including SORT, is often limited by the assumption of constant velocity in motion prediction. This assumption fails to accurately model scenarios involving acceleration or deceleration. This paper presents an effective enhancement to the classic SORT framework, addressing these limitations without resorting to computationally expensive deep learning models. First, we modify the Kalman filter’s motion model with a constant acceleration model to more accurately predict object motion in dynamic scenarios. Second, we introduce a spatio-temporal consistency constraint, implemented as a simple velocity-based filter, to identify and reject anomalous detections, thereby improving tracking robustness. Evaluated on the V2XSim 2.0 dataset, our enhanced method demonstrates consistent performance gains over the baseline across all tested object detectors. A detailed ablation study further confirms that both components contribute positively and exhibit a synergistic effect, validating our approach as a lightweight yet powerful solution for improving tracking accuracy and trajectory coherence.

Intelligent Automation Systems, such as automated storage and retrieval systems, self-driving vehicles, various types of autonomous robots, and autonomous workshop plants, act independently of direct human supervision. Their impact on society and human life will be significant. These automation systems are safety-critical, complex, and powerful with a higher-level functionality. Safety and reliability to perform their tasks safely and minimize failures is one of the key challenges and becomes costly and difficult to achieve. The development of novel safety and reliability technologies dealing with theoretical aspects and for intelligent automation systems has become a hot spot in recent years. With the novel safety and reliability technologies, the intelligent automation systems can detect system failures, identify operation risks, predict unknown safety hazards and vulnerabilities, and avoid situations that pose risks to humans, property, or the automation systems themselves. Recent developments confirm that there are still areas of research to be explored within the safety-critical approaches. This Special Issue on Emerging Trends in Safety-critical Issues for Intelligent Automation Systems of IEEE Transactions on Automation Science and Engineering (TASE) aims to present recent advances in theories, methods, and applications that address safety-critical challenges in autonomous intelligent systems. The objective is to compile state-of-the-art research that contributes to the development of resilient and trustworthy automation solutions in safety-sensitive scenarios. After a thorough and rigorous peer-review process, 27 high-quality articles were selected from numerous submissions worldwide. These articles closely align with the Special Issue’s scope and can be categorized into seven key topics. - Risk assessment and model-based safety and cybersecurity analysis [A1], [A2], [A3], [A4], [A5]. - Intelligent fault detection and fault-tolerant control [A6], [A7], [A8], [A9], [A10]. - Reliability and traceability of decision-making for intelligent automation systems [A11], [A12], [A13]. - Conflict detection and resolution in intelligent automation systems [A14], [A15]. - Safety- and security-related issues including functional safety and system security [A16], [A17], [A18]. - Design, development, validation, and applications of intelligent automation systems such as UAVs, UGVs, and UUVs [A19], [A20], [A21], [A22], [A23]. - Human-robot collaboration, risk assessment of intelligent automation [A24], [A25], [A26], [A27]. We believe this collection will provide a valuable reference for academia and industry alike, and inspire further research in this rapidly evolving field.

This paper proposes a novel hierarchical methodology to planning safe UAV trajectories in complex environments. We start by improving a canonical hybrid A* in relation to high memory requirements, performance degradation, and the low efficiency customarily observed in the initial global trajectory suggested by the planner. Then, the Marden theorem is applied - for the first time in local path planning - to generate continuous, non-intersecting, enclosed, and safe flight corridors, termed homotopic enclosed safe motion corridors (HESMCs) hereafter. This is efficiently realized through a series of unique ellipsoids along the initial route. Meanwhile, the optimized motion trajectory along the corridors is built by considering two waypoints and prescribed performance functions. The resolved path is safe and complete, with a comprehensive Lyapunov stability analysis included to ensure accurate and efficient trajectory tracking. The simulation and physical tests demonstrate the superiority of our proposed planner over existing state-of-the-art methods, with consistent and significant improvements in processing time and guaranteed completeness. Note to Practitioners—The authors perceived the contribution of the manuscript of particular relevance to users of UAVs seeking advanced safety in their guidance and navigational solutions, offering a blend of theoretical innovation and practical applicability. The work introduces a distinct hierarchical motion planner specifically designed to enhance safety and reliability in UAV navigation. Key to this is the development of an improved hybrid A* algorithm for global planning, which effectively tackles practical issues such as high memory consumption and performance degradation. A significant theoretical contribution is the application of the Marden theorem in local optimization. This facilitates the generation of homotopic enclosed motion corridors using unique safe boundary ellipsoids, thus reducing navigation complexity and the risk of failure during task execution. Additionally, the proposed scheme emphasizes the generation of motion trajectories considering position errors and prescribed performance functions, supplemented by a thorough Lyapunov stability analysis. Looking ahead, we aim to extend the proposed scheme in the context of UAV swarms for more efficient navigation in complex environments.

