Abdollah Homaifar

This paper presents the development of an integrated and modular agent-based simulation framework designed to simulate the interaction between Urban Air Mobility (UAM) components, such as Provider of Services to UAM (PSU) and UAM aircraft, to provide physically and visually realistic simulations. The simulator is designed by interfacing Robot Operating Systems (ROS) with AgentFly, integrating with an external high fidelity model of lift+cruise UAM aircraft to simulate various types of use cases. Interface methods have been developed to lay the groundwork for incorporating mission planning, decision-making, motion planning, and control algorithms into the framework. The framework enables efficient and scalable operations by supporting inter-agent communication and communication between PSU and individual aircraft. The simulation framework also includes a physics engine that can operate at a high frequency, allowing for real-time simulation while using actual model and terrain data for Atlanta city. This enables complex visualization of multiple aircraft along their flight corridors within a realistic 3D environment. The capability and performance of the developed simulation platform are demonstrated through several use cases involving mission planning, on-the-fly conflict detection and flight re-planning, motion planning in the presence of no-fly zones, and trajectory tracking through hardware-in-the-loop simulations.

Autonomous aerial vehicles (AAVs) are increasingly deployed in both military and civilian missions, generating large volumes of sensitive data at the edge. Centralized processing of this data creates security vulnerabilities, scalability limitations, and single points of failure. Federated learning (FL) mitigates some privacy concerns by keeping raw data local, but it still depends on a central server that is vulnerable to privacy attacks and operational failures. This paper proposes a fully decentralized federated learning framework for dynamic AAV networks based on multi-client functional encryption for inner products (DMCFE-IP). The framework removes the need for a central aggregator and eliminates reliance on a trusted third party (TTP) or Key Distribution Center (KDC) for key management, thereby strengthening both robustness and confidentiality. We employ the Metropolis–Hastings (MH) algorithm to achieve efficient consensus on shared model parameters and integrate Shamir’s Secret Sharing (SSS) to tolerate AAV dropouts without compromising security. Extensive simulations across diverse network topologies and non-identically distributed data show that the proposed framework attains rapid and stable convergence, with model states typically stabilizing within nine iterations per communication round. Moreover, while balanced data partitions facilitate predictable convergence, our results reveal that heterogeneous data distributions can in some cases yield lower root-mean-square error (RMSE) due to increased parameter diversity.

Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations can significantly degrade performance, thereby challenging the overall reliability of the models. Traditional robustness validation typically relies on perturbed test datasets to assess and improve model performance. In our framework, however, we propose a validation approach that extracts “weak robust” samples directly from the training dataset via local robustness analysis. These samples, being the most susceptible to perturbations, serve as an early and sensitive indicator of the model's vulnerabilities. By evaluating models on these challenging training instances, we gain a more nuanced understanding of its robustness, which informs targeted performance enhancement. We demonstrate the effectiveness of our approach on models trained with CIFAR-10, CIFAR-100, and ImageNet, highlighting how robustness validation guided by weak robust samples can drive meaningful improvements in model reliability under adversarial and common corruption scenarios.

In this paper, we introduce an integrated framework for assessing the risk of Urban Air Mobility (UAM) flight operations under wind hazards and enabling decision support using Large-Language Models (LLM) for UAM operators. The framework identifies blocked airspace locations due to non-operable wind speeds in different flight altitude levels of UAM operator's service region capturing dynamic in time blocked regions. Safe and wind-avoiding flight paths are strategically designed for impacted flight scenarios executing safe flight maneuvers. Cost functions such as energy demand and travel time evaluate the performance of the flight trajectories with a specific UAM aircraft model. Additionally, the risk level of flights associated with the energy consumption performance is assessed integrating battery degradation model due to ageing using aircraft charge cycles and reserve energy regulatory requirement. To support decision making efficiency of the UAM operator, a methodology for providing flight recommendations using LLM is integrated based on flight conditions, performance, and safety assessment information. The effectiveness of the proposed framework is demonstrated by considering flight scenarios in the Dallas-Fort Worth Metropolitan area with stopped-rotor and tilt-rotor UAM aircraft. Results show the blocked airspace for UAM flights, flight trajectories with safe aircraft maneuvers, and the evaluation of risk levels for the flights. Furthermore, contextually relevant recommendations provided by LLM for flight decision making addresses UAM operator's mission planning complexity. The framework enhances planning and airspace access efficiency while maintaining safety.

The integration of Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) is increasingly central to the development of intelligent autonomous systems for applications such as search and rescue, environmental monitoring, and logistics. However, precise coordination between these platforms in real-time scenarios presents major challenges, particularly when external localization infrastructure such as GPS or GNSS is unavailable or degraded [1]. This paper proposes a vision-based, data-driven framework for real-time UAV-UGV integration, with a focus on robust UGV detection and heading angle prediction for navigation and coordination. The system employs a fine-tuned YOLOv5 model to detect UGVs and extract bounding box features, which are then used by a lightweight artificial neural network (ANN) to estimate the UAV's required heading angle. A VICON motion capture system was used to generate ground-truth data during training, resulting in a dataset of over 13,000 annotated images collected in a controlled lab environment. The trained ANN achieves a mean absolute error of 0.1506° and a root mean squared error of 0.1957°, offering accurate heading angle predictions using only monocular camera inputs. Experimental evaluations achieve 95% accuracy in UGV detection. This work contributes a vision-based, infrastructure- independent solution that demonstrates strong potential for deployment in GPS/GNSS-denied environments, supporting reliable multi-agent coordination under realistic dynamic conditions. A demonstration video showcasing the system's real-time performance, including UGV detection, heading angle prediction, and UAV alignment under dynamic conditions, is available at: https://github.com/Kooroshraf/UAV-UGV-Integration

Adversarial robustness remains a critical challenge in deploying neural network classifiers, particularly in real-time systems where ground-truth labels are unavailable during inference. This paper investigates \textit{Volatility in Certainty} (VC), a recently proposed, label-free metric that quantifies irregularities in model confidence by measuring the dispersion of sorted softmax outputs. Specifically, VC is defined as the average squared log-ratio of adjacent certainty values, capturing local fluctuations in model output smoothness. We evaluate VC as a proxy for classification accuracy and as an indicator of adversarial drift. Experiments are conducted on artificial neural networks (ANNs) and convolutional neural networks (CNNs) trained on MNIST, as well as a regularized VGG-like model trained on CIFAR-10. Adversarial examples are generated using the Fast Gradient Sign Method (FGSM) across varying perturbation magnitudes. In addition, mixed test sets are created by gradually introducing adversarial contamination to assess VC's sensitivity under incremental distribution shifts. Our results reveal a strong negative correlation between classification accuracy and log(VC) (correlation rho < -0.90 in most cases), suggesting that VC effectively reflects performance degradation without requiring labeled data. These findings position VC as a scalable, architecture-agnostic, and real-time performance metric suitable for early-warning systems in safety-critical applications.

In this paper, we propose a conflict-free multi- agent flight scheduling that ensures robust separation in con- strained 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.

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.

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 98.621%, 99.960.1%, 99.880.1%, and 98.380.1%, respectively. This work provides a substantial advancement in enhancing the security and safety of AVs against GPS spoofing threats.