This study investigates the vulnerabilities of autonomous navigation and landing systems in Urban Air Mobility (UAM) vehicles. Specifically, it focuses on Trojan attacks that target deep learning models, such as Convolutional Neural Networks (CNNs). Trojan attacks work by embedding covert triggers within a model’s training data. These triggers cause specific failures under certain conditions, while the model continues to perform normally in other situations.We assessed the vulnerability of Urban Autonomous Aerial Vehicles (UAAVs) using the DroNet framework. Our experiments showed a significant drop in accuracy, from 96.4% on clean data to 73.3% on data triggered by Trojan attacks. To conduct this study, we collected a custom dataset and trained models to simulate real-world conditions. We also developed an evaluation framework designed to identify Trojan-infected models. This work demonstrates the potential security risks posed by Trojan attacks and lays the groundwork for future research on enhancing the resilience of UAM systems.

In this paper, we propose a conflict-free multi-agent flight scheduling that ensures robust separation in constrained airspace for Urban Air Mobility (UAM) operations application. First, we introduce Pairwise Conflict Avoidance (PCA) based on delayed departures, leveraging kinematic principles to maintain safe distances. Next, we expand PCA to multi-agent scenarios, formulating an optimization approach that systematically determines departure times under increasing traffic densities. Performance metrics, such as average delay, assess the effectiveness of our solution. Through numerical simulations across diverse multi-agent environments and real-world UAM use cases, our method demonstrates a significant reduction in total delay while ensuring collision-free operations. This approach provides a scalable framework for emerging urban air mobility systems.

As autonomous vehicles become an essential component of modern transportation, they are increasingly vulnerable to threats such as GPS spoofing attacks. This study presents an adaptive detection approach utilizing a dynamically tuned Density Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, designed to adjust the detection threshold (ε) in real-time. The threshold is updated based on the recursive mean and standard deviation of displacement errors between GPS and in-vehicle sensors data, but only at instances classified as non-anomalous. Furthermore, an initial threshold, determined from 120,000 clean data samples, ensures the capability to identify even subtle and gradual GPS spoofing attempts from the beginning. To assess the performance of the proposed method, five different subsets from the real-world Honda Research Institute Driving Dataset (HDD) are selected to simulate both large and small magnitude GPS spoofing attacks. The modified algorithm effectively identifies turn-by-turn, stop, overshoot, and multiple small biased spoofing attacks, achieving detection accuracies of 98.62±1%, 99.96±0.1%, 99.88±0.1%, and 98.38±0.1%, respectively. This work provides a substantial advancement in enhancing the security and safety of AVs against GPS spoofing threats.

The integration of Unmanned Aircraft Systems (UAS) into the National Airspace System (NAS) requires robust encounter modeling tools to evaluate Detect-and-Avoid (DAA) systems. However, existing tools often lack the ability to model the unique dynamics of large UAS (lUAS) and small UAS (sUAS), and few are available as open-source solutions. In this paper, we introduce novel flight modeling concepts for lUAS and sUAS, developed within an open-source framework. For lUAS, we propose a hybrid modeling strategy that combines probabilistic manned aircraft models with UAS-specific performance constraints. A machine learning-based surrogate model is employed to streamline feasibility evaluation and enable the generation of realistic trajectories. The sUAS flight modeling technique enables mission-aware trajectory generation by incorporating geospatial data and customized control architecture for fixed-wing and multirotor configurations. These models capture a wide range of aircraft dynamics, offering the potential to generate versatile encounter datasets for DAA evaluation. By releasing them as open-source resources, we aim to encourage broader collaboration, inform regulatory development, and drive innovation in encounter modeling, all in support of the safe and effective integration of UAS into the NAS.

