摘要
针对物流无人机在城市低空复杂环境和高密度动态交通流下的避障决策问题,提出一种动态三维避障算法。首先对城市低空环境建模并将无人机的动态避障问题表达为马尔可夫决策过程,通过在动作集中加入高度变化等飞行动作,将避障算法可行解的范围拓展到三维空间中。其次改进了奖励估值函数,使算法能够在绕飞以及爬升越障中通过蒙特卡罗树搜索权衡最优避障策略。仿真表明该算法能够选择最优策略,缩短24.4%的飞行时间并减少33.2%的飞行距离。最后考虑到无人机感知系统容易因建筑物遮挡受限而造成对环境状态观测不完全,对算法鲁棒性做出了验证,其结果表明随着感知范围缩短,算法仍能求得可行解。
Aiming at the collision avoidance problem of logistics unmanned aerial vehicle in the complexurban low-altitude environment and high-density dynamic traffic flow,a dynamic three-dimensional(3D)collisionavoidance algorithm is proposed.Firstly,we model the urban low altitude operating environment,express thedynamic collision avoidance problem of unmanned aerial vehicle as a Markov decision process,and expand thefeasible solution range of algorithm to the 3D space by adding the altitude change and other manoeuvre into theaction set of collision avoidance.Secondly,we improve the reward valuation function,so that the algorithm canbalance the optimal decision by Monte Carlo tree search in two-dimensional plane flying around and 3D spaceobstacle crossing.Finally,the global optimal solution is gradually obtained by approaching the single optimalfeasible solution.The simulation results show that the algorithm can optimize the collision avoidance action,andchoose the best collision avoidance strategy in flying around and crossing obstacles to shorten the flight time by24.4%and reduce the flight distance by 33.2%.For the unmanned aerial vehicle operating in the urban low-altitudeenvironment,its sense system is easy to be partially observable due to the limited building occlusion,and thealgorithm cannot obtain sufficient environmental state information input for solution calculation,so the algorithmrequires robustness.The simulation results show that with the shortening of sense radius,the algorithm has goodperformance and can still give most of the feasible solutions under the limited conditions of the unmanned aerialvehicle sense system.
作者
李安醍
李诚龙
郑远
LI Anti;LI Chengong;ZHENG Yuan(Xinjin Flight College,Civil Aviation Flight University of China,Chengdu 611431,China;College of Air Traffic Management,Civil Aviation Flight University of China,Guanghan 618307,China;School of Electronic Information Engineering,Beihang University,Beijing 100191,China;College of Computer Science and Technology,Civil Aviation Flight University of China,Guanghan 618307,China)
出处
《电子科技大学学报》
北大核心
2025年第2期257-265,共9页
Journal of University of Electronic Science and Technology of China
基金
国家自然科学基金民航联合基金重点项目(U2333214)
四川省自然科学基金(2023NSFSC0903)
中央高校基本科研业务费专项资金(J2023-079)
民航局安全能力建设项目(MHAQ2024033)。
关键词
无人机
航空安全
避障算法
马尔可夫决策过程
鲁棒性
unmanned aerial vehicle
aviation safety
collision avoidance algorithm
Markov decisionprocess
robustness
