基于DMOEA-APTC算法的无人机在线航迹规划

doi:10.16182/j.issn1004731x.joss.23-0615

摘要/Abstract

摘要：

为了解决具有时间关联性质的动态多目标优化问题，以无人机在线航迹规划问题为基础，引入时间关联特征概念并建立无人机时间关联动态多目标优化问题模型，提出一种使用自适应预测响应机制和时间关联性优化机制的动态多目标双层优化算法。根据环境变化相关性判断环境变化强弱并启用不同响应机制，快速适应环境变化；优化过程中通过最小二乘法学习历史数据拟合航迹未来预测值，根据预测可靠性自适应选择“仅优化当前”或“同时优化当前与未来”优化模式；使用改进后的切比雪夫分解法对符合偏好的航迹进行决策。实验结果表明：所提算法在复杂飞行环境下降低飞行时长的同时具有更高生存概率，提高了无人机飞行稳定性，更合理有效地处理了在线航迹规划问题。

关键词: 无人机, 在线航迹规划, 时间关联特征, 动态多目标优化算法, 预测策略, 动态威胁

Abstract:

In order to solve the dynamic multi-objective optimization problem with time correlation, this paper introduces the concept of time correlation feature and establishes the model of UAV time-correlation dynamic multi-objective optimization problem moedl on the basis of UAV online track planning problem, and proposes a dynamic multi-objective double-layer optimization algorithm using adaptive predictive response mechanism and time-correlation optimization mechanism (DMOEA-APTC). The intensity of environmental change was judged according to the correlation of environmental change and different response mechanisms were used to quickly adapt to environmental change. In the optimization process, the least square method was used to learn the historical data to fit the future predicted value of the flight path, and the optimization mode of "only optimize the current" or "optimize the current and future at the same time" was adaptively selected according to the reliability of the prediction. The improved Chebyshev decomposition method was used to make the decision of the preferred flight path. The experimental results show that the proposed algorithm can reduce the flight duration and have higher survival probability in complex flight environments, improve the flight stability of the UAV, and deal with the online flight path planning more reasonably and effectively.

Key words: UAV, online track planning, time correlation characteristics, dynamic multi-objective optimization algorithm, prediction strategy, dynamic threat

中图分类号:

TP273

李二超,张生辉 . 基于DMOEA-APTC算法的无人机在线航迹规划[J]. 系统仿真学报, 2024, 36(9): 2086-2099.

Li Erchao,Zhang Shenghui . UAV Online Track Planning Based on DMOEA-APTC Algorithm[J]. Journal of System Simulation, 2024, 36(9): 2086-2099.

图/表 19

图1

图2

图3

图4

图5

表1

威胁源参数

威胁	$μ x$	$μ y$	$σ x$	$σ y$
K1	-30	10	3.0	3.0
K2	5	0	3.0	3.0
K3	20	-10	3.0	3.0
K4	25	-5	3.0	3.0
K5	30	0	2.7	2.7
K6	30	-40	3.0	3.0
K7	-10	40	3.0	3.0
K8	-20	-30	2.7	2.7
K9	0	-30	2.1	2.1
K10	-14	-10	2.4	2.4
K11	-10	20	3.0	3.0
K12	10	30	2.1	2.1
K13	-30	-10	3.3	3.3
K14	-30	40	3.9	3.9
K15	20	20	4.5	4.5
K16	10	-20	4.5	4.5
K17	30	40	3.0	3.0

表1

图6

图7

图8

表2

静态威胁情况下规划结果

偏好设置	规划方法	飞行时间/s	生存概率	航向角平均变化值/(°)
$(ω 1, ω 2) Τ = (0.7,0.3) Τ$	DMOEA-APTC	171	0.931 68	9.667 7
$(ω 1, ω 2) Τ = (0.7,0.3) Τ$	DNSGA-II	175	0.907 86	11.457 4
$(ω 1, ω 2) Τ = (0.3,0.7) Τ$	DMOEA-APTC	165	0.876 83	5.309 0
$(ω 1, ω 2) Τ = (0.3,0.7) Τ$	DNSGA-II	168	0.850 36	8.586 5

表2

图9

图10

表3

突发威胁情况下规划结果

偏好设置	规划方法	飞行时间/ s	生存概率	航向角平均变化值/(°)
$(ω 1, ω 2) Τ = (0.7,0.3) Τ$	DMOEA-APTC	306	0.953 26	12.943 7
$(ω 1, ω 2) Τ = (0.7,0.3) Τ$	DNSGA-II	312	0.957 49	14.849 7
$(ω 1, ω 2) Τ = (0.3,0.7) Τ$	DMOEA-APTC	297	0.812 97	8.558 2
$(ω 1, ω 2) Τ = (0.3,0.7) Τ$	DNSGA-II	306	0.850 36	11.978 3