As robots become more prevalent in society and applied in various workplace sectors, individuals must have an appropriate amount of trust that aligns with robots' or automated systems' actual capabilities, facilitating optimal and safe human-robot interaction. Appropriately calibrated trust levels can enhance robots' safe and successful adoption into our society and their unique applied environments. The current research aims to assess individuals' self-reported trust levels in a triadic human-robot-human interaction concerning a collaborative haptically enabled “sonography” style robot (having tele-operative capabilities) to assess moderators of trust unique to this specific domain. The objectives of the current research are to identify participants' trust levels in a triadic interaction focusing on the operator's proxemic location while operating the robot (1) and to compare self-reported trust levels across conditions suggested by the literature to have an influence (2). A repeated measures ANDVA revealed a significant association between the replicated traditional sonography assessment and participants possessing higher trust levels than all robot-related conditions. Further, participants had greater trust for the smooth and slow-functioning robot than the non-smooth functioning robot. Lastly, the current study's findings suggest that, compared to the other robot-related conditions, the experimenter's location operating the tele-operative robot does not significantly influence participants' trust levels. Future research should consider exploring humans' qualitative perceptions of their interactions with sonography robots and whether trust can be more accurately calibrated over time. Doing so may assist in developing an in-depth understanding of the discrepancies between human-human interaction and human-robot interactions unique to this setting.

Neural Architecture Search (NAS) has significantly improved the accuracy of image classification and segmentation. However, these methods concentrate on finding segmentation structures for natural or medical applications. In this study, we introduce a NAS approach based on gradient optimization to identify ideal cell designs for road segmentation. To the best of our knowledge, this work represents the first application of gradient-based NAS to road extraction. Taking insight from the U-Net model and its successful variations in different image segmentation tasks, we propose NAS-enhanced U-Net, illustrated by an equal number of cells in both encoder and decoder levels. While cross-entropy combined with dice loss is commonly used in many segmentation tasks, road extraction brings up a unique challenge due to class imbalance. To address this, we introduce a combination of loss function. This function merges cross-entropy with weighted Dice loss, focusing on elevating the importance of the road class by assigning it a weight (⍵), while background Dice values are disregarded. The results indicate that the optimal weight for the proposed model equals 2. Additionally, our work challenges the assumption that increased model parameters or depth inherently leads to improved performance. Therefore, we establish search spaces 2,3,4,5,6,7 and 8 to automatically choose the optimal depth for model. We present promising segmentation results for our proposed method, achieved without any pretraining on the Massachusetts road dataset. Furthermore, these results are compared with those of 14 models categorized into four groups: U-Net, Segnet, FCN8, and Nas-U-Net.

In recent years, the development of robotics and artificial intelligence (AI) systems has been nothing short of remarkable. As these systems continue to evolve, they are being utilized in increasingly complex and unstructured environments, such as autonomous driving, aerial robotics, and natural language processing. As a consequence, programming their behaviors manually or defining their behavior through the reward functions [as done in reinforcement learning (RL)] has become exceedingly difficult. This is because such environments require a high degree of flexibility and adaptability, making it challenging to specify an optimal set of rules or reward signals that can account for all the possible situations. In such environments, learning from an expert's behavior through imitation is often more appealing. This is where imitation learning (IL) comes into play - a process where desired behavior is learned by imitating an expert's behavior, which is provided through demonstrations.This article aims to provide an introduction to IL and an overview of its underlying assumptions and approaches. It also offers a detailed description of recent advances and emerging areas of research in the field. Additionally, this article discusses how researchers have addressed common challenges associated with IL and provides potential directions for future research. Overall, the goal of this article is to provide a comprehensive guide to the growing field of IL in robotics and AI.

