ΕΛ EN
Home | People | Deliparaschos, Kyriakos M.
51
Scholarly Works
29%
OA Ratio
43%
Collaborative Ratio
Scholar

Deliparaschos, Kyriakos M.

Dr

Department of Electrical Engineering, Computer Engineering and Informatics

9
H-index (Scopus)
1227
Scholar Citations

Scholarly Works

Research Output

Recent Publications

Versatile UAV hardware platform for accelerating indoor aerial navigation research – ERRATUM

Kyriakos M. Deliparaschos, Xuefei Huang, Michalis Neofytou, Savvas G. Loizou, Argyrios Zolotas
Publishing year: 2026
Journal article
The Aeronautical Journal, 2026
ORCID

Versatile UAV hardware platform for accelerating indoor aerial navigation research

Deliparaschos K.M., Loizou S.G., Huang X., Neofytou M., Zolotas A.
Publishing year: 2026
Journal article
Aeronautical Journal, 2026, Volume 130, Issue 1348
Scopus
Pages 1859-1883
This study presents a bespoke hardware platform for indoor navigation, featuring a quadrotor equipped with an FZ3 card incorporating the AMD (formerly Xilinx) Zynq UltraScale+ ZU3EG MPSoC as the onboard computer. A core component of this platform is a field programmable gate array (FPGA) module specifically designed to efficiently compute Delaunay triangulations, enabling enhanced spatial awareness and real-time surface reconstruction. The onboard computer communicates with the flight controller, inertial measurement unit (IMU), ultra-wideband (UWB) localisation system, stereo camera, light detection and ranging (LiDAR) and ultrasonic sensors via robotic operating system (ROS) 2. The primary objective is to develop a cost-effective, modular unmanned aerial vehicle (UAV) system that can be adapted for a range of indoor navigation applications. The modular design supports different onboard computer platforms and sensor configurations, allowing researchers to easily customise the system for various experiments. By providing a practical framework for precise indoor navigation, this platform addresses the limitations of simulated, simplified laboratory setups, accelerating prototyping and supporting the deployment of UAVs in complex real-world environments. This work explores the UAV’s hardware architecture, the implementation of the Delaunay triangulation core on the FPGA system-on-chip (SoC), the ROS 2-based communication system and includes a detailed mass analysis and power es...

Lightweight Gated Recurrent Unit Variants for Real-Time Channel Prediction

K Christodoulides, KM Deliparaschos, R Wichman, T Charalambous
Publishing year: 2026
Other
arXiv preprint arXiv:2607.20697, 2026, 2026
Google Scholar

FPGA-Accelerated Onboard Perception for an Indoor Quadrotor UAV

Deliparaschos K.M., Loizou S.G., Neofytou M., Zolotas A.
Publishing year: 2026
Conference paper
IEEE International Conference on Emerging Technologies and Factory Automation ETFA, 2026
Scopus
This paper investigates whether field-programmable gate array (FPGA)-accelerated visual perception can operate onboard a flight-capable unmanned aerial vehicle (UAV) under practical payload and energy constraints. The prototype integrates a Pixhawk 6X flight controller, an H-Flow optical-flow and range sensor, an Intel RealSense D435i camera, and an AMD Kria KR260 mission computer. A You Only Look Once version 3 (YOLOv3) detector executes on a Deep Learning Processing Unit (DPU) implemented in the programmable logic (PL), while the processing system (PS) performs camera acquisition, communication, preprocessing, post-processing, and result logging. Preliminary indoor tests report a 2.115 kg take-off mass, a 29.984 Hz mean image-acquisition rate, and a 4.9 frames/s mean end-to-end perception rate at 424 × 240. The implemented design has an estimated on-chip power of 4.048 W and uses less than 30% of each reported major PL resource category. Flight-time ranges of 9-10 min and 15-16 min were observed with the DPU inference workload active and inactive, respectively. These results demonstrate system-level feasibility for low-speed indoor situational awareness while identifying software-pipeline throughput and direct energy measurement as the main targets for further development.

FPGA Implementation of Zonotopic Estimation for Linear Systems: Algorithmic Structure and Hardware-Oriented Design

Kyriakos Deliparaschos
Publishing year: 2026
Conference paper
MicDAT, 2026
ORCID

A Wearable Lower-Limb Exoskeleton with Sensor-Driven Neuro-Fuzzy Control for Monoplegia Rehabilitation

Deliparaschos K.M., Sagias V.D., Stergiou C., Zacharia P.
Publishing year: 2026
Journal article
Actuators, 2026, Volume 15, Issue 7
Scopus
This study presents the design and development of a wearable lower-limb exoskeleton system aimed at supporting motion assistance in monoplegia-related conditions. The proposed approach integrates a simplified sensing configuration with a data-driven neuro-fuzzy control framework based on an Adaptive Neuro-Fuzzy Inference System (ANFIS). Motion data are acquired from the healthy limb using bend flex sensors and are used to generate control signals for the actuation of the impaired limb through an Arduino-based embedded platform. The mechanical structure is developed using a lightweight 3D-printed design combined with high-torque DC motors and gear transmission mechanisms. Experimental evaluation conducted under controlled conditions demonstrates that the system is capable of capturing and reproducing fundamental motion patterns, with the ANFIS model providing a consistent mapping between sensor inputs and actuator responses. The obtained results indicate a satisfactory level of performance for motion pattern reproduction, particularly in terms of temporal behavior and transition between movement states. The presented system emphasizes low-cost implementation, computational efficiency, and practical implementation, making it suitable as a proof-of-concept framework for wearable assistive technologies. While the results demonstrate the feasibility of the proposed approach for motion reproduction, further studies involving extended testing and user-specific adaptation are require...

51
Unique publications
29.4%
Open access (15 publications; 15 without information)
43.1%
With other institutions (22 publications; 17 without information)

H-Index Reports

Index type Scopus Google Scholar Web of Science
H-index 9 13 1
H5-index 4 4 1
H10-index 6 8 1

Publications per year and source

No description yet.
Faculty
Faculty of Engineering and Technology
Department
Department of Electrical Engineering, Computer Engineering and Informatics
Title
Dr