表3

图11

图12

表4

突变威胁情况下规划结果

偏好设置	规划方法	飞行时间/s	生存概率	航向角平均变化值/(°)
$(ω 1, ω 2) Τ = (0.7,0.3) Τ$	DMOEA-APTC	438	0.916 01	11.887 3
$(ω 1, ω 2) Τ = (0.7,0.3) Τ$	DNSGA-II	447	0.892 31	14.160 6
$(ω 1, ω 2) Τ = (0.3,0.7) Τ$	DMOEA-APTC	429	0.844 18	8.930 3
$(ω 1, ω 2) Τ = (0.3,0.7) Τ$	DNSGA-II	432	0.810 41	11.247 6

表4

图13

图14

表5

偏好改变情况下规划结果

偏好设置	规划方法	飞行时间/s	生存概率	航向角平均变化值/(°)
$(0.7,0.3) Τ → (0.3,0.7) Τ$	DMOEA-APTC	435	0.884 95	11.036 7
$(0.7,0.3) Τ → (0.3,0.7) Τ$	DNSGA-II	441	0.875 93	13.085 1

表5

参考文献 31

1	卢新来, 杜子亮, 许赟. 航空人工智能概念与应用发展综述[J]. 航空学报, 2021, 42(4): 245-258.
	Lu Xinlai, Du Ziliang, Xu Yun. Review on Basic Concept and Applications for Artificial Intelligence in Aviation[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 245-258.
2	杨伟. 关于未来战斗机发展的若干讨论[J]. 航空学报, 2020, 41(6): 1-12.
	Yang Wei. Some Discussions on the Development of Future Fighters[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(6): 1-12.
3	Harker T W, Gilday M M, Berger D H. Department of Navy Unmanned Campaign Framework[EB/OL]. [2021-03-16]. .
4	雷宏杰, 姚呈康. 面向军事应用的航空人工智能技术架构研究[J]. 导航定位与授时, 2020, 7(1): 1-11.
	Lei Hongjie, Yao Chengkang. Technical Architecture of Aviation Artificial Intelligence for Military Application[J]. Navigation Positioning and Timing, 2020, 7(1): 1-11.
5	Aggarwal Shubhani, Kumar Neeraj. Path Planning Techniques for Unmanned Aerial Vehicles: A Review, Solutions, and Challenges[J]. Computer Communications, 2020, 149: 270-299.
6	Shahid Noor, Abrar Muhammad, Ajmal Ushna, et al. Path Planning in Unmanned Aerial Vehicles: An Optimistic Overview[J]. International Journal of Communication Systems, 2022, 35(6): e5090.
7	李波, 屈原, 徐静. 复杂动态环境下基于DMPC-PSO 的多无人机在线航迹规划[J]. 内蒙古师范大学学报(自然科学汉文版), 2018, 47(6): 491-498.
	Li Bo, Qu Yuan, Xu Jing. DMPC-PSO Based on Multiple Unmanned Aerial Vehicles Real-time Route Planning in Complex Dynamic Environment[J]. Journal of Inner Mongolia Normal University(Natural Science Edition), 2018, 47(6): 491-498.
8	陈都, 孟秀云. 基于改进ARA^*算法的无人机在线航迹规划[J]. 飞行力学, 2021, 39(1): 60-65.
	Chen Dou, Meng Xiuyun. UAV Online Path Planning Based on Improved ARA^*Algorithm[J]. Flight Dynamics, 2021, 39(1): 60-65.
9	Li Keyu, Lu Yonggen, Zhang Yanchi. Dynamic Obstacle Avoidance Path Planning of UAV Based on Improved APF[C]//2020 5th International Conference on Communication, Image and Signal Processing (CCISP). Piscataway, NJ, USA: IEEE, 2020: 159-163.
10	Liu Wei, Hao Peng, Zheng Zheng, et al. FBCRI Based Real-time Path Planning for Unmanned Aerial Vehicles in Unknown Environments with Uncertainty[J]. 机器人, 2013, 35(6): 641-650.
11	Margraff Julien, Stéphant Joanny, Labbani-Igbida Ouiddad. UAV 3D Path and Motion Planning in Unknown Dynamic Environments[C]//2020 International Conference on Unmanned Aircraft Systems (ICUAS). Piscataway, NJ, USA: IEEE, 2020: 77-84.
12	彭星光, 徐德民, 高晓光. 基于Pareto解集关联与预测的动态多目标进化算法[J]. 控制与决策, 2011, 26(4): 615-618.
	Peng Xingguang, Xu Demin, Gao Xiaoguang. A Dynamic Multi-objective Evolutionary Algorithm Based on Pareto Set Linkage and Prediction[J]. Control and Decision, 2011, 26(4): 615-618.
13	唐嘉钰, 李相民, 代进进. 基于威胁建模的UCAV武器投放在线航迹规划[J]. 西北工业大学学报, 2021, 39(2): 382-391.
	Tang Jiayu, Li Xiangmin, Dai Jinjin. Online Trajectory Planning for UCAV Performing Ground Attacks Based on Threat Modeling[J]. Journal of Northwestern Polytechnical University, 2021, 39(2): 382-391.
14	汪瀚洋, 陈亮, 徐海, 等. 基于MOEA/D-ARMS的无人机在线航迹规划[J]. 系统工程与电子技术, 2022, 44(11): 3505-3514.
	Wang Hanyang, Chen Liang, Xu Hai, et al. UAV Online Trajectory Planning Based on MOEA/D-ARMS[J]. Systems Engineering and Electronics, 2022, 44(11): 3505-3514.