This article investigates the topic of adaptive tracking consensus for a family of nonlinear multi-agent systems modeled by random differential equations, which are different from well-known stochastic differential equations. This paper provides some primitive results on random nonlinear multi-agent systems. An improved backstepping method named command filtered control is adopted to derive the adaptive control law, where the convergence of the filtering error is guaranteed. To tackle the serious nonlinearities and uncertainties, a series of dynamic gains are introduced in the design process. The tracking errors for each follower concerning the output of the leader can be regulated arbitrarily to a small enough value by choosing appropriate tuning parameters. All signals of the closed-loop system are analyzed to have bounds almost surely. Moreover, the feasibility of the theory developed in this paper is validated by an example of numerical simulation. Note to Practitioners—Inspired by all kinds of biological clustering or grouping behaviors in our natural world, the research on multi-agent systems has long been popular in both theoretical and engineering scenarios. In addition, colored noises are ubiquitous and negligible when dealing with control problems of different engineering plants. Based on the above observation, this paper was motivated to realize the tracking consensus control of a class of nonlinear multi-agent systems disturbed by colored noise, which is also called random nonlinear systems, with the help of an enhanced adaptive backstepping approach called command filtered control. Although there exist nonlinearities and random noises in each follower agent, the objective of output consensus still could be achieved with the combination of the methods of dynamic gains and command filtering. The application potential of this research is considerable, such as drone formation performance and drone cruise. Our future research will further investigate control problems of random nonlinear multi-agent systems under some practical obstacles such as actuator failures.

Networked systems are increasingly the target of cyberattacks that exploit vulnerabilities within digital communications, embedded hardware, and software. Arguably, the simplest class of attacks – and often the first type before launching destructive integrity attacks – are eavesdropping attacks, which aim to infer information by collecting system data and exploiting it for malicious purposes. A key technology of networked systems is state estimation, which leverages sensing and actuation data and first-principles models to enable trajectory planning, real-time monitoring, and control. However, state estimation can also be exploited by eavesdroppers to identify models and reconstruct states with the aim of, e.g., launching integrity (stealthy) attacks and inferring sensitive information. It is therefore crucial to protect disclosed system data to avoid an accurate state estimation by eavesdroppers. This survey presents a comprehensive review of the existing literature on privacy-preserving state estimation methods, while also identifying potential limitations and research gaps. Our primary focus revolves around three types of methods: cryptography, data perturbation, and transmission scheduling, with particular emphasis on Kalman-like filters. Within these categories, we delve into the concepts of homomorphic encryption and differential privacy, which have been extensively investigated in recent years in the context of privacy-preserving state estimation. Finally, we shed light on several technical and fundamental challenges surrounding current methods and propose potential directions for future research. Note to Practitioners—With the increasing openness and anonymization of the networked estimation systems, privacy concerns require to be paid more attention. The essence of the privacy-preserving approaches is to seek certain tradeoffs among privacy budget and various performance metrics, such as utility and energy. Cryptographic methods are suitable for high-performance processors because they need sufficient computation resources to generate and operate complicated secret keys. By contrast, perturbation methods can be realized faster, but the adverse impact on the legitimate systems should be limited not to violently disrupt the desired operations. In conclusion, the choice of these encryption approaches depends on practical demands. Moreover, general state-space models, which can represent most real-world dynamics, are the basis of the reviewed methods. Thus these approaches can be easily deployed to practical engineering systems to effectively guarantee their privacy, providing significant application values.

This paper originates from two well-accepted challenges in the control of a quadrotor with a cable-suspended payload: 1) designing a refined controller based on high-precision payload swing modeling to achieve the quantized prescribed robustness; and 2) resolving the trajectory tracking performance degradation issue caused by input saturation. To combat these challenges, we start with establishing a precise payload swing model. The experimental investigation reveals the fact that neglect of realistic factors like cable-joint dry friction and cable elasticity has significant impacts on the precision of the existing models, especially under small swing angles. Therefore, we propose a new integrated drag model including a novel sign of the payload airspeed-dependent term, which lumps all payload swing damping factors together. This model is experimentally verified to be precise to provide the payload swing disturbance spectrum for quantitatively designing the bandwidth of the uncertainty and disturbance estimator (UDE). Furthermore, we resolve the input saturation issue by augmenting the classic UDE-based controller with a tracking differentiator (TD). Rigorous performance analysis derives a clear relationship between the control performance and the UDE parameter, which forms a simple yet effective parameter tuning guideline for practical applications to ensure the prescribed robustness and trajectory tracking accuracy. The effectiveness and advantage of the proposed controller are verified via comparative experiments in different flight scenarios. Note to Practitioners—The control input saturation issue and multi-parameter optimization are frequently encountered in engineering practices. When applying the TD to address the input saturation, the selection of parameter r in the TD depends on the reference continuity. Specifically, if the reference is continuous, then r can be large; otherwise r should be small to smooth the reference to avoid input saturation. For the multi-parameter optimization, the feedback gains$k_{p}$and$k_{d}$should be tuned first to guarantee the system stability, followed by decreasing the UDE parameter T to improve the system robustness. However, the feasible range of T may be restricted by the measurement noise and actuator bandwidth in practice. The proposed algorithm is applicable not only in aerial transportation systems but also in addressing other disturbance rejection problems.

This article presents the development and optimization of a wheel-legged biped robot designed for community inspection tasks. The robot combines the efficiency of wheeled robots with the adaptability of legged systems, making it suitable for navigating diverse terrains in semistructured environments. The main innovations of this research include the development of an integrated control system that combines balance control, state estimation, and terrain adaptation using multisensor fusion. The robot’s mechanical structure is designed to withstand jumps and falls, while its electronic hardware and software architecture ensure real-time control and robust performance. Experiments demonstrate the robot’s capabilities including tracking velocity as high as 2 m/s, resisting severe disturbance or slippage, and traversing steps over 10 cm automatically. The results show that the proposed control methods and hardware design effectively ensure the robot’s robustness and adaptability, validating its potential for practical community inspection applications. This work contributes to the growing field of autonomous robots in public service and provides a foundation for future research and development.

