UAV Obstacle Avoidance Algorithm to Navigate in Dynamic Building Environments

In this work, a real-time collision avoidance algorithm was presented for autonomous navigation in the presence of fixed and moving obstacles building environments. The current implementation is designed between waypoints predefined flight trajectory that would be performed by an UAV during tasks such as inspections or construction progress monitoring. It uses simplified geometry generated from point cloud scenario. addition, it also employs information 3D sensors to detect position people other UAVs, which are not registered original cloud. If obstacle detected, estimates its motion computes evasion path considering environment. method has been successfully tested different scenarios, offering robust results all maneuvers. Execution times were measured, demonstrating computationally feasible implemented onboard UAV.