Autonomous Exploration of UAVs in Unknown Environment Based on Dynamic Behavior Trees

XU Xiaobin; GU Chengyu; LIN Shiyao; FAN Junfang

doi:10.12382/bgxb.2025.0490

您当前的位置：

首页 >

文章列表页 >

Autonomous Exploration of UAVs in Unknown Environment Based on Dynamic Behavior Trees

更新时间：2026-04-24

- Autonomous Exploration of UAVs in Unknown Environment Based on Dynamic Behavior Trees
- Acta Armamentarii Vol. 47, Issue 1, Pages: 250490(2026)
- 作者机构：
  
  北京信息科技大学自动化学院，北京 100192
  中国兵器科学研究院，北京 100089
- 作者简介：
- 基金信息：
- DOI：10.12382/bgxb.2025.0490
  CLC： V249.1
- Received：12 June 2025，
  
  Online First：11 February 2026，
  
  Published：31 January 2026
- 稿件说明：
移动端阅览
XU Xiaobin, GU Chengyu, LIN Shiyao, et al. Autonomous Exploration of UAVs in Unknown Environment Based on Dynamic Behavior Trees[J]. Acta Armamentarii, 2026, 47(1): 250490.
DOI：

XU Xiaobin, GU Chengyu, LIN Shiyao, et al. Autonomous Exploration of UAVs in Unknown Environment Based on Dynamic Behavior Trees[J]. Acta Armamentarii, 2026, 47(1): 250490. DOI： 10.12382/bgxb.2025.0490.

摘要

未知、全球定位系统拒止环境下，针对无人机自主探索时面临的环境动态性与实时复杂决策挑战，提出一种基于动态行为树（Dynamic Behavior Tree

DBT）的自主探索算法。该算法前端构建轻量化时变体素概率地图模型，并融合轻量化地图引导的改进切线爬虫实时路径规划器，通过环境感知优化实现安全高效导航。后端核心采用基于DBT的自适应决策机制，创新性地引入动态权重驱动的拓扑重构，采用层次化设计和模块化管理，赋予系统算法调度能力与主动响应环境变化的智能决策能力。通过ROS2/Gazebo平台的仿真验证，DBT在感知、决策与响应方面均表现出较好的性能，与有限状态机方法相比，DBT算法的探索覆盖率提升了2. 33%～12%，平均探索覆盖率提升了1%～13%，有效提升了无人机在未知环境中自主探索的效率、鲁棒性和智能化水平。

Abstract

To address the challenges of environmental dynamics and complex real-time decision-making encountered by unmanned aerial vehicles (UAVs) during autonomous exploration in unknown and GPS-denied environments

this paper proposes an autonomous exploration algorithm based on dynamic behavior trees (DBTs) . The front-end of this algorithm constructs a lightweight time-varying voxel probability map model

and integrates an improved Tangent Bug real-time path planner guided by the lightweight map

achieving safe and efficient navigation through optimized environmental perception. The core of the back-end employs an adaptive decision-making mechanism based on DBT

innovatively introducing a dynamic weight-driven topological reconfiguration. This mechanism utilizes a hierarchical design and modular management to endow the system with the algorithm scheduling capabilities and the intelligent decision-making ability to proactively respond to environmental changes. Simulation experiments conducted on the ROS2/Gazebo platform demonstrate that the DBT algorithm exhibits superior performance in perception

decision-making

and responsiveness. Compared with the finite state machine method

DBT algorithm increases the exploration coverage rate by 2. 33%-12% and the average exploration coverage rate by 1%-13%

significantly enhancing the efficiency

robustness

and intelligence level of UAV's autonomous exploration in unknown environments.

关键词

Keywords

references

DELEFORGE A, CARLO D D, STRAUSS M, et al. Audio-based search and rescue with a drone: highlights from the IEEE signal processing cup 2019 student competition [J]. IEEE Signal Processing Magazine,2019,36（5）:138-144.

MESVAN N. CNN-based human detection system for UAVs in search and rescue: arXiv: 2110. 01930 [R]. Ithaca, NY, US:Cornell University,2021:2110. 01930.

ANTOINE R, LOPEZ T, TANGUY M, et al. Geoscientists in the sky:unmanned aerial vehicles responding to geohazards [J]. Surveys in Geophysics,2020,41（6）.DOI:10.1007/s10712-020-09611-7.

XIAO Y, GUO Y H, YIN G D, et al. UAV multispectral image-based urban river water quality monitoring using stacked ensemble machine learning algorithms—a case study of the Zhanghe river, China[J]. Remote Sensing,2022,14（14）:3272.

YANG Z Q, YANG Y, HE X X, et al. Incremental coverage path planning method for UAV ground mapping in unknown area[J]. International Journal of Micro Air Vehicles,2024,16:10.

ORISATOKI M O, AMOUZADI M, DIZQAH A M. A heuristic informative-path-planning algorithm for autonomous mapping of unknown: arXiv: 2308. 12209 [R]. Ithaca, NY, US: Cornell University,2023:2308. 12209.

王乐，齐尧，何滨兵，等.机器人自主探索算法综述[J].计算机应用，2023,43（增刊S1）:314-322.

WANG L, QI Y, HE B B, et al.A survey of autonomous exploration algorithms for robots[J].Journal of Computer Applications,2023, 43（S1）:314-322.（in Chinese）

张世勇，张雪波，苑晶，等.旋翼无人机环境覆盖与探索规划方法综述[J].控制与决策，2022,37（3）:513-529.

ZHANG S Y, ZHANG X B, YUAN J, et al.A survey on environmental coverage and exploration planning methods for rotorcraft UAVs[J].Control and Decision,2022,37（3）:513-529.（in Chinese）

王伟伦，尤明，孙磊，等.未知环境下无人机集群智能协同探索路径规划[J].工程科学学报，2024,46（7）:1197-1206.

WANG W L, YOU M, SUN L, et al.Intelligent cooperative exploration path planning for UAV swarms in unknown environments[J].Chinese Journal of Engineering,2024,46（7）:1197-1206.（in Chinese）

DAI A N, PAPATHEODOROU S, FUNK N, et al. Fast frontier-based information-driven autonomous exploration with an MAV [C]∥Proceedings of 2020 IEEE International Conference on Robotics and Automation. Paris, France:IEEE,2020.

傅晋博，张栋，王孟阳，等.面向未知动目标的多机协同动态搜索决策方法[J/OL].兵工学报，doi: 10.12382/bgxb.2025.0057.

FU J B, ZHANG D, WANG M Y, et al.Multi-agent collaborative dynamic search decision method for unknown moving targets[J/OL].Acta Armamentarii, doi: 10.12382/bgxb.2025.0057.（in Chinese）

唐嘉宁，李成阳，周思达，等.基于深度强化学习的无人机自主探索方法[J].计算机科学，2024,51（增刊2）:154-159.

TANG J N, LI C Y, ZHOU S D, et al.Autonomous exploration method for UAVs based on deep reinforcement learning [J].Computer Science,2024,51（S2）:154-159.（in Chinese）

ZHOU B Y, HU H, SHEN S J. RACER: rapid collaborative exploration with a decentralized multi-UAV system [J]. IEEE Transactions on Robotics,2023,39（3）:1-20.

XU W, CAI Y X, HE D J, et al. FAST-LIO2:fast direct LiDAR-inertial odometry [J]. IEEE Transactions on Robotics, 2022, 38（4）:2053-2073.

史殿习，苏雅倩文，李宁，等.基于行为树调度的多无人机未知室内空间探索方法[J].计算机科学，2022,49（增刊2）:83-93.

SHI D X, SU Y Q W, LI N, et al.Multi-UAV unknown indoor space exploration method based on behavior tree scheduling[J].Computer Science,2022,49（S2）:83-93.（in Chinese）

唐嘉宁，刘雨晴，周思达，等.复合边界点驱动的未知三维环境探索路径规划方法研究[J].西北工业大学学报，2022, 40（3）:708-716.

TANG J N, LIU Y Q, ZHOU S D, et al.Research on exploration path planning method for unknown 3D environment driven by composite boundary points [J].Journal of Northwestern Polytechnical University,2022,40（3）:708-716.（in Chinese）

ZHOU B Y, ZHANG Y C, CHEN X Y, et al. FUEL: fast UAV exploration using incremental frontier structure and hierarchical planning [J]. IEEE Robotics and Automation Letters, 2021, 6（2）:779-786.

于群.未知环境下多旋翼无人机自主探索及建图[D].大连：大连海事大学，2023.

YU Q.Autonomous exploration and mapping for multi-rotor UAVs in unknown environments [D].Dalian: Dalian Maritime University,2023.（in Chinese）

VORONIN V, FRANTC V, SEMENISHCHEV E, et al. 3-D shape object reconstruction with non-lambertian surface from multiple views based on deep learning [J]. Proceedings of SPIE-the International Society for Optical Engineering,2022,12100.

方秋雨，张蕴霖，麻壮壮，等.未知环境下基于控制障碍函数的无人车轨迹规划[J].兵工学报，2023,44（增刊2）:90-100.

FANG Q Y, ZHANG Y L, MA Z Z, et al.Control barrier functions-based trajectory planning for unmanned ground vehicles in unknown environment[J].Acat Armamentarii,2023,44（S2）:90-100.（in Chinese）

董明泽，温庄磊，陈锡爱，等.安全凸空间与深度强化学习结合的机器人导航方法[J].兵工学报，2024,45（12）:4372-4382.

DONG M Z, WEN Z L, CHEN X A, et al.Research on robot navigation method integrating safe convex space and deep reinforcement learning[J].Acta Armamentarii,2024,45（12）:4372-4382.（in Chinese）

WANG X L, YIN Y, JING Q F. Maritime search path planning method of an unmanned surface vehicle based on an improved bug algorithm[J]. Journal of Marine Science and Engineering,2023, 11（12）:2320.

Views

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

GU Chengyu

LIN Shiyao

XU Xiaobin

FAN Junfang

Related Institution

No data

Postal code：100089
Tel：010-68963060/68962718 Fax：010-68963025 Email：bgxb@cos.org.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05059581号-4 京公网安备11010802024360号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：119049 Visits Today：36

⁰