An industrial case study of Unmanned Aerial System (UAS) operation and communications for integrated satellite-terrestrial networks in remote regions is considered. The objective is to evaluate and optimize the Quality of Service (QoS) of communication networks that combine satellite backhaul and ground-based transmission infrastructure for UAS operations. To address this challenge, this paper proposes a new algorithm for antenna tilt optimization procedure aiming to enhance terrestrial coverage, and maximise average Received Signal Strength Indicator (RSSI) along predefined UAS paths using terrain-aware ray-tracing models. A preliminary analysis of the satellite link is performed using simulation-based model of phased array terminal, assessing its suitability for Beyond Visual Line of Sight (BVLOS) operations through latency and RSSI profiling under variable link conditions. In addition, the study quantifies the QoS of the terrestrial network by analyzing RSSI, Signal-to-Interference-plus-Noise Ratio (SINR), latency, and throughput across UAS routes between key islands. The findings highlight the effectiveness of hybrid satellite-terrestrial architectures in extending coverage and reliability for critical UAS operations in geographically challenging environments. This work informs future network planning strategies for remote UAS deployments.

As vehicle autonomy increases, human operators become more susceptible to distractions and a loss of situational awareness (SA) due to cognitive limitations. Rapidly enhancing human SA in hazardous situations is, therefore, critical for timely hazard perception and collision avoidance, particularly in human-vehicle teaming contexts that demand fast, accurate hazard reasoning. This study evaluates the efficiency of a low-cost vibrotactile interface for enhancing hazard SA of human operators when teaming with heterogeneous autonomous vehicles, including both ground and aerial autonomous vehicles. To do so, we evaluate the effectiveness of a vibrotactile interface in challenging time-critical scenarios considering adversarial attacks to better understand the cognitive constraints faced by human operators. Our quantitative analysis, based on the data collected from 39 participants, demonstrates that: first, haptic cues can significantly enhance human hazard SA across various metrics for the ground and aerial scenarios; second, perception of aerial attacks in a 3-D environment is more challenging than ground risk perception.

Aerial search and rescue (SAR) rotorcrafts currently need multiple specialist human operators, increasing cost and the risk of downtime due to crew unavailability and mental stress. Autonomy can aid fewer operators performing multiple tasks, but the human operator must maintain situation awareness (SA) of crucial autonomous decisions. A key challenge is the cognitive stress on a multi-tasking human-in-the-loop (HITL) due to the AI agent making decisions without human understanding. Explainable AI (XAI) has often been proposed as a way to explain autonomy decisions, but current XAI solutions doesn’t adapt to real-time human factors in high stress and high stakes situations. Here, we allow an AI agent to perform autonomous rotorcraft navigation, whilst the HITL operator has to perform two simultaneous tasks: (i) search for a target on the ground by toggling an onboard camera, and (ii) maintain SA of the autonomous navigation task through our novel XAI interface. Our novel XAI approach leverages on dimensionality reduction techniques to visualize the reinforcement learning (RL) navigation’s internal states, highlighting patterns in its decision-making process through intuitive interactive clustering on saliency maps. To ensure convergence on performance, we design a two-way interface that allows the human to interpret AI decisions and then give feedback via a Large Language Model to modify the autonomous navigation. Testing demonstrates increased task performance (+43%), while experiencing substantial human reductions in physical demand (-53%), time pressure (-30%), effort (-23%), and frustration (-26%), but at the cost of slightly increased mental demand (+12%).

Human–autonomy teaming in the Low Altitude Economy (LAE) requires operators to manage both ground and aerial autonomous agents under time pressure, spatial uncertainty, and cognitive load. This study investigates how visual and haptic feedback affect operator situational awareness (SA) in simulated collision avoidance tasks involving cars and drones. A high-fidelity virtual environment was built using Unreal Engine 4 and AirSim, with haptic cues delivered through a wearable bHaptics vest. Twenty-two participants performed within-subject trials across visual-only and visual–haptic conditions. Results showed that haptic feedback significantly enhanced SA, particularly in dimensions related to information acquisition and spare mental capacity. Improvements were more consistent in car-based tasks, while drone scenarios exhibited greater inter-individual variability. These findings demonstrate the potential of multimodal interfaces to support cognitive performance and reduce platform-related disparities in operator SA. This work provides empirical evidence for designing adaptive, perception-aware interfaces in safety-critical human–autonomy teaming systems.

Wildfires pose major challenges to natural ecosystems and smart living due to its destructive nature. Unmanned Aerial vehicles (UAVs) or drones have been used to support fire fighter in identifying vulnerable areas and the detection of people that need assistance. Most of the current solutions use path planning approaches under simple and deterministic environments that fail to model the dynamic nature of fire. Furthermore, the localisation of victims is assumed to be known which is unrealistic in disaster-like scenarios. To alleviate this issue, this paper proposes a novel search and rescue (SAR) application using drones. A multi-agent deep Q-network is designed to train a fleet of UAVs to search for people and evacuate them in a wildfire scenario. A realistic forest environment is designed that considers variations in vegetation and fire propagation. This helps to challenge RL algorithms to be more adaptive to changes in the environment due to the evolution of fire. Extensive simulation experiments are conducted to show the advantages and effectiveness of the proposed approach.

