基于运行时保证的DAA系统运行安全保障方法设计

董磊; 王琦; 陈曦; 刘嘉琛

doi:10.13700/j.bh.1001-5965.2025.0122

基于运行时保证的DAA系统运行安全保障方法设计

doi: 10.13700/j.bh.1001-5965.2025.0122

董磊^{1, 2},
王琦^{1, 3},
陈曦^{1, 2, ,},
刘嘉琛^{1, 3}

1.
中国民航大学民航航空器适航审定技术重点实验室，天津 300300
2.
中国民航大学科技创新研究院，天津 300300
3.
中国民航大学安全科学与工程学院，天津 300300

基金项目:

中央高校基本科研业务费专项资金(3122022QD07,3122022044)

详细信息

通讯作者:
E-mail：chen_x@cauc.edu.cn

中图分类号: V243
计量
- 文章访问数: 256
- HTML全文浏览量: 117
- PDF下载量: 19
- 被引次数: 0
出版历程
- 收稿日期: 2025-03-11
- 录用日期: 2025-04-25
- 网络出版日期: 2025-06-11
- 整期出版日期: 2026-09-01

Design of operational security guarantee method for DAA system based on runtime assurance

DONG Lei^{1, 2},
WANG Qi^{1, 3},
CHEN Xi^{1, 2
, ,},
LIU Jiachen^{1, 3}

1.
Key Laboratory of Civil Aircraft Airworthiness Technology，Civil Aviation University of China，Tianjin 300300，China
2.
Science and Technology Innovation Research Institute，Civil Aviation University of China，Tianjin 300300，China
3.
College of Safety Science and Engineering，Civil Aviation University of China，Tianjin 300300，China

Funds:

The Fundamental Research Funds for the Central University (3122022QD07,3122022044)

More Information

Corresponding author: E-mail：chen_x@cauc.edu.cn

摘要

摘要:
针对无人驾驶航空器在城市空中交通(UAM)场景下的避让问题，提出了一个基于运行时保证的探测与避让模块(RTA-DAAM)，通过探测外部环境信息源判断航空器状态，并提供控制指令和告警信息，保证航空器在UAM场景下执行任务的高效性和安全性。对RTA-DAAM中的先进避让模块和备用避让模块的控制方法进行设计，同时考虑探测、决策和告警功能协同配合的重要性，定义航空器自身的净空边界、预防边界、障碍物的安全边界，划分不同的航空器状态，完成决策与告警逻辑的设计。仿真实验结果表明，RTA-DAAM可使航空器在仅损失3.40%效率的基础上，确保其始终存在期望分离距离，以保障DAA系统运行安全。小型无人机的实飞结果表明，RTA技术的引入可提升无人机的安全时间占比至96.9%，最大限度地确保了无人机的运行安全。
- 运行时保证 /
- 探测与避让系统 /
- 无人驾驶航空器 /
- 安全运行限制 /
- 决策与告警
Abstract:
A runtime assurance-detect and avoid module (RTA-DAAM) is proposed to address the avoidance issue of unmanned aerial vehicles in the urban air mobility (UAM) scenario. It does this by identifying external environmental information sources and providing control commands and alarm information to guarantee the effectiveness and safety of aircraft in the UAM scenario. The control methods of advanced and standby collision avoidance modules in RTA-DAAM are designed. Considering the importance of coordination of detection, decision-making and warning functions, defining the aircraft’s own clearance boundaries, prevention boundaries, and obstacle safety boundaries, and dividing the different aircraft states so as to complete the design of the decision-making and warning logics. The simulation results show that RTA-DAAM can ensure the desired separation distance of the aircraft at a loss of only 3.40% of efficiency, so as to ensure the safety of the DAA system. The implementation of RTA technology can increase UAV safety time to 96.9%, providing UAV safety to the greatest extent possible, according to the real flight results of tiny UAVs.
- runtime assurance /
- detect and avoid system /
- unmanned aerial vehicles /
- safe operating limits /
- decision and alarm