15	任智, 张栋, 唐硕. 基于强化学习的改进三维A^*算法在线航迹规划[J]. 系统工程与电子技术, 2023, 45(1): 193-201.
	Ren Zhi, Zhang Dong, Tang Shuo. Improved Three-dimensional A^* Algorithm of Real-time Path Planning Based on Reinforcement Learning[J]. Systems Engineering and Electronics, 2023, 45(1): 193-201.
16	池海红, 周明鑫. 融合强化学习和进化算法的高超声速飞行器航迹规划[J]. 控制理论与应用, 2022, 39(5): 847-856.
	Chi Haihong, Zhou Mingxin. Trajectory Planning for Hypersonic Vehicle Combined with Reinforcement Learning and Evolutionary Algorithms[J]. Control Theory & Applications, 2022, 39(5): 847-856.
17	Deb Kalyanmoy, Udaya Bhaskara Rao N, Karthik S. Dynamic Multi-objective Optimization and Decision-making Using Modified NSGA-II: A Case Study on Hydro-thermal Power Scheduling[C]//Evolutionary Multi-Criterion Optimization. Berlin, Heidelberg: Springer Berlin Heidelberg, 2007: 803-817.
18	Li Yibing, Zhang Sitong, Ye Fang, et al. A UAV Path Planning Method Based on Deep Reinforcement Learning[C]//2020 IEEE USNC-CNC-URSI North American Radio Science Meeting (Joint with AP-S Symposium). Piscataway, NJ, USA: IEEE, 2020: 93-94.
19	Liu Shengwei, Ma Yue. Research for Bidirectional Path Planning Based on An Improved A^* Algorithm[C]//2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications(AEECA). Piscataway: IEEE, 2020: 1036-1039.
20	Chen Haiyang, Ji Yebiao, Niu Longhui. Reinforcement Learning Path Planning Algorithm Based on Obstacle Area Expansion Strategy[J]. Intelligent Service Robotics, 2020, 13(2): 289-297.
21	Li Bohao, Wu Yunjie. Path Planning for UAV Ground Target Tracking Via Deep Reinforcement Learning[J]. IEEE Access, 2020, 8: 29064-29074.
22	Dogan A. Probabilistic Path Planning for UAVs[C]//2nd AIAA "Unmanned Unlimited" Conf. and Workshop & Exhibit. Reston, VA, USA: AIAA, 2003: AIAA 2003-6552.
23	Roberge V, Tarbouchi M, Labonté Gilles. Fast Genetic Algorithm Path Planner for Fixed-wing Military UAV Using GPU[J]. IEEE Transactions on Aerospace and Electronic Systems, 2018, 54(5): 2105-2117.
24	Song Qi, Zhao Qinglei, Wang Shuxin, et al. Dynamic Path Planning for Unmanned Vehicles Based on Fuzzy Logic and Improved Ant Colony Optimization[J]. IEEE Access, 2020, 8: 62107-62115.
25	Wu Xiaojing, Xu Lei, Zhen Ran, et al. Biased Sampling Potentially Guided Intelligent Bidirectional RRT^∗ Algorithm for UAV Path Planning in 3D Environment[J]. Mathematical Problems in Engineering, 2019, 2019: 5157403.
26	Ma Xiaoliang, Zhang Qingfu, Tian Guangdong, et al. On Tchebycheff Decomposition Approaches for Multiobjective Evolutionary Optimization[J]. IEEE Transactions on Evolutionary Computation, 2018, 22(2): 226-244.
27	何春雄, 龙卫江, 朱锋峰. 概率论与数理统计[M]. 北京: 高等教育出版社, 2012: 79-80.
28	彭星光. 面向无人系统的动态进化算法及应用[M]. 北京: 科学出版社, 2017: 87-104.
29	Xu Biao, Zhang Yong, Gong Dunwei, et al. Environment Sensitivity-based Cooperative Co-evolutionary Algorithms for Dynamic Multi-objective Optimization[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2018, 15(6): 1877-1890.
30	Goh C K, Tan K C. A Coevolutionary Paradigm for Dynamic Multi-objective Optimization[M]//Goh C K, Tan K C. Evolutionary Multi-objective Optimization in Uncertain Environments: Issues and Algorithms. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009: 153-185.
31	Deb K, Thiele L, Laumanns M, et al. Scalable Test Problems for Evolutionary Multiobjective Optimization[M]//Abraham A, Jain L, Goldberg R. Evolutionary Multiobjective Optimization: Theoretical Advances and Applications. London: Springer London, 2005: 105-145.

