A Path Planning Algorithm for Collective Monitoring Using Autonomous Drones
A Path Planning Algorithm for Collective Monitoring Using Autonomous Drones
复制标题
DOI：
10.1109/ciss.2019.8693023
复制
发表时间：
2019-03
期刊：
影响因子：
--
通讯作者：
Shafkat Islam;Abolfazl Razi
中科院分区：
文献类型：
--
作者：
Shafkat Islam;Abolfazl Razi
提出了一种面向任务的无人机编队路径规划算法。在提出的算法中，每架无人机在避免与固定和移动障碍物碰撞的同时，自主决策找到其飞往指定任务区域的飞行路径。与类似算法的主要区别是每个无人机的目标目的地不是先验固定的，并且无人机对自己进行定位，以便它们共同覆盖潜在的时变任务区域。该算法的一个潜在应用是部署一组自主无人机，共同覆盖不断演变的森林野火，并为消防员提供虚拟现实。我们提出了一种基于强化学习（RL）的新方法来适应相邻位置的连续状态空间。为了考虑更现实的场景，我们评估了定位误差对所提出算法性能的影响。仿真结果表明，当观测误差方差高达100（信噪比为-6dB）时，该算法的成功率约为80%。
This paper presents a novel mission-oriented path planning algorithm for a team of Unmanned Aerial Vehicles (UAVs). In the proposed algorithm, each UAV takes autonomous decisions to find its flight path towards a designated mission area while avoiding collisions to stationary and mobile obstacles. The main distinction with similar algorithms is that the target destination for each UAV is not apriori fixed and the UAVs locate themselves such that they collectively cover a potentially time-varying mission area. One potential application for this algorithm is deploying a team of autonomous drones to collectively cover an evolving forest wildfire and provide virtual reality for fire fighters. We formulated the algorithm based on Reinforcement Learning (RL) with a new method to accommodate continuous state space for adjacent locations. To consider more realistic scenario, we assess the impact of localization errors on the performance of the proposed algorithm. Simulation results show that success probability for this algorithm is about 80% when the observation error variance is as high as 100 (SNR:-6dB).