HTML全文

图 1 DAA系统运行环境

Figure 1. DAA system operating environment

下载: 全尺寸图片幻灯片

图 2 DAA系统架构

Figure 2. DAA system architecture

下载: 全尺寸图片幻灯片

图 3 RTA基础框架

Figure 3. RTA foundation framework

下载: 全尺寸图片幻灯片

图 4 RTA-DAAM架构

Figure 4. RTA-DAAM architecture

下载: 全尺寸图片幻灯片

图 5 CIFDS算法架构

Figure 5. CIFDS algorithm architecture

下载: 全尺寸图片幻灯片

图 6 CIFDS运行流程

Figure 6. CIFDS operation flowchart

下载: 全尺寸图片幻灯片

图 7 EGO-Planner规划示意图

Figure 7. EGO-Planner planning schematic

下载: 全尺寸图片幻灯片

图 8 决策模块运行示意图

Figure 8. Schematic diagram of operation of decision-making module

下载: 全尺寸图片幻灯片

图 9 基于RTA的决策与告警逻辑示意图

Figure 9. Schematic diagram of RTA-based decision-making and alerting logic

下载: 全尺寸图片幻灯片

图 10 仿真场景设置

Figure 10. Simulation scene setting

下载: 全尺寸图片幻灯片

图 11 回合奖励值变化

Figure 11. Episode reward changes

下载: 全尺寸图片幻灯片

图 12 航空器与目标点之间距离变化

Figure 12. Distance variation between aircraft and target point

下载: 全尺寸图片幻灯片

图 13 航空器任务执行时间占比

Figure 13. Percentage of aircraft operational status time

下载: 全尺寸图片幻灯片

图 14 航空器任务路径规划（俯视图）

Figure 14. Aircraft mission path planning (top view)

下载: 全尺寸图片幻灯片

图 15 航空器任务路径规划（左视图）

Figure 15. Aircraft mission path planning (left view)

下载: 全尺寸图片幻灯片

图 16 航空器与障碍物之间的最小安全距离

Figure 16. Minimum safe distance between aircraft and obstacles

下载: 全尺寸图片幻灯片

图 17 RTA-DAAM决策与告警过程

Figure 17. RTA-DAAM decision-making and alerting processes

下载: 全尺寸图片幻灯片

图 18 无人机运行场景

Figure 18. Scenarios of drone operations

下载: 全尺寸图片幻灯片

图 19 无人机飞行轨迹对比

Figure 19. Comparison of drone flight trajectories

下载: 全尺寸图片幻灯片

图 20 无人机与障碍物之间的最小安全距离

Figure 20. Minimum safe distance between a drone and an obstacle

下载: 全尺寸图片幻灯片

表 1 告警等级

Table 1. Alarm levels

告警等级	告警名称	采取措施
0	无告警	地面站可选择性干预
Ⅰ	预防告警	地面站可选择性干预
Ⅱ	纠正告警	地面站可选择性干预
Ⅲ	危险告警	地面站干预

下载: 导出CSV

表 2 参数设置

Table 2. Parameter settings

参数	数值
本机速度/（m·s⁻¹）	0.8
入侵机速度/（m·s⁻¹）	0.8
障碍物安全边界宽度/m	2.5
本机净空边界半径/m	1
本机预防边界半径/m	1.5
Actor学习率	2×10⁻⁴
Critic学习率	1×10⁻³
训练轮数/回合数	5000
批次大小/个	256
经验池容量/个	1×10⁶
折扣因子	0.99
噪声截断值	0.5
策略噪声	0.2

下载: 导出CSV

表 3 CIFDS与IFDS算法路径规划对比

Table 3. Comparison of path planning under CIFDS and IFDS algorithms

障碍环境	最大飞行角度变化/(°)		路径长度/m
障碍环境	CIFDS	IFDS	CIFDS	IFDS
E1	26.8	27.2	22.1	23.4
E2	28.5	32.4	23.7	26.6
E3	27.3	30.9	22.9	25.5

下载: 导出CSV

表 4 避让方法效率对比

Table 4. Comparison of efficiency of avoidance methods

避让方法	任务执行时间/s	路径长度/m
先进避让方法	76.5	61.2
RTA-DAAM避让方法	79.1	63.3
备用避让方法	93.0	74.4

下载: 导出CSV

表 5 不同密度场景下的航空器路径规划对比

Table 5. Comparison of aircraft path planning in different density scenarios

场景类型	安全时间占比/%		路径长度/m
场景类型	先进避让方法	RTA-DAAM 避让方法	先进避让方法	RTA-DAAM 避让方法
低密集度	100.0	100.0	60.8	61.4
中密集度	91.9	98.5	62.1	65.8
高密集度	77.2	93.8	65.6	74.7