[1]	刘斌, 兰莹, 黄文焘, 范勤勤. 融合动态窗口法的无人机动态路径规划算法[J]. 系统仿真学报, 2024, 36(8): 1843-1853.
[2]	黄志锋, 刘媛华. 基于改进哈里斯鹰和B-spline曲线的无人机路径规划研究[J]. 系统仿真学报, 2024, 36(7): 1509-1524.
[3]	王涛, 吉晓东. 混合概率信道下的全双工无人机中继轨迹优化[J]. 系统仿真学报, 2024, 36(6): 1369-1377.
[4]	高超, 黄郑, 赵轩, 王红星, 龙涛. 基于构型优选的5G集群无人机协同导航方法[J]. 系统仿真学报, 2024, 36(4): 981-990.
[5]	余翔, 邓千锐, 段思睿, 姜陈. 一种多无人机协同优先覆盖搜索算法[J]. 系统仿真学报, 2024, 36(4): 991-1000.
[6]	桂雪琪, 李春涛. 基于视野和速度引导的无人机集群避障算法[J]. 系统仿真学报, 2024, 36(3): 545-554.
[7]	李高扬, 黎向锋, 赵康, 金玉超, 易志东, 左敦稳. 全粒子推动野马优化算法的无人机三维路径规划[J]. 系统仿真学报, 2024, 36(3): 595-607.
[8]	卢元杰, 龙珊珊, 赵航, 冯国旭, 赵晓葭. 基于混合模型的异构无人机蜂群效能评估[J]. 系统仿真学报, 2024, 36(3): 700-712.
[9]	马赟, 王源, 李蒙, 王鹏, 汤艳玲. 非平面全驱动多旋翼无人机的鲁棒预测控制[J]. 系统仿真学报, 2024, 36(2): 415-422.
[10]	程洁, 郑远, 李诚龙, 江波. 面向超低空物流场景的多机协同航迹规划算法[J]. 系统仿真学报, 2024, 36(1): 50-66.
[11]	焦嵩鸣, 首云锋, 白健鹏, 王祝. 变电站巡检无人机分层运动规划方法研究[J]. 系统仿真学报, 2023, 35(9): 1975-1984.
[12]	牛双诚, 晋玉强, 寇昆湖. 基于区块链的多无人机协同任务分配方法研究[J]. 系统仿真学报, 2023, 35(5): 949-956.
[13]	付玉, 张垚, 赵萌, 王绵沼, 郑江鹏, 贾晨, 陈胜勇. 基于仿真数据迁移学习的固定翼无人机检测[J]. 系统仿真学报, 2023, 35(5): 998-1007.
[14]	赵拓, 邓汉强, 高佳隆, 黄健. 基于网络节点聚类的多无人机动态目标分配[J]. 系统仿真学报, 2023, 35(4): 695-708.
[15]	杨青青, 邓敏仪, 彭艺. 基于改进甲虫搜索算法的城市无人机路径规划[J]. 系统仿真学报, 2023, 35(12): 2527-2536.