Recent advancements in the field of Artificial Intelligence (AI) have provided opportunity to create autonomous devices, robots, and machines characterized particularly with the ability to make decisions and perform tasks without human mediation. One of these devices, Unmanned Aerial Vehicles (UAVs) or drones are widely used to perform tasks like surveillance, search and rescue, object detection and target tracking, parcel delivery (recently started by Amazon), and many more. The sensitivity in performing said tasks demands that drones must be efficient and reliable. For this, in this work, an approach to detect and track the target object, moving or still, for a drone is presented. Parrot AR Drone 2 is used for this application. Convolutional Neural Network (CNN) is used for object detection and target tracking. The object detection results show that CNN detects and classifies object with a high level of accuracy (98%). For real-time tracking, tracking algorithm responds faster than conventionally used approaches, efficiently tracking the detected object without losing it from sight. Calculated based on several iterations, the efficiency achieved for target tracking is 96.5%.

Mohammed Rabah, Ali Rohan, Yun-Jong Han, and Sung-Ho Kim. IJFIS 2018;18:204-13. https://doi.org/10.5391/IJFIS.2018.18.3.204

In this work, an advanced drone battery charging system is developed. The system is composed of a drone charging station with multiple power transmitters and a receiver to charge the battery of a drone. A resonance inductive coupling-based wireless power transmission technique is used. With limits of wireless power transmission in inductive coupling, it is necessary that the coupling between a transmitter and receiver be strong for efficient power transmission; however, for a drone, it is normally hard to land it properly on a charging station or a charging device to get maximum coupling for efficient wireless power transmission. Normally, some physical sensors such as ultrasonic sensors and infrared sensors are used to align the transmitter and receiver for proper coupling and wireless power transmission; however, in this system, a novel method based on the hill climbing algorithm is proposed to control the coupling between the transmitter and a receiver without using any physical sensor. The feasibility of the proposed algorithm was checked using MATLAB. A practical test bench was developed for the system and several experiments were conducted under different scenarios. The system is fully automatic and gives 98.8% accuracy (achieved under different test scenarios) for mitigating the poor landing effect. Also, the efficiency η of 85% is achieved for wireless power transmission. The test results show that the proposed drone battery charging system is efficient enough to mitigate the coupling effect caused by the poor landing of the drone, with the possibility to land freely on the charging station without the worry of power transmission loss.