Accurate and real-time acquisition of vehicular system dynamic states, road surface conditions, and motion states of surrounding participants is crucial for the safety, passenger comfort, and operational efficiency of autonomous vehicles (AVs) and connected automated vehicles (CAVs). In recent years, a significant amount of research has contributed to the field of state estimation for vehicles, roads, and pedestrians. From the systemwide perspective of intelligent transportation systems to a focused view on “vehicle-road-pedestrian”, this survey aims to provide a comprehensive review and summary of recent state estimation techniques for vehicle motion, road surface, and pedestrian motion. A thorough analysis of the reviewed literature, relevant datasets, evaluation metrics, and experimental platforms in this field is also conducted. Finally, existing challenges and future research directions about methods and performance evaluation are further discussed. This survey is expected to contribute to the advancement of research in dynamic state estimation of vehicle-road-pedestrian, thereby facilitating the development of efficient and safe intelligent transportation systems.

In the quadrotor-suspended-payload system, simultaneously achieving trajectory tracking and payload anti-swing control is essential but challenging. We reveal that the fast maneuver required by the anti-swing control may not be effectively executed by the classic quadrotor dual loop control framework, due to the inherent non-ideal inner loop actuation bandwidth in practice. To address this issue, we propose a novel hierarchical control framework incorporating the uncertainty and disturbance estimator (UDE)–based backstepping control. The proposed framework consists of three loops, where the outer loop tracking and anti-swing controller and the inner loop attitude controller are both designed in the conventional way, and more importantly, a newly proposed intermediate loop is induced between them. In the intermediate loop, the robust dynamic compensator is developed based on an experimentally verified actuator model to extend the quadrotor actuation bandwidth, such that the outer loop control bandwidth requirements are quantitatively satisfied. Furthermore, the system stability is proved by the Lyapunov method along with the system performance analysis based on the singular perturbation theorem. Finally, comparative simulation and experimental results are presented to demonstrate the feasibility and effectiveness of the proposed controller.

Fairness in Federated Learning (FL) is imperative not only for the ethical utilization of technology but also for ensuring that models provide accurate, equitable, and beneficial outcomes across varied user demographics and equipment. This paper proposes a new adversarial architecture, referred to as Adversarial Graph Attention Network (AGAT), which deliberately instigates fairness attacks with an aim to bias the learning process across the FL. The proposed AGAT is developed to synthesize malicious, biasing model updates, where the minimum of Kullback-Leibler (KL) divergence between the user's model update and the global model is maximized. Due to a limited set of labeled input-output biasing data samples, a surrogate model is created, which presents the behavior of a complex malicious model update. Moreover, a graph autoencoder (GAE) is designed within the AGAT architecture, which is trained together with sub-gradient descent to reconstruct manipulatively the correlations of the model updates, and maximize the reconstruction loss while keeping the malicious, biasing model updates undetectable. The proposed AGAT attack is implemented in PyTorch, showing experimentally that AGAT successfully increases the minimum value of KL divergence of benign model updates by 60.9% and bypasses the detection of existing defense models. The source code of the AGAT attack is released on GitHub.

Given the limitations of current methods in terms of accuracy and efficiency for robot scene recognition (SR) in domestic environments, this paper proposes an active scene recognition approach (ASR) that allows the robot to recognize scenes correctly using less images, even when the robot's position and observation direction are uncertain. ASR includes a behavior cloning-based action classification model, which can adjust the robot view actively to capture beneficial images for scene recognition. To address the lack of essential expert data for training the action model, we introduce an expert data generation method that avoids time-consuming and inefficient manual data collection. Additionally, we present a multi-view scene recognition method to handle the multiple images resulting from view changes. This method includes a scene recognition model that scores each image and a revision and prediction method to mitigate the compounding error introduced by behavior cloning as well as output the finial recognition result. We conducted numerous comparative experiments and an ablation study in various domestic environments using a publicly simulated platform to validate our ASR method. The experimental results demonstrate that our proposed approach outperforms state-of-the-art methods in terms of both accuracy and efficiency for scene recognition. Furthermore, our method, trained in simulated environments, demonstrates excellent generalization capabilities, allowing it to be directly transferred to the real world without the need for fine-tuning. When deployed on a TurtleBot 4 robot, it achieves precise and efficient scene recognition in diverse real-world environments.

This research article considers the subject of finite-time control for a set of uncertain high-order stochastic nonlinear systems (HOSNSs) with unknown time-varying control coefficients. The growth conditions for the uncertain nonlinearities are more inclusive compared to those found in most previous studies. The exponents of high-order systems can take arbitrary rational numbers, which can be represented by two positive odd integers, and they are not all exactly larger than 1. Based on the conventional backstepping idea, the method ofadding a power integratoris adopted to design an adaptive controller that renders the closed-loop system stochastically finite-time stable (SFTS). Due to the general nonlinearities, high-order exponents, and stochastic characteristics, the design process requires more effort, so domination instead of cancellation techniques is used. A simulation example demonstrates the correctness of the theoretical results.

To enhance path tracking performance in the presence of steering motor faults, this paper introduces an active fault-tolerant control strategy for electric vehicles with four inwheel motors. Firstly, the single-track vehicle dynamics model and steering faults model are established. The control framework includes an upper-level linear parameter-varying model predictive controller for active front steering, an upper-level event-triggered predictive controller for direct yaw control, and a lower-level torque allocation controller. The bi-directional long short-term memory (Bi-LSTM) network is used for low-latency rapid detection of steering system faults. If the fault is detected, the upper-level controller for direct yaw control is triggered to mitigate the negative impact of the steering actuator faults. Based on the high-fidelity CarSim model, the simulation test is conducted under a double-lane change scenario with severe stuck faults in the steering system. The simulation results indicate that the proposed scheme can reduce the cumulative tracking error by 37.86% under the set stuck faults compared with the baseline method.