The growing prevalence of cybersecurity threats has increased the demand for robust intrusion detection systems (IDSs). Deep learning techniques have shown promising results in detecting and mitigating these threats, making them an increasingly popular choice in IDS design. However, evaluating the performance of deep learning-based IDSs can be challenging due to the complexity of the models and the lack of standardized evaluation metrics. This review paper presents an overview of the most common evaluation metrics used in deep learning-based IDSs, including precision, confusion metrics, accuracy, F1 score, Area Under Curve (AUC), and recall. Several studies have applied machine-learning classic algorithms like Random Forest, Decision Tree, Logistic Regression, and others, but for this paper, we used a Convolutional Neural Network (CNN) that would be independent of the features in the dataset. The studied papers did not provide AUC and none of them balanced the dataset based on the feature's proportion. The dataset utilized in this study is the CSE-CIC-IDS2018 dataset, which underwent meticulous cleansing and normalization procedures to ensure the inclusion of legitimate and useful data. Furthermore, a weighting mechanism was introduced to balance the dataset and mitigate the potential for bias in the Machine Learning process.

Transcranial Magnetic Stimulation (TMS) is a non-invasive and painless technique used in both clinical trials and research on cortical activity and brain networks. TMS involves the use of an electromagnetic coil, which can induce powerful but brief magnetic pulses. When the coil is headed against the scalp, it can induce electrical activity in underlying brain tissue. For effective results, the TMS coil should be in appropriate contact with patients' scalp and positioned for consistent stimulation. In many cases, it requires researchers and clinicians to not only hold and position the coil on subjects' head, also to take care to ensure appropriate and consistent contact between the TMS coil and subject's scalp. This task is noticeably tiresome for the operators considering weight of the coil and a dense cable attached to it. On the other side, the patient or participant has to sit motionless; otherwise, the contact will be lost and the stimulation will have a reduced impact. In this paper, we propose and develop a haptically-enabled teleoperated robotic platform that removes all those limitations and burdensome from both TMS operators and patients/participants. The operator, through a haptic interface, remotely controls a robotic arm holding the coil. This system provides the operator with the sense of touch to feel the contact force between the coil and patient/participant's head. Therefore, operators and patients/participants do not need to be in the same location while conducting TMS, including the “motor thresholding” procedure. This will offer a huge benefit to the healthcare services in rural areas. Experimental evaluations carried out to demonstrate the effectiveness of the proposed robotic system.

As the computer networks growing up rapidly, network engineers and administrators are going through a lot of difficulties to keep the network under their management properly and troubleshoot the issues pretty quick. Also they need to keep thinking about the future growth and compatibility to new features and technologies. Therefor manual network management and monitoring is not efficient anymore and most of the companies are trying to adapt the new technology for automation either in monitoring and/or troubleshooting.Software Defined Networking (SDN) is one of the new technologies which is trying to help the network engineers or administrators to have their networks under more control. Also deep-learning and Artificial Intelligent are some technologies which can help to prevent issues or improve the network control performance.

As 5G, new generation of wireless technology, started to be implemented all around the world, scientists and engineers have been working to use more of its benefits in their fields. One of the most interesting areas that 5G, and ultra fast communications in general, is being devised is the networked systems. Amongst network-based systems, telerobotic has attracted most attention thanks to its numerous applications in medicine, under water explorations, rescue systems, and outer space discovery. However, there are challenges and considerations in developing such systems based on 5G technology. In this paper we are going to review some of these challenges also talk about the key benefits of 5G and its use case in robotics. This paper introduces main novel features and properties of 5G networks, such as network slicing, eMBB, uRLLC, mMTC, and more. An immediate utilisation of 5G is due to its ultra low latency capabilities, and is discussed in latency critical services. As an outcome, 0.25−100 ms is the range of delays experienced in such services utilising 5G with error rates less than 10−3.