Reconfigurable Intelligent Surface (RIS) is envisioned to revolutionize 6G wireless networks, particularly in complex environments like smart airports, by customizing analog beamforming with desired direction and magnitude. Through precise configuration refinement, the intelligent surface intends to achieve equivalent Quality of Service (QoS) with fewer antennas, thereby enhancing coverage and capacity in high-demand areas of airports. However, existing model-free algorithms struggle to obtain a stable policy gradient of intelligent surface configuration. Moreover, centralized channel estimation is inefficient to massive communication and more vulnerable to eavesdroppers. To address these challenges, a robust Proximal Policy Optimization-Huber (PPO-Huber) algorithm was developed to improve the efficiency and robustness of digital connectivity within airports. Concerning the privacy of channel models in massive communication, we proposed an optimal Differential Private Federated Learning (DPFL) with noise reduction, ensuring secure access to channel information. Comprehensive convergence analyses are conducted for each proposed algorithm to facilitate hyperparameter tuning and suggest potential research directions. Experimental results demonstrate that our algorithms not only offer flexible deployment of intelligent surface without accurate channel knowledge, but also substantially breaking the communication-privacy-utility trilemma in massive RIS-aided 6G wireless networks of smart airports.

This paper proposes a deep reinforcement learning-based neighbor selection algorithm designed to enhance the Augmented Cucker-Smale flocking control model for non-holonomic agents. By retaining the control layer, we introduce an additional neighbor selection layer that precedes the control. This layer employs deep reinforcement learning to train the system for faster flock convergence. The actor network within this layer generates probability distributions that determine the inclusion of each neighbor in the control layer. The numerical simulations confirm that the algorithm significantly speeds up flock formation by optimally selecting neighbors for the controller.

This study seeks towards a better understanding of multi-vehicle routing problems (VRPs) under restricted observability. Unlike most prior research that assumes full knowledge of tasks and vehicles, this paper addresses VRPs where each vehicle’s observation is confined to the k-nearest neighbourhood. Vehicles make decisions based on localized policies in a decentralized manner. We theoretically demonstrate that for the imitation policy, the upper bound of the optimality gap diminishes as the neighbourhood range expands. Subsequently, we employed a multi-agent cross-observability policy optimization (MACOPO) algorithm to solve the VRPs with restricted observability. The algorithm optimizes a cross-entropy term by leveraging a fully observable expert to guide the training. Empirical results supported both the theoretical findings and the effectiveness of the multi-agent learning algorithm.

Time-series modelling (TSM) is a critical task for intelligent vehicles (IVs), covering areas like fault detection, health monitoring, and inference of road user intentions. In this study, we present a novel TSM approach for enhancing the accuracy of multi-variate signal forecasting in intelligent vehicles. Our method leverages advanced Transformer networks within a relativistic generative adversarial network (RGAN) training framework. The RGAN training framework efficiently improves the accuracy of vehicle states forecasting for IV, demonstrating effective learning of long-time dependencies for more accurate predictions over extended sequences. Additionally, we introduce a high-dimensional extension (HDE) built-in block for the time-series Transformer to explore the impact of higher-dimensional features on representing long-term sequences. The experimental data is collected from a real-world electric vehicle testing bed. We evaluate the proposed RGANFormer framework and the HDE block on two popular time-series models, namely, Autoformer and FiLM. The results demonstrate that the RGANFormer, along with the built-in HDE block, significantly enhances long-term sequential forecasting accuracy for both multivariate and univariate tasks.

With the increasing deployment of IoT and Industry 4.0, the federated learning system was presented to preserve the privacy between the third-party IoT systems and the security operation center in smart airports. Nonetheless, the extremely skewed distribution of cyber threats increases the complexity of intrusion detection system (IDS) in smart airports, while privacy preservation limits the utility of IDS in the process of server model update. In this article, we have devised a knowledge distillation (KD)-based Convolutional Neural Network and Gated Recurrent Unit (CNN-GRU) model to improve the accuracy of multiple intrusion detection. In addition, the tradeoff between privacy and accuracy is achieved by denoising the adaptive parameter update mechanism to upgrade the optimizer of Differentially-Private (DP) Federated IDS. The results indicate high effectiveness and robustness of DP Federated KD-based IDS for third-party IoT systems of a smart airport.

The fifth generation (5G) technology is expected to play a key role in the development of urban air mobility (UAM). 5G networks have the potential to provide the high-speed, low-latency connectivity needed for UAM vehicles to communicate with each other, with ground stations, and with air traffic management systems. This connectivity is crucial for ensuring safe and efficient operation of UAM vehicles in crowded urban environments. This paper investigate the fundamental requirements for UAM connectivity and provides performance analysis for communication data link between ground station and UAM flying platform in proximity using 3rd Generation Partnership Project (3GPP) standard concerning atmosphere, rain and Doppler effects. Furthermore, the Quality-of-Service (QoS) performance in terms of latency and throughput have been discussed to complete an overview of the 5G data link communications analysis. To conclude, the integration of 5G technology with UAM has the potential to revolutionize the way people and goods are transported within urban areas, enabling faster, more efficient, and safer transportation.

