As a research hotspot in the UAV field, autonomous obstacle avoidance of UAVs in the unknown environment plays an important role in geographical reconnaissance, map drawing, field rescue, and other aspects. This paper designs an autonomous obstacle avoidance algorithm for UAVs based on obstacle contour detection. By analyzing the image features of unknown obstacles, the algorithm outputs the location coordinates and contour of obstacles in real-time. In this process, by reducing the time complexity of smooth filtering, the computational efficiency is improved. Meanwhile, converting the image to HSV color space effectively avoids the influence of light intensity, and the Otus threshold segmentation method is introduced to improve the real-time performance of the algorithm. The method is combined with the D* path search algorithm to realize autonomous obstacle avoidance of UAVs in an unknown environment. The algorithm is simulated in the Airsim environment, and compared with the existing obstacle avoidance methods, the effectiveness of the algorithm is verified.
Autonomous Obstacle Avoidance Algorithm for UAVs Based on Obstacle Contour Detection
Lect. Notes Electrical Eng.
International Conference on Guidance, Navigation and Control ; 2022 ; Harbin, China August 05, 2022 - August 07, 2022
2023-01-31
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Vision-Based Obstacle Avoidance for UAVs
AIAA | 2007
|Obstacle Avoidance Manager for UAVs Swarm*
IEEE | 2020
|Reactive obstacle avoidance for Rotorcraft UAVs
Tema Archiv | 2011
|British Library Conference Proceedings | 2011
|