A Two-level Memetic Path Planning Algorithm for Unmanned Air/Ground Vehicle Cooperative Detection Systems

The Unmanned Air/Ground Vehicle (UAV/UGV) cooperative detection systems are widely used in terrain reconnaissance, disaster rescue and urban/rural buildings survey, in which the UAV in the air can provide a broad view and take photography, while the UGV on the ground can offer sufficient load capacity and serve as repeater stations as well. The path planning of UAV/UGV is one of the most important issues in the cooperative detection system, and its studies have attracted great attentions in recent years. In this study, a two-level memetic path planning algorithm is proposed to help the unmanned air/ground vehicle cooperative systems detect realistic urban illegal building, considering the limits of the endurance capacity of the UAV, the load capacity of the UGV, and the communication restrictions between them. Experiments on both the synthetic data and the realistic urban illegal building data show the effectiveness of the proposed algorithm on solving the path planning problem in the UAV/UGV cooperative system for urban illegal building detection tasks.