Abstract Increased drone proliferation in civilian and professional settings has created new threat vectors for airports and national infrastructures. The economic damage for a single major airport from drone incursions is estimated to be millions per day. Due to the lack of balanced representation in drone data, training accurate deep learning drone detection algorithms under scarce data is an open challenge. Existing methods largely rely on collecting diverse and comprehensive experimental drone footage data, artificially induced data augmentation, transfer and meta-learning, as well as physics-informed learning. However, these methods cannot guarantee capturing diverse drone designs and fully understanding the deep feature space of drones. Here, we show how understanding the general distribution of the drone data via a generative adversarial network (GAN), and explaining the under-learned data features using topological data analysis (TDA) can allow us to acquire under-represented data to achieve rapid and more accurate learning. We demonstrate our results on a drone image dataset, which contains both real drone images as well as simulated images from computer-aided design. When compared to random, tag-informed and expert-informed data collections (discriminator accuracy of 94.67%, 94.53% and 91.07%, respectively, after 200 epochs), our proposed GAN-TDA-informed data collection method offers a significant 4% improvement (99.42% after 200 epochs). We believe that this approach of exploiting general data distribution knowledge from neural networks can be applied to a wide range of scarce data open challenges.

In this paper, a novel integrated real-time trajectory planning and tracking control framework capable of dealing with autonomous ground vehicle (AGV) parking maneuver problems is presented. In the motion planning component, a newly-proposed idea of utilizing deep neural networks (DNNs) for approximating optimal parking trajectories is further extended by taking advantages of a recurrent network structure. The main aim is to fully exploit the inherent relationships between different vehicle states in the training process. Furthermore, two transfer learning strategies are applied such that the developed motion planner can be adapted to suit various AGVs. In order to follow the planned maneuver trajectory, an adaptive learning tracking control algorithm is designed and served as the motion controller. By adapting the network parameters, the stability of the proposed control scheme, along with the convergence of tracking errors, can be theoretically guaranteed. In order to validate the effectiveness and emphasize key features of our proposal, a number of experimental studies and comparative analysis were executed. The obtained results reveal that the proposed strategy can enable the AGV to fulfill the parking mission with enhanced motion planning and control performance.Note to Practitioners—This article was motivated by the problem of optimal automatic parking planning and tracking control for autonomous ground vehicles (AGVs) maneuvering in a restricted environment (e.g., constrained parking regions). A number of challenges may arise when dealing with this problem (e.g., the model uncertainties involved in the vehicle dynamics, system variable limits, and the presence of external disturbances). Existing approaches to address such a problem usually exploit the merit of optimization-based planning/control techniques such as model predictive control and dynamic programming in order for an optimal solution. However, two practical issues may require further considerations: 1). The nonlinear (re)optimization process tends to consume a large amount of computing power and it might not be affordable in real-time; 2). Existing motion planning and control algorithms might not be easily adapted to suit various types of AGVs. To overcome the aforementioned issues, we present an idea of utilizing the recurrent deep neural network (RDNN) for planning optimal parking maneuver trajectories and an adaptive learning NN-based (ALNN) control scheme for robust trajectory tracking. In addition, by introducing two transfer learning strategies, the proposed RDNN motion planner can be adapted to suit different AGVs. In our follow-up research, we will explore the possibility of extending the developed methodology for large-scale AGV parking systems collaboratively operating in a more complex cluttered environment.

This article studies the problem of trajectory optimization for autonomous ground vehicles with the consideration of irregularly placed on-road obstacles and multiple maneuver phases. By introducing a series of event sequences, a new multiphase constrained optimal control formulation is constructed to describe the automatic overtaking process. Although existing trajectory optimization techniques can be applied to address the constructed problem, they may suffer from poor or premature convergence issues due to the complexity of the mission formulation. Thus, to offer an effective alternative, a novel desensitized trajectory optimization method is designed and implemented to explore the optimal overtaking maneuver for the AGVs. The proposed method applies a double layer structure, where an enhanced intelligent optimization method is used in the outer layer such that the main inner optimization routine can be boosted by starting at a better reference solution. The algorithm convergence as well as the solution optimality conditions are theoretically analyzed. Numerical results are provided to illustrate the validity of the established formulation. Comparative case studies were executed to demonstrate the quality of the obtained solution and the enhanced performance of the proposed trajectory optimization method.

The satellite-terrestrial networks (STN) utilize the spacious coverage and low transmission latency of the Low Earth Orbit (LEO) constellation to transfer requested content for subscribers especially in remote areas. With the development of storage and computing capacity of satellite onboard equipment, it is considered promising to leverage in-network caching technology on STN to improve content distribution efficiency. However, traditional caching and distribution schemes are not suitable in STN, considering dynamic satellite propagation links and time-varying topology. More specifically, the unevenness of user distribution heightens difficulties for assurance of user quality of experience. To address these problems, we first propose a density-based network division algorithm. The STN is divided into a series of blocks with different sizes to amortize the data delivery costs. To deploy the caching satellites, we analyze the link connectivity and propose an approximate minimum coverage vertex set algorithm. Then, a novel cache node selection algorithm is designed for optimal subscriber matching. On the basis of time-varying network model, the STN cache content updating mechanism is derived to enable a stable and sustainable quality of user experience. The simulation results demonstrate that the proposed user-oriented STN content distribution scheme can obviously reduce the average propagation delay and network load under different network conditions and has better stability and self-adaptability under continuous time variation.

A passive fault tolerant control scheme is proposed for the full reentry trajectory tracking of a hypersonic vehicle in the presence of modeling uncertainties, external disturbances, and actuator faults. To achieve this goal, the attitude error dynamics with relative degree two is formulated first by ignoring the nonlinearities induced by the translational motions. Then, a multivariable twisting controller is developed as a benchmark to ensure the precise tracking task. Theoretical analysis with the Lyapunov method proves that the attitude tracking error and its first-order derivative can simultaneously converge to the origin exponentially. To depend less on the model knowledge and reduce the system uncertainties, an incremental twisting fault tolerant controller is derived based on the incremental nonlinear dynamic inversion control and the predesigned twisting controller. In this article, it is shown that not only the benefits of both incremental control and twisting control are inherited, but also their side effects are reduced. Notably, the proposed controller is user friendly in that only fixed gains and partial model knowledge are required. Numerical simulations in various cases and comparison studies are conducted to verify the effectiveness of the proposed method.