下载: 导出CSV

参考文献(32)

[1]	Huang X. The small-drone revolution is coming: scientists need to ensure it will be safe[J]. Nature, 2025, 637(8044): 29-30.
[2]	Thipphavong D P, Apaza R, Barmore B, et al. Urban air mobility airspace integration concepts and considerations[C]//Proceedings of the Aviation Technology, Integration, and Operations Conference. Reston: AIAA, 2018: 3676.
[3]	Michelmann J, Straubinger A, Al Haddad C, et al. Urban air mobility 2030+: pathways for UAM–a scenario-based analysis[EB/OL]. [2025-03-01]. https://www.semanticscholar.org/paper/URBAN-AIR-MOBILITY-2030%2B%3A-PATHWAYS-FOR-UAM-%E2%80%93-A-Michelmann-Straubinger/dde5cd91a5cd19fd5cec68241fb59bc954e2eed0.
[4]	Cheng A W, Witzberger K E, Phojanamongkolkij N, et al. Urban air mobility (UAM) airspace research roadmap-systems engineering approach to managing airspace evolution towards UML-4[C]//AIAA Aviation 2022 Forum. Reston: AIAA, 2022.
[5]	Muñoz C, Narkawicz A, Hagen G, et al. DAIDALUS: detect and avoid alerting logic for unmanned systems[C]//Proceedings of the IEEE/AIAA 34th Digital Avionics Systems Conference. Piscataway: IEEE Press, 2015.
[6]	Davies J, Wu M H. Comparative analysis of ACAS-Xu and DAIDALUS detect-and-avoid systems: NASA/TM-2018-219773[R]. Washington, D. C. : NASA, 2018.
[7]	Ryu J Y, Lee H, Lee H T. Detect and avoid AI system model using a deep neural network[C]//Proceedings of the IEEE/AIAA 41st Digital Avionics Systems Conference. Piscataway: IEEE Press, 2022: 1-8.
[8]	工业和信息化部, 科学技术部, 财政部, 中国民用航空局. 绿色航空制造业发展纲要(2023—2035年)[R]. 北京: 工业和信息化部, 科学技术部, 财政部, 中国民用航空局, 2023. Ministry of Industry and Information Technology, Ministry of Science and Technology, Ministry of Finance, Civil Aviation Administration of China. Guideline for green aviation manufacturing development (2023—2035)[R]. Beijing: Ministry of Industry and Information Technology, Ministry of Science and Technology, Ministry of Finance, Civil Aviation Administration of China, 2023(in Chinese).
[9]	曹宏业, 刘潇, 董绍康, 等. 面向强化学习的可解释性研究综述[J]. 计算机学报, 2024, 47(8): 1853-1882. Cao H Y, Liu X, Dong S K, et al. A survey of interpretability research methods for reinforcement learning[J]. Chinese Journal of Computers, 2024, 47(8): 1853-1882(in Chinese).
[10]	Castelvecchi D. Can we open the black box of AI?[J]. Nature, 2016, 538(7623): 20-23.
[11]	Perez-Cerrolaza J, Abella J, Borg M, et al. Artificial intelligence for safety-critical systems in industrial and transportation domains: a survey[J]. ACM Computing Surveys, 2024, 56(7): 1-40.
[12]	董磊, 刘嘉琛, 陈曦, 等. 面向适航符合性的智能航电系统认证研究进展[J]. 航空工程进展, 2023, 14(3): 26-40. Dong L, Liu J C, Chen X, et al. Research progress of AI-based avionics system certification for airworthiness compliance[J]. Advances in Aeronautical Science and Engineering, 2023, 14(3): 26-40(in Chinese).
[13]	Fuller J G. Run-time assurance: a rising technology[C]//Proceedings of the AIAA/IEEE 39th Digital Avionics Systems Conference. Piscataway: IEEE Press, 2020: 1-9.
[14]	董磊, 王琦, 陈曦, 等. 运行时保证技术的研究现状与发展综述[J]. 计算机应用, 2025, 45(3): 1003-1015. Dong L, Wang Q, Chen X, et al. Survey of research status and development of runtime assurance technology[J]. Journal of Computer Applications, 2025, 45(3): 1003-1015(in Chinese).
[15]	Cofer D, Amundson I, Sattigeri R, et al. Run-time assurance for learning-based aircraft taxiing[C]//Proceedings of the AIAA/IEEE 39th Digital Avionics Systems Conference. Piscataway: IEEE Press, 2020: 1-9.