Industry 5.0 is here, and human interaction experts claim that in the process of augmenting a high production/manufacturing workplace, a safety critical situation is created with the introduction of “Cobots”. A Multi-Agent Safety System (MASS) is presented as a solution in this paper which uses commercial, wearable technologies with high data sharing acceptance rates such as the Apple watch to collect and share real time ECG signals with the Cobot. Principal Component Analysis (PCA) is selected as a dimension reduction tool because it is well established and meets the requirements for reliability in the development of a human-centric, safety system. Five Machine Learning (ML) classifiers (KNN, NB, RF, DT and GBM) are used with binary classification to predict whether the human is Distracted (Event 1) or Not Distracted (Event 0) to determine if this will pose a safety risk to the Human Robot Collaboration (HRC) System. Decision Tree (DT) classifier with 4 Principal Components (PCs) is evaluated at 98% Accuracy and 99%AUC and is the recommended model for future development of the MASS. A road map is also presented to ensure the longevity of MASS while signifying the inclusion of real time data which can close the demographic data gap and help to improve the privacy, efficiency and contextual reliability of the MASS model in the Industry 5.0 workplace.

This study aims to explore different pre-trained models offered in the Torchvision package which is available in the PyTorch library. And investigate their effectiveness on fine-grained images classification. Transfer Learning is an effective method of achieving extremely good performance with insufficient training data. In many real-world situations, people cannot collect sufficient data required to train a deep neural network model efficiently. Transfer Learning models are pre-trained on a large data set, and can bring a good performance on smaller datasets with significantly lower training time. Torchvision package offers us many models to apply the Transfer Learning on smaller datasets. Therefore, researchers may need a guideline for the selection of a good model. We investigate Torchvision pre-trained models on four different data sets: 10 Monkey Species, 225 Bird Species, Fruits 360, and Oxford 102 Flowers. These data sets have images of different resolutions, class numbers, and different achievable accuracies. We also apply their usual fully-connected layer and the Spinal fully-connected layer to investigate the effectiveness of SpinalNet. The Spinal fully-connected layer brings better performance in most situations. We apply the same augmentation for different models for the same data set for a fair comparison. This paper may help future Computer Vision researchers in choosing a proper Transfer Learning model.

The early and reliable detection of COVID-19 infected patients is essential to prevent and limit its outbreak. The PCR tests for COVID-19 detection are not available in many countries, and also, there are genuine concerns about their reliability and performance. Motivated by these shortcomings, this article proposes a deep uncertainty-aware transfer learning framework for COVID-19 detection using medical images. Four popular convolutional neural networks (CNNs), including VGG16, ResNet50, DenseNet121, and InceptionResNetV2, are first applied to extract deep features from chest X-ray and computed tomography (CT) images. Extracted features are then processed by different machine learning and statistical modeling techniques to identify COVID-19 cases. We also calculate and report the epistemic uncertainty of classification results to identify regions where the trained models are not confident about their decisions (out of distribution problem). Comprehensive simulation results for X-ray and CT image data sets indicate that linear support vector machine and neural network models achieve the best results as measured by accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC). Also, it is found that predictive uncertainty estimates are much higher for CT images compared to X-ray images.

This paper investigates a novel synchronisation strategy for controlling Internet-based teleoperation systems. These kinds of systems considerably suffer from network-induced latencies. Random time-varying delays resulted by the Internet deteriorate the stability and performance of teleoperation processes. Moreover, uncertain dynamic elements, including human operators and partially known remote environments introduce further difficulties to the control design of such systems. Utilising the learning capabilities of artificial neural networks, this paper develops an adaptive algorithm to deal with time-delays and uncertainties negatively affecting an Internet-based teleoperation process. The stable convergence of the proposed control algorithm is proved by Lyapunov-Krasovskii stability criteria. Moreover, the robust performance of the controller is also verified via experimental evaluations.

End to end learning for autonomous navigation and driving has become a growing research trend in both industry and academia in recent years. Its promise is in treating the whole driving pipeline as the development of a deep neural network (DNN). Its Achilles' heel is access to thousands of images required for training of the DNN. This paper comprehensively investigates the applicability of the deep transfer learning for the specific task of end to end learning of autonomous navigation. Five state of the art DNNs including ResNet, AlexNet, and Densenet are applied here for extracting features from images taken by the front-facing camera of a mobile robot. Extracted features have different information values as DNNs have different architectures and learning capabilities. These features are then processed by a multilayer fully connected neural network to estimate the robot angular velocity. Obtained results for different DNNs indicate that the transfer learning-based models show a promising performance for accurately estimating the angular velocity purely using visual information. According to obtained results, AlexNet-base model outperforms others in terms of the estimation accuracy and the performance consistency.