This article focuses on the design, test, and validation of a deep neural network (DNN)-based control scheme capable of predicting optimal motion commands for autonomous ground vehicles (AGVs) during the parking maneuver process. The proposed design utilizes a multilayer structure. In the first layer, a desensitized trajectory optimization method is iteratively performed to establish a set of time-optimal parking trajectories with the consideration of noise-perturbed initial configurations. Subsequently, by using the preplanned optimal parking trajectory data set, several DNNs are trained in order to learn the functional relationship between the system state-control actions in the second layer. To obtain further improvements regarding the DNN performances, a simple yet effective data aggregation approach is designed and applied. These trained DNNs are then utilized as the motion controllers to generate feedback actions in real time. Numerical results were executed to demonstrate the effectiveness and the real-time applicability of using the proposed control scheme to plan and steer the AGV parking maneuver. Experimental results were also provided to justify the algorithm performance in real-world implementations.

The rapid technological advances of cellular technologies will revolutionize network automation in industrial internet of things (IIoT). In this paper, we investigate the two-timescale resource allocation problem in IIoT networks with hybrid energy supply, where temporal variations of energy harvesting (EH), electricity price, channel state, and data arrival exhibit different granularity. The formulated problem consists of energy management at a large timescale, as well as rate control, channel selection, and power allocation at a small timescale. To address this challenge, we develop an online solution to guarantee bounded performance deviation with only causal information. Specifically, Lyapunov optimization is leveraged to transform the long-term stochastic optimization problem into a series of short-term deterministic optimization problems. Then, a low-complexity rate control algorithm is developed based on alternating direction method of multipliers (ADMM), which accelerates the convergence speed via the decomposition-coordination approach. Next, the joint channel selection and power allocation problem is transformed into a one-to-many matching problem, and solved by the proposed price-based matching with quota restriction. Finally, the proposed algorithm is verified through simulations under various system configurations.

Current state-of-the-art neural network explanation methods (e.g. Saliency maps, DeepLIFT, LIME, etc.) focus more on the direct relationship between NN outputs and inputs rather than the NN structure and operations itself, hence there still exists uncertainty over the exact role played by neurons. In this paper, we propose a novel neural network structure with Kolmogorov-Arnold Superposition Theorem based topology and Gaussian Processes based flexible activation function to achieve partial explainability of the neuron inner reasoning. The model feasibility is verified in a case study on binary classification of the banknotes.

Constrained autonomous vehicle overtaking trajectories are usually difficult to generate due to certain practical requirements and complex environmental limitations. This problem becomes more challenging when multiple contradicting objectives are required to be optimized and the on-road objects to be overtaken are irregularly placed. In this article, a novel swarm intelligence-based algorithm is proposed for producing the multiobjective optimal overtaking trajectory of autonomous ground vehicles. The proposed method solves a multiobjective optimal control model in order to optimize the maneuver time duration, the trajectory smoothness, and the vehicle visibility, while taking into account different types of mission-dependent constraints. However, one problem that could have an impact on the optimization process is the selection of algorithm control parameters. To desensitize the negative influence, a novel fuzzy adaptive strategy is proposed and embedded in the algorithm framework. This allows the optimization process to dynamically balance the local exploitation and global exploration, thereby exploring the tradeoff between objectives more effectively. The performance of using the designed fuzzy adaptive multiobjective method is analyzed and validated by executing a number of simulation studies. The results confirm the effectiveness of applying the proposed algorithm to produce multiobjective optimal overtaking trajectories for autonomous ground vehicles. Moreover, the comparison to other state-of-the-art multiobjective optimization schemes shows that the designed strategy tends to be more capable in terms of producing a set of widespread and high-quality Pareto-optimal solutions.

Quadrature spatial modulation (QSM) is recently proposed to increase the spectral efficiency (SE) of SM, which extends the transmitted symbols into in-phase and quadrature domains. In this paper, we propose a generalized QSM (GQSM) scheme to further increase the SE of QSM by activating more than one transmit antenna in in-phase or quadrature domain. A low-complexity detection scheme for GQSM is provided to mitigate the detection burden of the optimal maximum-likelihood (ML) detection method. An upper bounded bit error rate is analyzed to discover the system performance of GQSM. Moreover, by collaborating with the non-orthogonal multiple access (NOMA) technique, we investigate the practical application of GQSM to cooperative vehicular networks and propose the cooperative GQSM with OMA (C-OMA-GQSM) and cooperative GQSM with NOMA (C-NOMA-GQSM) schemes. Computer simulation results verify the reliability of the proposed low-complexity detection as well as the theoretical analysis, and show that GQSM outperforms QSM in the entire SNR region. The superior BER performance of the proposed C-NOMA-GQSM scheme make it a promising modulation candidate for next generation vehicular networks.