Agile flight is significant for target tracking, search and rescue, and delivery applications. To achieve agile flight, we can exploit the actuator’s potential by utilizing the full dynamics of the quadrotor. However, the 6-degrees-of-freedom dynamics render the optimization problem non-convex, and thus computationally intractable. To tackle this issue, we convert the original non-convex optimal control problem (OCP) into a convex subproblem and use the sequential convex programming (SCP) algorithm to iteratively solve the subproblems. Moreover, the state-triggered constraints are proposed to simultaneously optimize the time allocation of the waypoint and the trajectory itself. The numerical and physical experiment results1show that the SCP algorithm can significantly reduce the computing time while ensuring a satisfactory solution.

In the field of Simultaneous Localization and Map Building (SLAM), robots have become highly proficient in self-localization. However, the localization and tracking of irregular objects in the environment still pose significant challenges. Consequently, this work proposes a real-time approach to detect moving objects in the environment and estimate their six-degree-of-freedom (6-DoF) motion without making any assumptions about the type of the objects. The central idea is to analyze the correlation between map points and segmenting point clouds which are parts of dynamic objects belonging to different groups. Then, a region-based bundle adjustment method has been developed to obtain the optimized pose of the objects on the SE(3) manifold. Our method surpasses existing appearance-based approaches, which struggle to handle irregular objects. To validate the effectiveness of our algorithm, we tested our algorithm in real-world environments. The results demonstrate our method achieves superior accuracy in tracking dynamic objects, showcasing its potential for various applications.

In this paper, we propose the innovative use of Intelligent Vehicle Carriers (IVCs) as a key solution to address the energy constraints of small-scale unmanned Intelligent Vehicles (IVs). IVCs function as both transporters and charging stations, significantly boosting the operational range and efficiency of IVs. Our research delves into the IV-IVC collaborative framework, highlighting the existing challenges, exploring potential solutions, and examining a range of applications. This study offers a visionary approach to revolutionizing intelligent transportation systems by leveraging the synergistic relationship between IVs and IVCs.

Internet of Things (IoT) devices have been widely deployed to build smart cities. How to efficiently collect data from large-scale IoT devices is a valuable and challenging research topic. Benefiting from agility, flexibility, and deployability, an unmanned aerial vehicle (UAV) has great potential to be an aerial base station. However, given the limited battery capacity, the flight time of a UAV is limited. This article focuses on using multi-UAVs to execute long-distance data collection from large-scale IoT devices. We design a multi-UAVs-assisted large-scale IoT data collection system. The core facilities of this system are the data center and charging stations, which are equipped with a limited number of charging piles to provide charging services for UAVs. To ensure the efficient operation of the system, the problem of deployment and flight planning of UAVs is formulated as a joint optimization problem. To solve the problem, a population-based optimization algorithm with a three-layer structure, namely, EDDE-DPDE, is proposed. It includes two core components: 1) elite-driven differential evolution (EDDE) and 2) differential evolution with a dynamic population (DPDE), which are two variants of differential evolution. Thanks to ideas of reusing elite individuals and historical information, the proposed EDDE-DPDE shows an improvement of at least 11.11% compared with four powerful algorithms in terms of average travel time.

Despite recent advancements in robotic exploration, estimating the three-dimensional (3-D) motion of unknown dynamic objects, which are prevalent in chaotic construction sites, remains an unresolved challenge. In this work, we studied the problem of detecting and tracking the six-degree-of-freedom (6-DoF) motion of unknown moving objects using only a stereo camera. The fundamental idea of our approach is to estimate the positions of map points at each timestamp and model their uncertainty in position, such that the correlation between map points can be found by segmenting point clouds that are parts of moving objects into different groups. By analyzing the correlation between map points, we can detect the dynamic objects in the scene without making any assumptions about the type of objects. Thus, this approach enables tracking of both known and unknown moving objects, such as a robot carrier with stacked luggage. It surpasses the performance of existing appearance-based methods, which often face difficulties when dealing with unknown objects. Through extensive real-world experiments, we demonstrate the effectiveness of our approach in accurately tracking moving objects, highlighting its potential for various applications. In addition, we successfully deploy our object motion estimation algorithm in an unmanned ground vehicle (UGV) for the purpose of avoiding unknown moving objects in real-world scenarios. This practical implementation underscores the applicability of our approach in real-world settings.

Random nonlinear systems (RNSs) are a class of nondeterministic systems that are distinguished from the intensively studied stochastic nonlinear systems (SNSs). The research on RNSs is becoming more and more popular thanks to its practical significance. To economize communication resources and alleviate network burden, a model-based event-triggered control (MBETC) scheme is applied to a family of RNSs in a strict-feedback fashion. With the help of the adaptive command filtering design technique, all signals of the closed-loop system are rendered ultimately bounded in the mean sense, and the notorious Zeno behavior is circumvented to appear. A simulation example is taken to manifest the validity of the main results.

This paper introduces a novel algorithm, refer to NEWDQN, which is based on the deep Q-network (DQN) framework. The primary objective of this algorithm is to optimize the successful rate both in autonomous drone obstacle avoidance and target tracking tasks, while this algorithm can also improve the drawbacks of the previous algorithm in convergence. Furthermore, the algorithm endows the drone with environment perception capabilities and incorporates a direction-based reward-penalty function into the reward function, enhancing the drone's generalization ability and overall performance. Extensive simulations demonstrate that compared to conventional DQN and Double DQN (DDQN) algorithms, NEWDQN exhibits faster convergence speed, shorter tracking paths, and more robust adaptability to different environments.