[16]	He Y N, Schumann J, Yu H F. Toward runtime assurance of complex systems with AI components[J]. PHM Society European Conference, 2022, 7(1): 166-174.
[17]	Ghori S, Khamvilai T, Feron E, et al. Runtime assurance for distributed avionics architecture[C]//Proceedings of the IEEE/AIAA 41st Digital Avionics Systems Conference. Piscataway: IEEE Press, 2022: 1-6.
[18]	Abate M, Mote M, Dor M, et al. Run time assurance for spacecraft attitude control under nondeterministic assumptions[J]. IEEE Transactions on Control Systems Technology, 2024, 32(3): 862-873.
[19]	Avram R, Zhang X D, Muse J A, et al. Nonlinear adaptive control of quadrotor UAVs with run-time safety assurance[C]//Proceedings of the AIAA Guidance, Navigation, and Control Conference. Reston: AIAA, 2017: 1896.
[20]	Chen S D, Sun Y W, Li D C, et al. Runtime safety assurance for learning-enabled control of autonomous driving vehicles[C]//Proceedings of the International Conference on Robotics and Automation. Piscataway: IEEE Press, 2022: 8978-8984.
[21]	高雅琪. 无人机系统中DAA模块的研究和设计实现[D]. 成都: 电子科技大学, 2022. Gao Y Q. Research design and implementation on DAA module of UAV system[D]. Chengdu: University of Electronic Science and Technology of China, 2022(in Chinese).
[22]	Owen M P, Panken A, Moss R, et al. ACAS Xu: integrated collision avoidance and detect and avoid capability for UAS[C]//Proceedings of the IEEE/AIAA 38th Digital Avionics Systems Conference. Piscataway: IEEE Press, 2020: 1-10.
[23]	Borshchova I, Ellis K. DAAMSIM: a simulation framework for establishing detect and avoid SYSTEM requirements[J]. Drone Systems and Applications, 2022, 10(1): 266-286.
[24]	ASTM International. Standard practice for methods to safely bound behavior of aircraft systems containing complex functions using run-time assurance: ASTM F3269-21[S]. West Conshohocken: ASTM International, 2021.
[25]	Torens C, Nagarajan P, Schirmer S, et al. Certification aspects of runtime assurance for urban air mobility: AIAA 2024-1464[R]. Reston: AIAA, 2024.
[26]	Wang H L, Lyu W T, Yao P, et al. Three-dimensional path planning for unmanned aerial vehicle based on interfered fluid dynamical system[J]. Chinese Journal of Aeronautics, 2015, 28(1): 229-239.
[27]	Yao P, Wang H L, Liu C. 3-D dynamic path planning for UAV based on interfered fluid flow[C]//Proceedings of the IEEE Chinese Guidance, Navigation and Control Conference. Piscataway: IEEE Press, 2015: 997-1002.
[28]	Li Y X. Deep reinforcement learning: an overview[EB/OL]. (2018-11-26)[2025-03-01]. https://arxiv.org/abs/1701.07274.
[29]	Szepesvári C. Algorithms for reinforcement learning[M]. Berlin: Springer, 2022.
[30]	吴健发, 王宏伦, 王延祥, 等. 无人机反应式扰动流体路径规划[J]. 自动化学报, 2023, 49(2): 272-287. Wu J F, Wang H L, Wang Y X, et al. UAV reactive interfered fluid path planning[J]. Acta Automatica Sinica, 2023, 49(2): 272-287(in Chinese).
[31]	顾雪平, 刘彤, 李少岩, 等. 基于改进双延迟深度确定性策略梯度算法的电网有功安全校正控制[J]. 电工技术学报, 2023, 38(8): 2162-2177. Gu X P, Liu T, Li S Y, et al. Active power correction control of power grid based on improved twin delayed deep deterministic policy gradient algorithm[J]. Transactions of China Electrotechnical Society, 2023, 38(8): 2162-2177(in Chinese).
[32]	Zhou X, Wang Z P, Ye H K, et al. EGO-Planner: an ESDF-free gradient-based local planner for quadrotors[J]. IEEE Robotics and Automation Letters, 2021, 6(2): 478-485.