Lorant Andras Szolga

Smart city traffic systems increasingly rely on edge intelligence and distributed learning to coordinate vehicles and infrastructure. However, many existing approaches prioritize system-level optimization while overlooking how humans perceive, interpret, and respond to automated decisions, limiting efficiency and real-world adoption. This paper proposes a human-centric edge intelligence framework that integrates federated reinforcement learning (FRL) with interpretable human–machine interfaces for urban traffic coordination. Vehicles and signalized intersections operate as decentralized learning agents, collaboratively optimizing traffic flow while retaining data locally. Human-centered constraints are embedded directly into the learning process through reward design and action-space restrictions, ensuring that system decisions can be expressed as clear, actionable guidance via augmented reality head-up displays and voice prompts. We present a layered edge architecture and a smart-intersection scenario to demonstrate how sensing, learning, communication, and human interaction are jointly coordinated. A simulation-based evaluation pipeline using SUMO and CARLA is introduced to examine corridor-level traffic dynamics, visual perception scenarios, and human-facing advisory interactions. SUMO is used for microscopic traffic-flow and signal-control modeling, while CARLA supports visual validation of safety-critical events and interface-level driver advisories. A dedicated SUMO–CARLA workflow diagram is provided to clarify how traffic-state generation, FRL decision-making, visual scenario reconstruction, and HMI advisory evaluation are connected. To ground the design in real-world evidence, we additionally report a descriptive trajectory analysis of the public NGSIM Peachtree Street dataset; this analysis characterizes speed, acceleration, and following-headway behavior and motivates the proposed reward and advisory-trigger design, but it is a descriptive/motivational analysis of existing trajectory data rather than an evaluation of the proposed FRL framework. This paper is explicitly positioned as a conceptual and methodological framework contribution: no FRL policy has been trained, no SUMO–CARLA simulation has been executed, and no quantitative comparison or ablation results are reported. These experiments constitute the planned next phase of this research program. Because the framework is part of an ongoing security-sensitive smart-city research effort, deployment-specific control interfaces and protected configuration details are reported at an abstracted level, while the non-sensitive simulation structure, evaluation metrics, and agent-level learning process are described for reproducibility. The proposed framework provides a practical pathway for evaluating intelligent mobility systems that balance decentralized optimization, privacy preservation, interpretability, scalability, and human-aligned operation.

The design and the fabrication procedures for the access to flexible, light, and transparent heterojunction and homojunction Single-Material Organic Solar Cells (SMOSCs) in direct ITO/MoO ₃ /SM/Bphen/Al and inverse ITO/ZnO/SM/MoO ₃ /Al architectures using PET/ITO support/electrodes and single-component active materials (SMs) are described. The optoelectronic and photovoltaic parameters of the cells on flexible PET/ITO support/electrodes were compared to the data collected for similar cells developed on rigid glass/ITO substrates.

Adverse climate events have recently highlighted an increasing need to deploy sustainable energetic infrastructures. The existing electric conversion circuits for solar energy provide high efficiency; however, gaps in sustainability and robustness can be identified by considering their operation during intense perturbations, potentially occurring for interplanetary energy transfer. Additionally, charging characteristics for energy storage units influence differently the operation life of battery arrays, with increased stability providing favorable operating conditions. Therefore, the present study develops an alternative controller for managing solar energy as well as a prototype for tracking the maximum power point, both constrained by robustness and renewability studies. For the presented design, stability analyses and simulations validated the management of electric energy from solar panels and the developed configuration resulted in improving current peak integral transient characteristics by using an alternative control method, demonstrating stability for an indefinite number of energy storage units. Furthermore, the estimation for VLSI (Very-Large-Scale Integration) of this constrained design has been concluded to potentially provide a solution with adequate performance, comparable to state-of-the-art computational circuits. However, certain limitations could arise when substituting the main computation parts with analyzed solutions and proceeding with integration-based manufacturing.

Recent climate events have highlighted an increasing need for developing sustainable energetic infrastructures. Mainly, the evolution of existing industrial domains toward sustainability would involve major changes in energy management. As a consequence, research studies have analyzed various possibilities for extending sustainability, with space-based energy applications garnering increased interest as a potential solution to provide the necessary sustainable energy for existing industries. Therefore, this study researched the development of a reduced-complexity orbital ephemerides set to demonstrate the increase in heuristic optimization agent density. Additionally, the required translations were studied and applied to place a hypothetical charging station as a target on planet Earth while considering real-scale interplanetary measurements during studies and simulations. Furthermore, the rocket thruster control analysis validated the consistency of this hypothetical methodology by proving the potential of using simplified ephemerides in coarse optimization, therefore reducing optimization resources. Thus, the results of this study indicate the consistency of this hypothetical optimization process, as evidenced by the similarity between command and error signal outputs. By such means, this improves the probability of finding a global optimum, potentially providing improvements in various aerospace domains in the scenario of orbital calibration optimization. Several future directions were discussed for applying the main concept to real-world operations to assess its actual applicability.

This study proposes an intelligent patrol planning framework that leverages reinforcement learning, spatiotemporal crime forecasting, and simulated sensor telemetry to optimize autonomous vehicle (AV) navigation in urban environments. Crime incidents from Washington DC (2024–2025) and Seattle (2008–2024) are modeled as a dynamic spatiotemporal graph, capturing the evolving intensity and distribution of criminal activity across neighborhoods and time windows. The agent’s state space incorporates synthetic AV sensor inputs—including fuel level, visual anomaly detection, and threat signals—to reflect real-world operational constraints. We evaluate and compare three learning strategies: Deep Q-Network (DQN), Double Deep Q-Network (DDQN), and Proximal Policy Optimization (PPO). Experimental results show that DDQN outperforms DQN in convergence speed and reward accumulation, while PPO demonstrates greater adaptability in sensor-rich, high-noise conditions. Real-map simulations and hourly risk heatmaps validate the effectiveness of our approach, highlighting its potential to inform scalable, data-driven patrol strategies in next-generation smart cities.

A new drone-based image processing technique for item and human detection is presented in this work. Unlike previous methods that relied on a steady network connection for optimal results, a Raspberry Pi 4 module was installed on the drone for local processing and detection. In the first investigation, a lightweight drone was constructed using some of the most advanced racing components, specifically chosen to meet particular needs. Convolutional neural networks and TensorFlow Lite were used in the second stage to develop a computationally efficient detection method on the Raspberry Pi. Multiple objects in a single image might be detected in a single algorithm iteration thanks to the chosen algorithm, Single Shot Detection (SSD). To securely mount the drone’s battery, Raspberry Pi module, and additional battery, a container was created and 3D printed.