As a new network architecture, Information-Centric Networks (ICN) has great advantages in content distribution and can better meet our needs. But it faced with many threats unavoidably. There are four types of attack in ICN: naming related attacks, routing related attacks, caching related attacks and miscellaneous attacks. These attacks will undermine the availability of ICN, the confidentiality and privacy of data. In addition, routers store a large amount of content for the users' request, and it is necessary to protect these intermediate nodes. Since the styles of content stored in nodes are not the same, using a unified set of intrusion detection rules simply will cause a large number of false positives and false negatives. Therefore, every node should perform intrusion detection according to its own characteristics. In this paper, we propose an intrusion detection mechanism to alert for abnormal packets. We introduce a extensive solution using machine learning for attacks in ICN. Moreover, the nodes in this scheme can adapt to the external environment and intelligently detect packets. Simulation on the machine learning algorithm involved prove that the algorithm is effective and suitable for network packets.

The reliance on timely delivery of messages between avionics and distributed sensor networks in aerospace, IoT, and industry 4.0 holds key importance. In these applications, latency, jitter, and quality of service (QoS) have to take precedence in the network while synchronized tasks performed utilizing Time-Triggered Ethernet (TTE). Currently, some applications of TTE are used in areas of Industry 4.0, Avionics, Aerospace, and Automotive. Time synchronization is a fundamental service in many of the time distributed systems, such as real-time embedded systems and flexible systems. The TTE incorporates periodic execution of tasks that provide the foundation of dependable deterministic systems. TTE development system uses switches and end systems to achieve Time-Triggered (TT) traffic in the network. This is achieved by adjusting all the nodes in the network with an autonomous time. In this paper, we discuss how the performance of TTE is affected by the introduction of external GNSS synchronization. We also discuss requirements from applications, which require synchronization with GNSS, such as controlling multiple TTE development systems at several locations, communication between UAV or a Swarm of UAV's to form a system of system. We also discuss how synchronization in the TTE development system will be achieved with an external time source from GNSS. This will allow the TTE development system to synchronize and perform periodic tasks based on GNSS. The proposed synchronization technique will be beneficial for use with UAV's, Swarm of UAV's and even connecting multiple TTE Systems of Systems. With the external GNSS synchronization in the TTE development system, we will be able to analyze and understand the advantages it has on the performance, latency, jitter, and QoS in a network. We will also analyze external synchronization in TTE as how it will be beneficial to connect multiple TTE systems of systems.

Multi-channel optimisation relies on accurate channel state information (CSI) estimation. Error distributions in CSI can propagate through optimisation algorithms to cause undesirable uncertainty in the solution space. The transformation of uncertainty distributions differs between classic heuristic and Neural Network (NN) algorithms. Here, we investigate how CSI uncertainty transforms from an additive Gaussian error in CSI into different power allocation distributions in a multi-channel system. We offer theoretical insight into the uncertainty propagation for both Water-filling (WF) power allocation in comparison to diverse NN algorithms. We use the Kullback-Leibler divergence to quantify uncertainty deviation from the trusted WF algorithm and offer some insight into the role of NN structure and activation functions on the uncertainty divergence, where we found that the activation function choice is more important than the size of the neural network.

The objective of this paper is to present an approximation-based strategy for solving the problem of nonlinear trajectory optimization with the consideration of probabilistic constraints. The proposed method defines a smooth and differentiable function to replace probabilistic constraints by the deterministic ones, thereby converting the chance-constrained trajectory optimization model into a parametric nonlinear programming model. In addition, it is proved that the approximation function and the corresponding approximation set will converge to that of the original problem. Furthermore, the optimal solution of the approximated model is ensured to converge to the optimal solution of the original problem. Numerical results, obtained from a new chance-constrained space vehicle trajectory optimization model and a 3-D unmanned vehicle trajectory smoothing problem, verify the feasibility and effectiveness of the proposed approach. Comparative studies were also carried out to show the proposed design can yield good performance and outperform other typical chance-constrained optimization techniques investigated in this paper.

Highly constrained trajectory optimization problems are usually difficult to solve. Due to some real-world requirements, a typical trajectory optimization model may need to be formulated containing several objectives. Because of the discontinuity or nonlinearity in the vehicle dynamics and mission objectives, it is challenging to generate a compromised trajectory that can satisfy constraints and optimize objectives. To address the multiobjective trajectory planning problem, this paper applies a specific multiple-shooting discretization technique with the newest NSGA-III optimization algorithm and constructs a new evolutionary optimal control solver. In addition, three constraint handling algorithms are incorporated in this evolutionary optimal control framework. The performance of using different constraint handling strategies is detailed and analyzed. The proposed approach is compared with other well-developed multiobjective techniques. Experimental studies demonstrate that the present method can outperform other evolutionary-based solvers investigated in this paper with respect to convergence ability and distribution of the Pareto-optimal solutions. Therefore, the present evolutionary optimal control solver is more attractive and can offer an alternative for optimizing multiobjective continuous-time trajectory optimization problems.

This brief presents an integrated trajectory planning and attitude control framework for six-degree-of-freedom (6-DOF) hypersonic vehicle (HV) reentry flight. The proposed framework utilizes a bilevel structure incorporating desensitized trajectory optimization and deep neural network (DNN)-based control. In the upper level, a trajectory data set containing optimal system control and state trajectories is generated, while in the lower level control system, DNNs are constructed and trained using the pregenerated trajectory ensemble in order to represent the functional relationship between the optimized system states and controls. These well-trained networks are then used to produce optimal feedback actions online. A detailed simulation analysis was performed to validate the real-time applicability and the optimality of the designed bilevel framework. Moreover, a comparative analysis was also carried out between the proposed DNN-driven controller and other optimization-based techniques existing in related works. Our results verify the reliability of using the proposed bilevel design for the control of HV reentry flight in real time.

