Autonomous obstacle avoidance for UAVs in complex environments is crucial, single sensors have limitations, and multi-source sensor fusion technology has received attention. Based on the above problems, this paper summarizes the research on autonomous obstacle avoidance algorithms for UAVs in complex environments based on multi- source sensor fusion in recent years. Firstly, the classification and basic principles of multi-source sensor fusion algorithms at the data layer, feature layer and decision layer are sorted out, and the characteristics of commonly used sensors such as LiDAR and vision sensors are elaborated, as well as the basic algorithm of autonomous obstacle avoidance. Secondly, the application examples of different fusion level algorithms in UAV obstacle avoidance are analyzed, such as the data layer and feature layer fusion practice of Dashuai Wang’s team, the improvement of Bayesian algorithm to achieve multi-level fusion of Honglei Zhang’s team, etc., and a variety of innovative obstacle avoidance algorithms are also introduced. Finally, the performance of various algorithms is compared and evaluated, the challenges faced by the current research are analyzed, and the future development trend is looked forward to, so as to provide a comprehensive reference for the research in this field.
Li Fan (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: