[an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive]
[an error occurred while processing this directive]

弹箭与制导学报 >

2026 , Vol. 46 >Issue 2: 212 - 224

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2026.02.010

学术文章

动态环境下的无人机正则虚拟管道生成方法

  • 林海超 ,
  • 王志胜 , *
展开
  • 南京航空航天大学自动化学院, 江苏 南京 211100
*

收稿日期: 2026-02-05

  网络出版日期: 2026-05-09

收起

A Regular Virtual Tube Generation Method for UAV Operating in Dynamic Environments

  • LIN Haichao ,
  • WANG Zhisheng , *
Expand
  • College ofAutomation, Nanjing University of Aeronautics and Astronautics, Nanjing, 211100,Jiangsu, China

Received date: 2026-02-05

  Online published: 2026-05-09

Fold

摘要

针对森林火灾中火焰蔓延与烟雾扩散对无人机造成的威胁,提出一种在动态火灾与烟雾耦合的环境中正则虚拟管道实时生成方法,以满足无人机在该环境下的高安全性飞行需求。首先构建起融合火灾蔓延规律与烟雾平流扩散机制的动态环境预测模型,并提出一种协同表征实时位置风险与时空预测风险的双重度量机制,构建了静态和动态障碍物统一量化代价场和时空约束窗口。其次,构建风险感知的管道生成框架,利用风险感知A*算法搜索时空可行路径,利用自适应安全虚拟管道生成算法来生成正则虚拟管道。仿真结果表明,该方法可随火情变化实时生成虚拟管道,并且相比于现有方法,最小安全距离提升43.2%,最高代价值降低28.7%,规划时间减小82.9%,显著增强了无人机在多源高风险环境下的航迹安全和飞行安全。

关键词： 虚拟管道; 火灾与烟雾耦合; 时空风险表征; 二次规划; 无人机

本文引用格式

林海超 , 王志胜 . 动态环境下的无人机正则虚拟管道生成方法[J]. 弹箭与制导学报, 2026 , 46(2) : 212 -224 . DOI: 10.15892/j.cnki.djzdxb.2026.02.010

Abstract

To address the threats posed to the unmanned aerial vehicles (UAVs) by flame spread and smoke dispersion in forest fires,this paper proposes a real-time method for generating a regular virtual tube in a dynamic environment with coupled fire and smoke to support safety-critical UAV flight.Firstly,a dynamic environment prediction model is developed based on the wildfire spread dynamics and a smoke advection-diffusion mechanism.A dual-metric mechanism is then proposed to simultaneously characterize the real-time positional risk and spatiotemporal predictive risk,resulting in a unified quantified cost field for both static and dynamic obstacles and a spatiotemporal constraint window.Next,a risk-aware tube-generation framework is built to search a spatiotemporally feasible path by using a risk-aware A* algorithm and generate the regular virtual tube by using an adaptive safe virtual-tube generation algorithm.Simulated results show that the proposed method can regenerate the virtual tube in real time as the fire conditions evolve.Compared with the existing methods,the proposed method increases the minimum safe distance by 43.2%,reduces the maximum cost by 28.7%,and decreases the replanning time by 82.9%,significantly improving both the trajectory safety and flight safety of UAVs in multi-source high-risk environments.

Key words： virtual tube; fire-smoke coupling; spatiotemporal risk characterization; quadratic programming; unmanned aerial vehicle

[an error occurred while processing this directive]

参考文献

原文顺序 | 文献年度倒序 | 文中引用次数倒序
[1]
XU Y Q, LI J M, ZHANG F Q. A UAV-based forest fire patrol path planning strategy[J]. Forests, 2022, 13(11):1952.

DOI

[2]
ISLAM S M T, HU X L. Real-time autonomous path planning for dynamic wildfire monitoring with uneven importance[J]. Applied Intelligence, 2024, 54(17):8505-8524.

DOI

[3]
LIU C, SZIRANYI T. Active wildfires detection and dynamic escape routes planning for humans through information fusion between drones and satellites[C]// Proceedings of the 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC).Bilbao, ES:IEEE, 2023:1977-1982.

[4]
WANG S K, WU M Q, WEI X H, et al. An advanced multi-source data fusion method utilizing deep learning techniques for fire detection[J]. Engineering Applications of Artificial Intelligence, 2025, 142:109902.

DOI

[5]
PAPACHRISTOS C, MASCARICH F, ALEXIS K. Thermal-inertial localization for autonomous navigation of aerial robots through obscurants[C]// Proceedings of the 2018 International Conference on Unmanned Aircraft Systems (ICUAS).Dallas,TX, USA:IEEE, 2018:394-399.

[6]
LIU C, SZIRANYI T. Optimal wildfire escape route planning for drones under dynamic fire and smoke[C]// Proceedings of the 2023 17th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).Bangkok, TH:IEEE, 2023:429-434.

[7]
CHEN C H, YAO Z Q, JIANG J L, et al. SmokeNav:millimeter-wave-radar/inertial measurement unit integrated positioning and semantic mapping in visually degraded environments for first responders[J]. Advanced Intelligent Systems, 2024, 6(12):2400241.

DOI

[8]
XIE S T, HU J Y, BHOWMICK P, et al. Distributed motion planning for safe autonomous vehicle overtaking via artificial potential field[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11):21531-21547.

DOI

[9]
SUN Y, FU L. Real-time game theory based artificial potential field method for multiple unmanned aerial vehicles path planning[C]// Proceedings of the 2018 International Technical Meeting of The Institute of Navigation.Reston,VA, USA:ION, 2018:521-528.

[10]
VÁSÁRHELYI G, VIRÁGH C, SOMORJAI G, et al. Optimized flocking of autonomous drones in confined environments[J]. Science Robotics, 2018, 3(20):eaat3536.

DOI

[11]
YAO W J, DE MARINA H G, LIN B H, et al. Singularity-free guiding vector field for robot navigation[J]. IEEE Transactions on Robotics, 2021, 37(4):1206-1221.

DOI

[12]
HU BB, ZHANG H T, YAO W J, et al. Spontaneous-ordering platoon control for multirobot path navigation using guiding vector fields[J]. IEEE Transactions on Robotics, 2023, 39(4):2654-2668.

DOI

[13]
YAO W J, DE MARINA H G, SUN Z Y, et al. Guiding vector fields for the distributed motion coordination of mobile robots[J]. IEEE Transactions on Robotics, 2023, 39(2):1119-1135.

DOI

[14]
ZHAO Y J, MA Y, HU S L. USV formation and path-following control via deep reinforcement learning with random braking[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(12):5468-5478.

DOI

[15]
SINGLA A, PADAKANDLA S, BHATNAGAR S. Memory-based deep reinforcement learning for obstacle avoidance in UAV with limited environment knowledge[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(1):107-118.

DOI

[16]
HE L, AOUF N, WHIDBORNE J F, et al. Integrated moment-based LGMD and deep reinforcement learning for UAV obstacle avoidance[C]// Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA).Paris, FR:IEEE, 2020:7491-7497.

[17]
DOUKHI O, LEE D J. Deep reinforcement learning for autonomous map-less navigation of a flying robot[J]. IEEE Access, 2022, 10:82964-82976.

DOI

[18]
JIANG D, DU L, LI S H, et al. An improved dynamic window approach based on reinforcement learning for the trajectory planning of automated guided vehicles[J]. IEEE Access, 2024, 12:36016-36025.

DOI

[19]
RUBÍ B, MORCEGO B, PÉREZ R. Deep reinforcement learning for quadrotor path following and obstacle avoidance[M]// KOUBAAA, AZARA T. Deep Learning for Unmanned Systems.Cham,CH:Springer, 2021:563-633.

[20]
GAO Y, BAI C G, FU R, et al. A non-potential orthogonal vector field method for more efficient robot navigation and control[J]. Robotics and Autonomous Systems, 2023, 159:104291.

DOI

[21]
MAO P D, QUAN Q. Making robotics swarm flow more smoothly:a regular virtual tube model[C]// Proceedings of the 2022 IEEE/RSJ International Conference on IntelligentRobots and Systems (IROS).Kyoto, JP:IEEE, 2022:4498-4504.

[22]
MAO P D, FU R, QUAN Q. Optimal virtual tube planning and control for swarm robotics[J]. The International Journal of Robotics Research, 2024, 43(5):602-627.

DOI

[23]
QUAN Q, HUANG S H, CAI K Y. A degree of flowability for virtual tubes[J]. Robotics and Autonomous Systems, 2025, 193:105108.

DOI

[24]
GAO Y, BAI C G, QUAN Q. Distributed control for a multiagent system to pass through a connected quadrangle virtual tube[J]. IEEE Transactions on Control of Network Systems, 2023, 10(2):693-705.

DOI

[25]
YUAN M S, CHEN M, LUNGU M H, et al. Curve virtual tube planning and distributed control for swarm UAVs with complex constraints and disturbances[J]. IEEE Transactions on Industrial Electronics, 2026, 73(2):3037-3048.

DOI

[26]
YUE S Y, ZHENG D, WEI M J, et al. Behavior-based cooperative control method for fixed-wing UAV swarm through a virtual tube considering safety constraints[J]. Chinese Journal of Aeronautics, 2025, 38(11):103445.

DOI

[27]
LV S L, GAO Y, QUAN Q. High-efficiency vector field by time-optimal spatial iterative learning[J]. IEEE Transactions on Robotics, 2025, 41:5624-5644.

DOI

[28]
LEI Y Q, QUAN Q, SHE Z K. Mean-field-based density control for swarm robotics passing-through a virtual tube[J]. IEEE Control Systems Letters, 2024, 8:3500-3505.

DOI

[29]
WU Z C, WANG B, LI M Z, et al. Simulation of forest fire spread based on artificial intelligence[J]. Ecological Indicators, 2022, 136:108653.

DOI

[30]
SUN X, LI N, CHEN D Q, et al. A forest fire prediction model based on cellular automata and machine learning[J]. IEEE Access, 2024, 12:55389-55403.

DOI

[31]
CHENG S B, PRENTICE I C, HUANG Y H, et al. Data-driven surrogate model with latent data assimilation:application to wildfire forecasting[J]. Journal of Computational Physics, 2022, 464:111302.

DOI

[32]
ALESSANDRI A, BAGNERINI P, GAGGERO M, et al. Parameter estimation of fire propagation models using level set methods[J]. Applied Mathematical Modelling, 2021, 92:731-747.

DOI

[33]
XIA Z Y, CHENG S B. PyTorchFire:a GPU-accelerated wildfire simulator with differentiable cellular automata[J]. Environmental Modelling & Software, 2025, 188:106401.

[34]
RAO K, YAN H C, ZHANG R F, et al. Gradient-based online regular virtual tube generation for UAV swarms in dynamic fire scenarios[J]. IEEE Transactions on Industrial Informatics, 2024, 20(12):14204-14213.

DOI

[35]
RUI X P, HUI S, YU X T, et al. Forest fire spread simulation algorithm based on cellular automata[J]. Natural Hazards, 2018, 91(1):309-319.

DOI

[36]
RAVSHANOV N, MURADOV F, AKHMEDOV D. Operator splitting method for numerical solving the atmospheric pollutant dispersion problem[J]. Journal of Physics:Conference Series. 2020, 1441(1):012164.

DOI

[37]
LIU Y L, LIAO M C, LI J C, et al. Deep learning emulator towards both forward and adjoint modes of atmospheric gas-phase chemical process[J]. Atmosphere, 2025, 16(9):1109.

DOI

[38]
SOPHOCLEOUS K, CHRISTOUDIAS T. Reduced-precision chemical kinetics in atmospheric models[J]. Atmosphere, 2022, 13(9):1418.

DOI

[39]
RAO P, MANORANJAN V S. Tracking contaminant transport backwards with an operator-splitting method[J]. Mathematics, 2023, 11(13):2828.

DOI

Options
文章导航

/

〈 〉

[an error occurred while processing this directive]