In this work, a real-time collision avoidance algorithm was presented for autonomous navigation in the presence of fixed and moving obstacles in building environments. The current implementation is designed for autonomous navigation between waypoints of a predefined flight trajectory that would be performed by an UAV during tasks such as inspections or construction progress monitoring. It uses a simplified geometry generated from a point cloud of the scenario. In addition, it also employs information from 3D sensors to detect and position obstacles such as people or other UAVs, which are not registered in the original cloud. If an obstacle is detected, the algorithm estimates its motion and computes an evasion path considering the geometry of the environment. The method has been successfully tested in different scenarios, offering robust results in all avoidance maneuvers. Execution times were measured, demonstrating that the algorithm is computationally feasible to be implemented onboard an UAV.
UAV Obstacle Avoidance Algorithm to Navigate in Dynamic Building Environments
2022
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
Metadata by DOAJ is licensed under CC BY-SA 1.0
UAV obstacle avoidance algorithm to navigate in dynamic building environments
BASE | 2022
|UAV obstacle avoidance algorithm to navigate in dynamic building environments
BASE | 2022
|Towards Safer Obstacle Avoidance for Continuum-Style Manipulator in Dynamic Environments
BASE | 2016
|Dynamic map for obstacle avoidance
IEEE | 2003
|Dynamic Map for Obstacle Avoidance
British Library Conference Proceedings | 2003
|