Communication delays are known to create stability and performance issues in multilateral teleoperation systems. Multilateral teleoperation configurations usually include more than two communication channels, which can become problematic for robot control when limitations in network bandwidth results in delays and uncertainties in data transmission routes. This study develops a sliding surface based on the synchronization errors characterized between each sides of the considered multilateral teleoperation system. Here, two slave robots receive commands from the master system to cooperatively execute the desired teleoperation task in the remote, shared workspace. Lyapunov stability analysis approach guarantees the performance of the proposed controller. Moreover, the effectiveness of the controller is experimentally evaluated through a real-world Internet-based double-slave teleoperation system.

This paper proposes a robust adaptive algorithm that effectively copes with time-varying delay and uncertainties in Internet-based teleoperation systems. Time-delay induced by the communication network, as a major problem in teleoperation systems, along with uncertainties in modeling of robotic manipulators and remote environment warn the stability and performance of the system. A robust adaptive control algorithm is developed to deal with the system uncertainties and to provide a smooth estimation of delayed reference signals. The proposed control algorithm generates chattering-free torques which is one of the practical considerations for robotic applications. In addition, the achieved input-to-state stability gains do not necessarily require high gain control torques to retain the system's stability. Experimental simulation studies validate the effectiveness of the proposed control strategy on a teleoperation system consisting of a Phantom Omni Haptic device and SimMechanics model of the industrial manipulator UR10. The validation of the proposed control methodology was executed through a real-time Internet-based communication established over 4G mobile networks between Australia and Scotland.

Interacting with human operators, remote environment, and communication networks, teleoperation systems are considerably suffering from complexities and uncertainties. Managing these is of paramount importance for safe and smooth performance of teleoperation systems. Among the countless solutions developed by researchers, type-2 fuzzy (T2F) algorithms have shown an outstanding performance in modeling complex systems and tackling uncertainties. Moreover, artificial neural networks (NNs) are well known for their adaptive learning potentials. This article proposes an adaptive interval type-2 fuzzy neural-network control scheme for teleoperation systems with time-varying delays and uncertainties. The T2F models are developed based on the experimental data collected from a teleoperation setup over a local computer network. However, the resulted controller is evaluated on an intercontinental communication network through the Internet between Australia and Scotland. Moreover, the slave robot and the remote workspace are completely different and unforeseen. Stability and performance of the proposed control is analyzed by Lyapunov-Krasovskii method. Comprehensive comparative studies demonstrate that the proposed controller outperforms traditional techniques in experimental evaluations.

Traditional point prediction systems compute a most probable value without representing the uncertainty. The point prediction is a value close to the mean or the median. A person or an autonomous system may require a prediction corresponds to a different cumulative probability (CP), known as the uncertainty bound. Therefore, in this paper, we present a probability density computing neural network (NN) training procedure. To overcome the limitation of an effective cost function, example uncertainty bounds are constructed with the help of correlation. Similar occurrences are selected through the correlation and weights are assigned to each similar occurrence based on both shape-similarities and ratio based similarities. Then example results from similar samples are considered. The normalized weighted distribution of examples is the probability distribution. Finally, a shallow NN with the example probability density is trained. The NN receives input circumstances and the cumulative probability. The NN returns the value corresponds to the given circumstances and the cumulative probability. Proposed cumulative probability computation point from a shallow NN is less computation extensive compared to the correlation-based similarity analysis. Moreover, we propose a probability density computation NN for the first time. We also upload an example code to the GitHub.