This paper considers using drones to conduct the last-mile parcel delivery. To enable the beyond-battery-lifetime flight, drone stations are considered to replace or recharge the battery for drones. We focus on the flight planning problem with the goal of minimizing the total travel time from the depot to a customer, a key indicator of the quality of service. We investigate four typical ways for the drone to get extra energy at drone stations: 1) replacing the battery with a fresh one, 2) recharging the battery to the full capacity, 3) recharging the battery to the optimal level, and 4) recharging the battery to the optimal level accounting for the availability of drone stations (i.e., whether a drone station is occupied by other drones). While the first two scenarios can be formulated following the framework of integer linear programming, the last two scenarios turn into mixed-integer nonlinear programming problems. To address the later problems, we present a framework in which discretized state graphs are constructed first and then the optimal paths are found by graph searching algorithms. We propose a dynamic version of Dijkstra’s algorithm to deal with the unavailability issue of drone stations. The algorithm can quickly find the optimal flight path for a drone, and extensive computer-based experimental results have been presented to demonstrate the effectiveness of the proposed method. Note to Practitioners—Multi-rotary unmanned aerial vehicles (UAVs), also known as drones, have been regarded as a promising means to reshape future logistics. To save human labour and reduce cost, many giant logistics companies have been dedicated to developing various drones to deliver light and small parcels during the past decade. However, due to the limitation of payload, the battery capacity is constrained, which prevents drones from long-distance flights. Practitioners have tried the drone-vehicle collaboration method, but this still requires human labour to participate. In this paper, we present a framework where drones autonomously conduct long-distance delivery with the assistance of drone stations. It is worth pointing out that such a framework is not to replace the ground delivery method but to serve as an alternative to the ground counterpart for small and light parcels. A particular focus is on the flight planning from the depot to a destination, which includes not only a sequence of drone stations to stop at but also the corresponding rest time to recharge the battery. Several typical scenarios about battery recharging are discussed, and a dynamic version of Dijkstra’s algorithm is presented to deal with the challenging case where drone station resources are limited. The presented approach is able to find out the optimal flight plan quickly.

This paper considers using unmanned aerial vehicles (UAVs) to survey important sites across a city. When the sites are relatively far from the UAVs’ depot, the UAVs may not be able to reach many of the sites. Suppose that a UAV can take public transportation vehicles (PTVs) like a passenger. Then, it may reach a site that is unreachable by flying only. Based on this UAV-PTV scheme, we investigate a task-UAV assignment problem, which assigns a set of surveillance tasks to UAVs. We formulate a mixed-integer linear programming (MILP) problem that minimizes the overall energy consumption of UAVs, subject to that every site is surveyed by a certain number of UAVs during a given time window, and all UAVs successfully return to the depot. Considering that this problem is NP-hard, we present two sub-optimal solutions. The first solution orders the surveillance tasks according to the starting times of their time windows. Then, starting from the earliest one, it assigns the tasks one by one to UAVs. The second solution breaks the tasks into small non-overlapping groups. It then assigns tasks to UAVs group by group. The former solution quickly addresses the assignment problem, but it lacks the overall management of UAV resources. The latter improves this by assigning a group of tasks simultaneously, and it can control the computation complexity by limiting the group size. The comparison with the brute force method shows that the proposed solutions can achieve competitive performance in a reasonable time. Note to Practitioners—Unmanned aerial vehicles (UAVs) have been widely used in surveillance missions. However, one challenge practitioners often meet is the limited flight duration. Commercial UAVs are in general powered by the onboard battery. Due to the restriction of payload, the battery capacity is constrained, which limits the UAVs’ operation time. In this paper, we present the approach exploiting public transportation vehicles (PTVs). In our design, a UAV can take a public transportation vehicles such as buses, trams and trains on the roof and transfer between vehicles when necessary. With this UAV-PTV collaboration scheme, we consider how to efficiently assign surveillance tasks to UAVs. Due to the NP-hardness of the considered problem, two suboptimal algorithms are presented.

This paper addresses a trajectory planning problem for a team of UAVs following several ground vehicles on uneven terrain for video surveillance. A model predictive control-based multi-UAV path planning algorithm is designed. A theoretical justification of the path planning algorithm is provided. Extensive simulation studies demonstrate the performance of the proposed method.

Using drones to carry out commercial parcel delivery can significantly promote the transformation and upgrading of the logistics industry thanks to the saving of human labor source, which is becoming a new component of intelligent transportation systems. However, the flight distance of drones is often constrained due to the limited battery capacity. To address this challenge, this paper designs a multi-drones-assisted commercial parcel delivery system, which supports long-distance delivery by a generalized service network (GSN). Each node of the GSN is equipped with charging piles to provide a charging service for drones. Given the limited number of charging piles at each node and the limited battery capacity of a drone, to ensure the efficient operation of the system, the flight planning problem of drones is converted into a large-scale optimization problem by a priority-based encoding mechanism. To solve this problem, an enhanced backtracking search algorithm (EBSA) is reported, which is inspired by the characteristics of the considered flight planning problem and the weak ability of the backtracking search algorithm to escape from a local optimum. The core components of EBSA are the designed comprehensive learning mechanism and local escape operator. Experimental results prove the validity of the improved strategies and the excellent performance of EBSA on the considered flight planning problem.

The information of the shaft torque and the resistance torque is crucial to develop advanced control and fault diagnosis/detection schemes for electrified powertrain systems. However, reliable physical sensors for torque measurement are not affordable for commercial vehicle applications. This article investigates the simultaneous estimation problem of the state dynamics and the resistance torque for integrated motor-transmission (IMT) systems of electric vehicles. To this end, the IMT system is first reformulated as a nonlinear switched model, where the resistance torque is considered as an unknown input (UI). This modeling reformulation allows taking into account not only the nonlinear nature of IMT dynamics but especially also the intrinsic discontinuity of the gear-shifting process. Then, we propose a nonlinear switched observer (NSO) structure to simultaneously estimate the nonlinear IMT dynamics, thus the shaft torque, and the unknown resistance torque. The observer design does not require any a priori information on the unknown resistance torque as for the classical proportional-integral observer design, nor the well-known matching condition for UI decoupling techniques. Using the Lyapunov stability theory, we derive sufficient conditions, expressed in terms of linear matrix inequality (LMI) constraints, to design an NSO with a guaranteed$\ell _{\infty }$performance to mitigate the negative effect of sensor noises and disturbances. In particular, we propose to incorporate LMI-based bumps limitation conditions in the optimization-based observer design to reduce the impacts of expressive discontinuities at switching instants. Comparative studies are performed between the related estimation methods to show the practical effectiveness of the proposed solution.

A sensor-equipped Unmanned Aerial Vehicle (UAV) can be used to gather surface information of a structure, performing an autonomous inspection. It can significantly improve the efficiency of the visual inspection tasks and reduce the operating cost and the human risks involved in the tasks. A complete inspection coverage path generating method comprising two sets of viewpoints is presented in this research. The first set of viewpoints, revolving viewpoints, is generated based on the geometry of the inspection target and revolving around the target. The second set of viewpoints, gap-filling viewpoints, is generated to compensate for the insufficiency of the revolving viewpoints, filling all the unseen surface patches and guaranteeing full coverage. The system's scalability was proven by the planning outcomes for two different structures on different scales, which met both requirements of close-up inspection and photogrammetry.

This article studies the quality of coverage of deploying flying base stations mounted on unmanned aerial vehicles (UAV-BSs) after disasters or during some occasional events. In particular, we focus on the problem of minimizing the average UAV-user distance, while maintaining connectivity between the UAV-BSs and some nearby stationary base stations (SBSs). The UAV-BSs can be deployed at different altitudes, and their transmission powers may also be different. We first propose a decentralized deployment algorithm for a Line-of-Sight (LoS) scenario. This algorithm allows UAV-BSs to determine their movements based on only local information. So, it is applicable in a large scale. The local optimality and the convergence of the algorithm are proved. Moreover, we discuss how to use the algorithm in Non-LoS (NLoS) scenarios. Specifically, during its movement, each UAV-BS needs to verify the connectivity requirement as well as if a future movement will lose any already covered users. This extension guarantees that the average UAV-user distance keeps reducing during the movements of UAV-BSs. Computer simulations and comparisons with a benchmark method confirm the effectiveness of the proposed algorithms in terms of the quality of coverage.

This article considers the use of an unmanned aerial vehicle (UAV) for covert video surveillance of a mobile target on the ground and presents a new online UAV trajectory planning technique with a balanced consideration of the energy efficiency, covertness, and aeronautic maneuverability of the UAV. Specifically, a new metric is designed to quantify the covertness of the UAV, based on which a multiobjective UAV trajectory planning problem is formulated to maximize the disguising performance and minimize the trajectory length of the UAV. A forward dynamic programming method is put forth to solve the problem online and plan the trajectory for the foreseeable future. In addition, the kinematic model of the UAV is considered in the planning process so that it can be tracked without any later adjustment. Extensive computer simulations are conducted to demonstrate the effectiveness of the proposed technique.Note to Practitioners—The “Follow Me” flight mode is available in many unmanned aerial vehicle (UAV) products, and this technique enables a UAV to automatically follow a target. However, this flight mode may make the UAV noticeable to the target and compromise the video surveillance missions of the UAV. Inspired by some security surveillance applications where UAV surveillance is conducted so that a target would not take actions to avoid being monitored, we propose an efficient method to construct the trajectory for the UAV. The proposed method considers the visual covertness and the battery capacity limitation of the UAV, and it can produce a trajectory online for the UAV. The proposed method and scenario can potentially extend the “Follow Me” flight mode and generate new applications and market for UAVs.

Unmanned aerial vehicles (UAVs) are increasingly applied to surveillance tasks, thanks to their excellent mobility and flexibility. Different from existing works using UAVs for video surveillance, this paper employs a UAV team to carry out collaborative radio surveillance on ground moving nodes and disguise the purpose of surveillance. We consider two aspects of disguise. The first is that the UAVs do not communicate with each other (or the ground nodes can notice), and each UAV plans its trajectory in a decentralized way. The other aspect of disguise is that the UAVs avoid being noticed by the nodes for which a metric quantifying the disguising performance is adopted. We present a new decentralized method for the online trajectory planning of the UAVs, which maximizes the disguising metric while maintaining uninterrupted surveillance and avoiding UAV collisions. Based on the model predictive control (MPC) technique, our method allows each UAV to separately estimate the locations of the UAVs and the ground nodes, and decide its trajectory accordingly. The impact of potential estimation errors is mitigated by incorporating the error bounds into the online trajectory planning, hence achieving a robust control of the trajectories. Computer-based simulation results demonstrate that the developed strategy ensures the surveillance requirement without losing disguising performance, and outperforms existing alternatives. Note to Practitioners—The paper is motivated by the covertness requirement in the radio surveillance (also called eavesdropping) by UAVs. In some situations, the UAV user (such as the police department) wishes to disguise the surveillance intention from the targets, and the trajectories of UAVs play a significant role in the disguising. However, the typical UAV trajectories such as standoff tracking and orbiting can easily be noticed by the targets. Considering this gap, we focus on how to plan the UAVs’ trajectories so that they are less noticeable while conducting effective eavesdropping. We formulate a path planning problem aiming at maximizing a disguising metric, which measures the magnitude of the relative position change between a UAV and a target. A decentralized method is proposed for the online trajectory planning of the UAVs based on MPC, and its robust version is also presented to account for the uncertainty in the estimation and prediction of the nodes’ states.