Large-scale multi-antenna systems can effectively improve data transmission reliability and throughput for smart grid. However, the massive number of antennas and radio frequency (RF) chains also result in high complexity and energy cost. In this paper, we develop a new performance benchmark named energy economic efficiency for measuring the time-average throughput per energy cost. Then, we investigate how to maximize long-term energy economic efficiency via the joint optimization of communication and energy resource allocation. The formulated joint optimization problem is NP-hard because it not only involves long-term nonlinear optimization objective and constraints, but also involves both integer and continuous optimization variables. Next, we propose an online joint antenna selection and power control algorithm by combining nonlinear fractional programming, Lyapunov optimization, and bisection method. The proposed algorithm can achieve bounded performance deviation from the optimum performance without requiring the prior knowledge of future channel state information (CSI), energy arrival, and electricity price. Finally, a comprehensive theoretical analysis is provided, and the proposed algorithm is verified through simulations under various system configurations.

This paper investigates the problem of one-step ahead optimal active sensing strategy to minimise estimation errors with range-only measurements for non-manoeuvring target. The determinant of Fisher Information Matrix (FIM) is utilized as the objective function in the proposed optimisation problem since it quantifies the volume of uncertainty ellipsoid of any efficient estimator. In consideration of physical velocity and turning rate constraints, the optimal heading angle command that maximises the cost function is derived analytically. Simulations are conducted to validate the analytical findings.

In this paper, a multi-agent probabilistic optimization algorithm is applied to the problem of multi-vehicle coordination. The algorithm is known as “Probability Collectives” (PC) and has roots in Game Theory and Optimization theory. It is traditionally used for finding optimal solutions of NP-hard problems such as the travelling salesman problem. On the other end, the proposed PC formulation presented in this paper focuses on a minimal complexity implementation for solving the coordination problem in a time of the order of magnitude of 0.1. Besides time constraints, the emphasis in the design is put on ensuring that the algorithm always comes up with a feasible solution. Simulations show that both objectives are reached while having a decentralized algorithm, and flexible with respect to the type of situations it can deal with. Additional benefits of the PC algorithm include robustness to agent failure and the possibility to accommodate non-collaborative vehicles (market penetration of autonomous vehicles <; 100%).

Car tracking in a traffic environment is a crucial task for the autonomous vehicle. Through tracking, a self-driving car is capable of predicting each car’s motion and trajectory in the traffic scene, which is one of the key components for traffic scene understanding. Currently, 2D vision-based object tracking is still the most popular method, however, multiple sensory data (e.g. cameras, Lidar, Radar) can provide more information (geometric and color features) about surroundings and show significant advantages for tracking. We present a 3D car tracking method that combines more data from different sensors (cameras, Lidar, GPS/IMU) to track static and dynamic cars in a 3D bounding box. Fed by the images and 3D point cloud, a 3D car detector and the spatial transform module are firstly applied to estimate current location, dimensions, and orientation of each surrounding car in each frame in the 3D world coordinate system, followed by a 3D Kalman filter to predict the location, dimensions, orientation and velocity for each corresponding car in the next time. The predictions from Kalman filtering are used for re-identifying previously detected cars in the next frame using the Hungarian algorithm. We conduct experiments on the KITTI benchmark to evaluate tracking performance and the effectiveness of our method.

In this paper, a constrained space maneuver vehicles trajectory optimization problem is formulated and solved using a new three-layer-hybrid optimal control solver. To decrease the sensitivity of the initial guess and enhance the stability of the algorithm, an initial guess generator based on a specific stochastic algorithm is applied. In addition, an improved gradient-based algorithm is used as the inner solver, which can offer the user more flexibility to control the optimization process. Furthermore, in order to analyze the quality of the solution, the optimality verification conditions are derived. Numerical simulations were carried out by using the proposed hybrid solver and the results indicate that the proposed strategy can have better performance in terms of convergence speed and convergence ability when compared with other typical optimal control solvers. A Monte-Carlo simulation was performed and the results show a robust performance of the proposed algorithm in dispersed conditions.

This paper proposes a two-stage optimization framework for generating the optimal parking motion trajectory of autonomous ground vehicles. The motivation for the use of this multilayer optimization strategy relies on its enhanced convergence ability and computational efficiency in terms of finding optimal solutions under the constrained environment. In the first optimization stage, the designed optimizer applies an improved particle swarm optimization technique to produce a near-optimal parking movement. Subsequently, the motion trajectory obtained from the first stage is used to start the second optimization stage, where gradient-based techniques are applied. The established methodology is tested to explore the optimal parking maneuver for a car-like autonomous vehicle with the consideration of irregularly parked obstacles. Simulation results were produced and comparative studies were conducted for different mission cases. The obtained results not only confirm the effectiveness but also reveal the enhanced performance of the proposed optimization framework.

This paper addresses the problem of maneuver recognition and behavior anomaly detection for generic targets by means of pattern matching techniques. The problem analysis is performed making specific reference to moving vehicles in a multi-lane road scenario, but the proposed technique can be easily extended to significantly different monitoring contexts. The potential extensions include, but are not limited to, public surveillance in train station or airport, road incidents and relative precursors detection, and vehicle trajectories monitoring. The overall proposed solution consists of a trajectory analysis tool and a string-matching method. This allows the integration of two different approaches, to detect both a priori defined patterns of interest and generic maneuver/behavior standing out from those regularly exhibited. The proposed string matching algorithm is newly developed in this paper, based on Regular Expressions. For generating reference patterns, a technique for the automatic definition of a dictionary of regular expressions matching the commonly observed target maneuvers is developed. The advantages of the proposed approach are extensively analyzed and tested by means of numerical simulations and experiments.

