3D G-learning in UAVs

Abstract

In this paper, we focus on the learning strategy of path planning for Unmanned Aerial Vehicles (UAVs). We propose the G-Learning method to solve the problem of path planning in 3D and optimize the model algorithm. With G-Learning algorithm, the cost matrix can be calculated in real-time and adaptively updated based on the geometric distance and risk information shared with other UAVs. Extensive experimental results validate the effectiveness and feasibility of CGLA for safe navigation of multiple UAVs.