This paper investigates a human-machine cooperative trajectory planning and tracking control approach for automated vehicles. The proposed method is developed based on a novel algorithm of cooperative human-machine rapidly-exploring random (HM-RRT) for path planning, together with the risk assessment of driver behavior. First, the driver’s behaviour is assessed according to the information of the predicted vehicle trajectory, the identified safe driving area and the driving risks evaluated in both lateral and longitudinal directions. Based on the driver’s expected driving task, when driving risks are identified by real-time assessment, then the human-machine cooperation is activated during trajectory planning. By HM-RRT, the newly developed safety assurance mechanism for path planning, the cooperative trajectory is then generated, which incorporates the driver’s desire and actions and automation’s corrective actions, to ensure the safety, stability and smoothness of the human-vehicle system. The simulation and experimental results show that the proposed HM-RRT algorithm can effectively improve the convergence rate and reduce the computation load, comparing to the conventional method. Beyond this, the proposed human-machine cooperation approach is able to simultaneously ensure the safety, stability and smoothness of the vehicle and largely reduce human-machine conflicts in real-time applications, demonstrating its feasibility and effectiveness.

To enable the drone delivery service in a remote area, this paper considers the approach of deploying charging stations and collaborating with public transportation vehicles. From the warehouse which is far from a customer, a drone takes some public transportation vehicles to reach some position close to the remote area. When the customer is unreachable from the position where the drone leaves the public transportation vehicle, the drone swaps the battery at a charging station. The focus of this paper is the deployment of charging stations. We propose a new model to characterize the delivery time for customers. We formulate the optimal deployment problem to minimize the average delivery time for the customers, which is a reflection of customer satisfaction. We then propose a sub-optimal algorithm that relocates the charging stations in sequence, which ensures that any movement of a charging station leads to a decrease in the average flight distance. The comparison with a baseline method confirms that the proposed model can more accurately estimate the flight distance of a customer than the commonly used model, and the proposed algorithm can relocate the charging stations achieving lower flight distance.

With the rapid increase of vehicles in recent years, traffic surveillance becomes a crucial issue of traffic management. Since the traditional static sensor-based surveillance system can only passively monitor traffic, this paper considers the usage of unmanned aerial vehicles (UAVs), which can proactively conduct traffic surveillance thanks to the excellent mobility of UAVs. Specifically, we consider the navigation problem of a network of UAVs to effectively monitor a group of ground targets which move along a curvy road. A surveillance optimization problem is stated, and a distributed navigation algorithm for the UAV network is developed. It is proved that the proposed algorithm is locally optimal. Simulations confirm the effectiveness of the proposed navigation algorithm.

Drones are a promising tool for parcel delivery, since they are cost-efficient and environmentally friendly. However, owing to the limited capacity of the on-board battery, their flight range is constrained. Thus, they cannot deliver some parcels if the customers are too far from the depot. To address this issue, this article proposes a novel method, in which a parcel delivery drone can “take” a public transportation vehicle and travel on its roof. The problem under consideration is how to make use of the public transportation network to route the drone between the depot and the customer. Compared to the currently available methods that use drones, the most important merit of this approach is a significant expansion of the delivery area. We construct a multimodal network consisting of public transportation vehicles' trips and drone flights. Because of the complexity of this multimodal network, we convert it to a simple network with a set of simple procedures. In the extended network, we formulate the shortest drone path problem that minimizes the return instant to the depot, subject to that the drone energy consumption on this path is no greater than the initial energy. We present a Dijkstra-based method to find the shortest drone path. Moreover, we extend the proposed method to the case with uncertainty, because the public transportation vehicles cannot exactly follow their timetables in practice. Simulation results are presented to demonstrate how the method works.

Drones have been regarded as a promising means for future delivery industry by many logistics companies. Several drone-based delivery systems have been proposed but they generally have a drawback in delivering customers locating far from warehouses. This paper proposes an alternative system based on a public transportation network. This system has the merit of enlarging the delivery range. As the public transportation network is actually a stochastic time-dependent network, we focus on the reliable drone path planning problem (RDPP). We present a stochastic model to characterize the path traversal time and develop a label setting algorithm to construct the reliable drone path. Furthermore, we consider the limited battery lifetime of the drone to determine whether a path is feasible, and we account this as a constraint in the optimization model. To accommodate the feasibility, the developed label setting algorithm is extended by adding a simple operation. The complexity of the developed algorithm is analyzed and how it works is demonstrated via a case study.

