Akademik Veri Yönetim Sistemi
JOURNAL OF POLYTECHNIC-POLITEKNIK DERGISI, 2024 (ESCI)
The use of autonomous unmanned aerial vehicles (UAVs) has become one of the most used in many sectors in the last few years. This growing reliance on UAVs necessitates advanced navigation systems to ensure their safe and efficient operation, particularly in environments dense with both static and dynamic objects. Collision avoidance is a fundamental requirement in such scenarios. This study introduces a novel collision avoidance system for an UAV that incorporates the use of LiDAR for the identification of stationary and an optical flow (OF) for the identification of dynamic obstructions in their path. By fusing LiDAR's high-resolution spatial data with the relative motion detection capability of the OF, proposed system enables detection and avoidance of both static and dynamic objects on-the-fly. To evaluate the efficacy of the proposed system, various simulation and experiment were conducted. The results indicate that the system successfully avoids either stationary or dynamic obstacles.