This paper considers the problem of two-dimensional constrained trajectory optimization of a point-mass aerial robot for constant-maneuvering target localization using bearing-only measurement. A performance metric that can be utilized in trajectory optimization to maximize target observability is proposed first based on geometric conditions. One-step optimal maneuver that maximizes the observability criterion is then derived analytically for moving targets. The heading angle constraint is also incorporated in the proposed optimal maneuver derivation to support practical application. Numerical simulations with some comparisons are presented to validate the analytical findings.

Hybrid Electric Propulsion System (HEPS) is attracting growing interest from researchers and other stakeholders working in the field. The pace of technology development is accelerating due to pressures for more energy efficient air vehicles with lower emissions and environmental impact; and to meet ACARE 2050 targets. The battery pack State of Charge (SOC) plays a critical role in the HEPS supervisory controller. In this paper, firstly a new operation-classification battery model is proposed for Li-Po battery. Moreover, since the accuracy of parameter identification is important in state estimation. An event triggered Adaptive Genetic Algorithm (AGA) is used for online parameter identification. Secondly, the Extended Kalman Filter (EKF) is applied for single battery cell SOC estimation. Furthermore, based on maximum and minimum battery cell voltages and SOC values, a Fuzzy Logic Estimator (FLE) is used for pack SOC estimation. Experimental results show that the proposed AGA can effectively track battery parameter variation and the SOC estimation error for single cell and for the complete battery pack with less than 1% error.

This paper describes a novel particle swarm optimizer algorithm. The focus of this study is how to improve the performance of the classical particle swarm optimization approach, i.e., how to enhance its convergence speed and capacity to solve complex problems while reducing the computational load. The proposed approach is based on an improvement of particle swarm optimization using evolutionary game theory. This method maintains the capability of the particle swarm optimizer to diversify the particles' exploration in the solution space. Moreover, the proposed approach provides an important ability to the optimization algorithm, that is, adaptation of the search direction, which improves the quality of the particles based on their experience. The proposed algorithm is tested on a representative set of continuous benchmark optimization problems and compared with some other classical optimization approaches. Based on the test results of each benchmark problem, its performance is analyzed and discussed.

This paper proposes a novel game-theoretical autonomous decision-making framework to address a task allocation problem for a swarm of multiple agents. We consider cooperation of self-interested agents, and show that our proposed decentralized algorithm guarantees convergence of agents with social inhibition to a Nash stable partition (i.e., social agreement) within polynomial time. The algorithm is simple and executable based on local interactions with neighbor agents under a strongly connected communication network and even in asynchronous environments. We analytically present a mathematical formulation for computing the lower bound of suboptimality of the outcome, and additionally show that at least 50% of suboptimality can be guaranteed if social utilities are nondecreasing functions with respect to the number of coworking agents. The results of numerical experiments confirm that the proposed framework is scalable, fast adaptable against dynamical environments, and robust even in a realistic situation.

In this paper we present a decentralised algorithm to solve the Task Allocation problem. Given a set of tasks and a set of robots each with its own utility function, this problem concerns the non-overlapping allocation of tasks to agents maximising the sum of the robot's utility functions. Our algorithm provides a constant factor approximation of (1 - 1/e ≈ 63%) for positive-valued monotone submodular utility functions, and of (1/e ≈ 37%) for positive-valued non-monotone submodular utility functions. In our algorithm, robots only rely on local utility function and neighbour to neighbour communications to find the solution. The algorithm proceeds in two steps. Initially, the robots use Maximum Consensus-based algorithm to find a relaxed solution of the problem using the multilinear extension of their utility functions. Finally, they follow a randomised rounding procedure to exchange valuations on sets of tasks in order to round the relaxed solution. To conclude, we provide experimental evidence of our claims for both monotone and non-monotone submodular functions.

Most optical flow algorithms are based on the assumption of brightness constancy of individual pixels while moving on the image plane. Although being attractive analytically, this assumption is often violated under non-ideal visual conditions resulting in poor flow estimates. This paper presents an approach to support the validity of the assumption under such conditions. The method describes the grey-level of each pixel by the content of its neighbourhood using a geometric moment rather than its individual intensity function value. Then, the description of each pixel is normalised and made insensitive to fluctuations of intensity. As a result, the optical flow algorithm becomes much more reliable and robust against visual phenomena like varying illumination, specular reflections and shadows. The proposed approach is applied to a regression method and comprehensive results on synthetic and real data are reported. 1

Capture mechanisms are used to transfer objects between two vehicles in the space with no physical contact. A sphere (canister) detection and tracking method using an enhanced Hough transform technique and Hinfinfilter is proposed. The presented system aims to assist in the capture operation, currently investigated the European Space Agency and other partners, and to be used in space missions as an alternative to docking or berthing operations. Test results show the robustness and reliability of the proposed method. They also demonstrate the low computational and memory complexities needed.