This article studies deploying autonomous drones to provide Internet service to affected users in disaster areas. Specifically, the problem of minimizing the average drone-user distance is considered. Unlike some existing location-based approaches, a range-based reactive drone deployment algorithm is proposed. Instead of assuming that the users' locations are known, the proposed algorithm only requires the drones to measure the received signal strength and to share such information with other nearby drones. It is decentralized and easily implementable in real time. The algorithm's convergence is proved and its performance is validated by simulations and comparisons with a benchmark scheme.

This paper considers using UAVs to carry out an active and collaborative radio surveillance on a group of ground mobile nodes while disguising the surveillance intention. The UAVs try to prevent being visually noticed by the nodes, and a new measure to quantify the disguising performance is proposed. We formulate a new trajectory optimization problem to maximize the new disguising metric subject to an uninterrupted surveillance requirement and the collision avoidance and the aeronautic maneuverability of the UAVs. A model predictive control (MPC) based scheme is developed. Computer simulations and comparisons with a random trajectory construction method show that the proposed method guarantees the surveillance performance without the loss of disguising performance.

Shark attacks can make beach tourists anxious about sharing the ocean with apex predators. Although the raw number of shark attacks is deficient, the absolute terror caused by sharks is genuine. This article introduces a novel method named as the “drone shark shield system,” which uses communicating autonomous drones to intervene and prevent shark attacks for protecting swimmers and surfers. We detail the design of the drone shark shield system and the strategy for repelling sharks through multiple intersections. A shark interception algorithm is developed to guide drones to predicted intersection points for deterring sharks. Computer simulations are conducted to illustrate our method.

This paper focuses on the application of surveillance and monitoring using unmanned aerial vehicles (UAVs). A novel coverage model is proposed to characterize the quality of coverage (QoC) of a target by a UAV. On the basis of this model, a reactive collision free three-dimensional deployment algorithm is proposed, with the goal of maximizing the overall QoC of targets by a network of UAVs. The algorithm consists of two navigation laws for the horizontal movement and the vertical movement, both of which are easily implementable in real time. The convergence of the algorithm is proved, and the computational complexity is analyzed. Computer simulations are conducted to demonstrate the performance of the proposed method.

A parcel delivery system with a unmanned aerial vehicle (UAV) and a public train is presented, where the train moves naturally as it is and the UAV can depart the train to deliver parcels. The UAV can travel with the train and replace its battery on the roof. An optimization problem is formulated to minimize the total delivery time and two algorithms are proposed. The exact algorithm gives the optimal schedule, but it is not scalable. The developed suboptimal algorithm is computationally efficient and achieves close performance to that of the exact algorithm. Realistic simulations are conducted to evaluate the proposed algorithms and they are compared with existing schemes.

Though drones have become a promising tool for parcel delivery, due to the limited capacity of the on-board battery, their flight range is constrained. To enlarge the coverage range, the paper proposes a novel method, in which a parcel delivery drone can "take" a public transportation vehicle and travel on its roof. We investigate how to make use of the public transportation network to route the drone between the depot and a customer. Considering the complexity of the public transportation network, its randomness and time-dependency, instead of off-line planning a global optimal path, an adaptive algorithm is developed. Simulation results are presented to demonstrate how the proposed approach works.

A navigation algorithm for source seeking in a sensor network environment is presented in this paper. The solution consists of a gradient-free approach and maximum likelihood topology maps of sensor networks. The robot is navigated using an angular velocity limited by maximum and minimum constants, and by sensor measurements gathered by sensors that are close to robot's current location. The location of the robot is calculated using sensor topology coordinates, which is an alternative to the physical coordinate system and does not depend on physical distance measurement techniques such as received signal strength. However, actual physical distances are hidden in topology maps due to nonlinear distortions compared to physical distance between nodes. Thus, the proposed control law does not depend on any distance-based information. The performance of the algorithm is evaluated using computer simulations and experiments with a real mobile robot.

We focus on the problem of deploying unmanned aerial vehicles to service mobile users in a cellular network, with the aim of maximizing coverage and reducing interference effects. An optimization model that is distributed in nature is proposed and a maximizing algorithm is developed to find a locally optimal solution. The performance of this distributed algorithm is shown to be superior in quality and solution time to a standard greedy algorithm. Testing on a simulation of a practical scenario is performed to demonstrate the application of the method to real scenarios as well as to illustrate the tradeoff between maximizing coverage and minimizing interference.

This paper studies the problem of using path constrained mobile sinks (MSs) to collect data in Wireless Sensor Networks (WSNs). Accounting the feature of nonuniform node distribution, the proposed protocol aims at balancing the energy consumption, including energy expenditure to transmit data packet and network overhead, to make the network operate as long as possible with all nodes alive. We propose an energy-aware unequal clustering algorithm and an energy-aware routing algorithm. Through simulations, we confirm that the proposed approach achieves longer network lifetime against alternatives.

This paper considers the data delivery delay problem in wireless sensor networks. The delivery delay is a significant measure when the data freshness is the first concern of users. The goal of this paper is to route delay-sensitive data to mobile nodes (M nodes) within an allowed latency. The data collection system is composed of a set of M nodes amounted on buses, a set of sensor nodes to detect the interested phenomenon and a set of special nodes deployed at bus stops to assist data routing. An optimization-based approach called improved-unusual message delivery path construction (I-UMDPC) is proposed. Considering the actual features of bus operation, two aspects of uncertainties are accounted in our approach: 1) the bus arrival time and 2) the stop duration. Extensive simulations as well as practical experiments on our testbed demonstrate that I-UMDPC is able to route delay-sensitive data reliably and efficiently and performs better than existing work.