基于高基尼不纯度的UAV&UGV协作监测系统路径规划

空地异构机器人系统由无人机和地面车组成,通过两者相互协作完成持续监测任务可以提高工作效率、解决无人机续航能力不足的问题.在该异构机器人系统中,地面车可以为无人机进行补能,保证监测任务的持续性.由于周期性的监测路径极易发生监测规律信息的泄露,提高无人机监测路径的随机性具有重要意义.针对此问题,引入基尼不纯度指标来评估监测路径的随机性,以目标点的归一化访问间隔时间及其基尼不纯度的加权之和最小为优化目标,建立无人机和地面车协作系统持续监测路径规划模型,提升监测路径的隐私性.采用蚁群算法对无人机监测路径和地面车补能路径进行优化求解,验证了模型的有效性与合理性.通过与其他算法比较,说明了蚁群算法具有更快的搜索速度和运行效率.

Path planning of unmanned aerial vehicle & unmanned ground vehicle collaborative monitoring system based on high Gini impurity

A heterogeneous robot system is composed of an unmanned aerial vehicle(UAV) and an unmanned ground vehicle(UGV). By cooperating with each other to complete continuous monitoring tasks, the work efficiency can be improved and the problem of insufficient endurance capacity of the UAV can be solved. In this heterogeneous robot system, the UGV can recharge energy for the UAV to ensure the continuity of the monitoring task. Since periodic monitoring paths are prone to leakage of monitoring regularity information, it is significant to improve the randomness of the UAV''s monitoring path. Aiming at this problem, this paper introduces the Gini impurity index to evaluate the randomness of the monitoring path. With the optimization goal of minimizing the weighted sum of normalized visit interval time of target nodes and their Gini impurity, a continuous monitoring path planning model of the UAV&UGV cooperative system is established,which improves the privacy of monitoring path. Finally, the ant colony algorithm is used to optimize the UAV''s monitoring path and the UGV''s energy supply path, which verifies the validity and rationality of the model. Compared with other algorithms, it is proved that the ant colony algorithm has faster search speed and operation efficiency.