This paper describes a multiple sensor fusion approach in which a sensor based navigation scheme needs to fuse a stochastic aerial robot position estimate from an extended Kalman Filter (EKF) with a deterministic aerial robot position estimate from an Interval Analysis (IA) algorithm. The aerial robot is equipped with inertial sensors (INS) and ultrasonic sensors. An EKF is used to estimate the aerial robots position using the inertial sensors. When landmarks are present, the ultrasonic sensor measurements are processed using an IA algorithm to get an interval aerial robot position estimate. In order to obtain a better estimate for the aerial robot position both deterministic and stochastic estimates need to be used via a data fusion approach. Thus there is a need to study how to fuse the aerial robot position estimate having a Gaussian distribution (from EKF) with a aerial robot position estimate that has a uniform distribution (from IA). This is accomplished here by using the Box-Muller transform to transform the interval aerial robot position estimate having a uniform distribution to a real number aerial robot position with a Gaussian distribution and giving that as a measurement to the EKF to obtain a fused estimate of the aerial robot position.

This work describes a new approach for mobile robot navigation using interval analysis and fuzzy logic. The robot is equipped with inertial sensors, encoders and ultrasonic sensors. The map used for this study is two-dimensional and it is assumed to be known. Multiple sensor fusion for robot localisation and navigation has attracted a lot of interested in recent years. The most commonly used approach is based on Kalman filter and other stochastic filters. Here we propose an alternative approach using interval analysis with multiple sets of ultrasonic measurements. Interval analysis has been already successfully applied in the past for robot localisation. But the results obtained may be conservative. Therefore this approach is extended using multiple sets of ultrasonic measurements, which results in estimation of multiple interval robot positions. These multiple interval robot positions are then fused using fuzzy logic to give a less conservative interval robot position estimate. Also interval analysis based algorithm can be used only in the presence of land marks. This problem is overcome here using additional sensors such as encoders and inertial sensors, which gives an estimate of the robot position using fuzzy logic in the absence of land marks.

Multiple sensor fusion for robot localisation and navigation has attracted a lot of interest in recent years. This paper describes a sensor based navigation approach using an interval analysis (IA) based adaptive mechanism for an unscented Kalman filter (UKF). The robot is equipped with inertial sensors (INS), encoders and ultrasonic sensors. A UKF is used to estimate the robots position using the inertial sensors and encoders. Since the UKF estimates may be affected by bias, drift etc. we propose an adaptive mechanism using IA to correct these defects in estimates. In the presence of landmarks the complementary robot position information from the IA algorithm using ultrasonic sensors is used to estimate and bound the errors in the UKF robot position estimate.

We present the lateral acceleration control design of nonlinear missile model using a multiobjective evolutionary optimisation method (NSGA-II -like). The controller design for the uncertain plants is carried out by minimising gain and phase margins and tracking performance objectives of the corresponding vertices. Pareto surfaces are used to identify a feasible control structure and analyse its performance tradeoffs. Based on the selected trade-off solution, the interpolated controller, whose poles, zeros and gains are linear continuous functions of Mach number and incidence, are designed for the whole operating envelope. The interpolated controller is now synthesised by minimising the Euclidean distance of multiple operating points' objective values. The stability is preserved by additionally overlapping these operating regions. The nonlinear simulation results show that the resulting interpolated controller is indeed a robust tracking controller for all possible perturbations.

In this paper an effective conventional/intelligent approach has been described which solves the problem of actuator competing factors for the class of indirect all-wheel drive skid-steer mobile robots. The above arrangement allows all the wheels to be independently driven in order to meet the different variations in the tyre-ground interface. However this wheel independence in practice can result in the independent wheel controllers to compete in order to achieve their individual design objective. It has been observed from real mobile robots that this phenomenon results in higher than usual current requests due to the force mismatch between the different wheel actuators which strain the energy system faster than usual and consequently result in a higher risk of being unsuccessful when operating autonomously in demanding environments such as a planetary rover, a construction or a mining robot.

The present aim of this research is to design a navigation sensor suite for a newly built mobile robot using low cost multiple sensors. A basic requirement for an autonomous mobile robot is its ability to localize itself accurately. This paper describes an accurate method for generating navigational data for a wheeled mobile robot. An adaptive extended Kalman filter (AEKF) is used to fuse data from multiple low cost sensors. In order to estimate the spatial position of a wheeled robot, a combination of accelerometers, a rate gyroscope and two wheel encoders are used. The system discussed in this paper has more measurement sensors than system states and therefore the sensors give overlapping, low-grade information affected by noise, bias, drift, etc. The dynamics of the robot and sensor system are non-linear. Therefore an AEKF is used to estimate these overlapping low-grade measured sensor data and give the best possible estimate of the mobile robot position. The adaptive mechanism in this case uses the Riccati Equation adaption. The basic idea is to change the Kalman Gain. This is done by changing the Process noise co-variance matrix adaptively. Simulations show an improved performance in the estimates from the AEKF when compared to the EKF.

In this paper, an indirect adaptive control scheme is proposed for a multiple-input multiple-output differentially steered mobile robot. The resulted closed-loop system has an effective control for both the vehicle longitudinal velocity and the vehicle yaw rate. The closed-loop system stability is examined via LMI quadratic stability test. The proposed scheme shows effectiveness for a variety of realistic simulation scenarios.

This paper presents the application of the Takagi-Sugeno (TS) model synthesis for a quasi-linear parameter varying (QLPV) four wheel differentially steered mobile robot. The focus of this paper is a mathematical description of the mobile robot model as a QLPV and application of the TS fuzzy logic framework which complements the QLPV approach. Using QLPV model data several local TS linear models were identified using recursively the subtractive clustering method with specified error criteria. The identified TS local models resulted in a family of LTI models, which are equivalent to the linearised QLPV models. The T-S blended model synthesis resulted in a close approximation to the non-linear model dynamics.