The field of neuroevolution has received great attention in recent years due to its promising capability for developing well-performing models. It has been applied to many real-world problems ranging from medical diagnosis to autonomous robots. The choice of the evolutionary algorithm (EA) has a huge impact on the neuroevolution overall performance. Despite recent progress in the field, it is not clear what the best choice of EA is. The problem becomes more severe considering a dozen of EAs available for neuroevolution applications. In this paper, six state of the art EAs are applied for the task of autonomous robot navigation. These EAs are MultiVerse optimizer (MVO), moth-flame optimization (MFO), particle swarm optimization (PSO), cuckoo search (CS), Grey wolf optimizer (GWO) and bat algorithm. MLP networks are trained using these six evolutionary algorithms to solve the classification task related to the autonomous robot navigation. Comprehensive experiments are conducted using three datasets and obtained results are visually and statistically compared. To the best knowledge of the authors, comparison among the aforementioned algorithms has not been considered in the literature. It is found that neuroevolution methods perform well for the task of autonomous robot navigation. Amongst investigated EAs, MVOtrained achieves the highest and most consistent performance metrics.

Imitation learning is an efficient paradigm for teaching and controlling intelligent autonomous cars. Obtaining a set of suitable demonstrations to learn an end-to-end policy from raw pixels is a challenging task in imitation learning problems. Deep neural networks have recently shown outstanding results in learning from raw high dimensional data for solving a wide range of real-world applications. The success of deep neural networks depends on finding suitable hyperparameters for constructing network architecture. Besides, designing hand-crafted deep architectures is not an efficient way for achieving the best performance. To address this issue, this paper performs a neuro-evolution method based on genetic algorithm for finding the optimal deep neural networks architecture in terms of hyperparameters. The experimental results show the effectiveness of the proposed approach for training an autonomous vehicle.

Deep neural networks have proven themselves as a strong approach in image classification and object detection with high accuracy. However, they are computationally demanding and the trained networks contain millions of active parameters and connections. Two recent trends of having deeper and dense architectures and the deployment of trained networks on resource-constrained devices such as smart phones and portable tablets bring new challenges. Instead of deploying an ensemble of smaller networks, we propose a pruning methodology on a trained network so that a smaller version of a fully trained network has the same and even better accuracy in comparison to the original one. We achieve two objectives with the pruning scheme. First, we have a smaller network with a better accuracy level, and we make the trained model avoids overfitting. Accordingly, an evolutionary based framework including three steps is defined to perform further tuning on trained deep network using dropping nodes and connections. This study shows that implementing genetic algorithm, after preprocessing and training stages, not only results in partially connected networks, but also increases performance and reduces overfitting specially when the depth and width of fully connected networks are investigated in small datasets.

Stability and task accomplishment of Internet-based teleoperation systems are greatly susceptible to the network latency and uncertainty. Control of a teleoperation system aims to provide satisfactory performance of the remote task and in some cases to provide the operator with sensory feedback. This paper reviews the recent control methodologies used for teleoperation systems with model uncertainty, unknown time-varying delay, and Internet-based communication. The focus is on control algorithms that are suitable for nonlinear uncertain systems to decrease restrictions and increase application scope. The key features of these control algorithms are highlighted, and their advantages and disadvantages are comparatively discussed.

Kinematic and dynamic modelling of UR5 manipulator

Kinematics and dynamics modelling of manipulators are essential for analysis, optimisation, control system design, and motion planning of the manipulators. Deriving these models is a time consuming task and it involves tedious mathematical calculations specifically for manipulators with more than two degrees of freedom. In this paper, development and evaluation of a symbolic modelling tool for the kinematic and dynamic equations of serial manipulators with revolute and prismatic joints are presented. The tool allows a quick access to the full kinematics and dynamics equations of the manipulators. The user only requires to provide the DH parameters for obtaining the kinematic model and the centre of the gravity, mass parameters and momentum of inertia matrices of the links to be able to obtain the dynamic model. The tool is shared for public access and it is aimed to benefit researchers or graduate students in the area of robotics. Evaluation of the models generated by the tool is demonstrated through its accuracy for control design of PUMA 560.