Maneuverable Autonomous Drone for Navigation and Intelligence (MADNI)

Page content

Maneuverable Autonomous Drone for Navigation and Intelligence (MADNI), is an in-house IoT-driven Unmanned Aerial Vehicle (UAV) developed at School of Engineering, Ulster University.

Engineered by Dr. Usman Hadi and his research team, MADNI boasts IoT-driven technology with locally crafted features, including 5G standalone connectivity, obstacle avoidance, object detection, facial recognition and real-time video streaming.

How MADNI works

5G Connectivity Utilizes high-speed 5G connectivity for faster and more reliable communication, enabling seamless data transfer and control over larger distances.

Obstacle Avoidance Enhances safety during flight by autonomously detecting and avoiding obstacles.

Object Detection Provides the capability to identify and track various objects, facilitating applications in surveillance, monitoring, and data collection.

Facial Recognition Enables the drone to recognize and identify individuals, which can be valuable in security and search-and-rescue scenarios.

Real-time Video Streaming Offers live video streaming capabilities, allowing users to remotely monitor and assess situations in real-time.

IoT Integration Incorporates Internet of Things (IoT) technology, enhancing connectivity and enabling the drone to interact with other devices and systems.

Autonomous Navigation Capable of autonomous navigation, reducing the need for constant human intervention and making it suitable for various applications.

Research Outputs

R. Rajathanakodi and M. U. Hadi, "MAD-STORM: Maneuverable Autonomous Drone with Sensing Technologies for Observing Rainfall and Meteorology in Northern Ireland," 2024 35th Irish Signals and Systems Conference (ISSC), Belfast, United Kingdom, 2024, pp. 1-6, doi: 10.1109/ISSC61953.2024.10603132.
C. Rose, R. McMurray and M. U. Hadi, "A Reinforcement Learning Control and Fault Detection Method for the MADNI Drone," 2024 35th Irish Signals and Systems Conference (ISSC), Belfast, United Kingdom, 2024, pp. 1-6, doi: 10.1109/ISSC61953.2024.10602956.
Abbasi, AB, Hadi, MU. Optimizing UAV computation offloading via MEC with deep deterministic policy gradient. Transactions on Emerging Tel Tech. Oct. 2023; e4874. doi: 10.1002/ett.4874
Gibson, J.; Hadi, M.U. Modeling and Optimal Control for Rotary Unmanned Aerial Vehicles in Northern Ireland Climate. Appl. Sci. 2022, 12, 7677. https://doi.org/10.3390/app12157677
Muhammad Usman Hadi, Jack Gibson. Enhancing Rotary Unmanned Aerial Vehicle (RUAV) Stability in Challenging Wind Conditions: A Reinforcement Learning Approach. Intl J Robust Nonlinear. Nov, 2023.