With the rapid development of aviation technology, especially in intelligent situation awareness, autonomous flight control and electric propulsion, the number of unmanned aerial vehicles (UAVs) has grown explosively, bringing challenges to low-altitude flight safety. Autonomous UAV detect and avoid (DAA) technology is a key future direction. Firstly, this paper focuses on UAV multi-sensor data fusion, proposing an asynchronous trajectory fusion method via comprehensive weighting that accounts for multiple influencing factors. Secondly, for trajectory tracking of ownship and intruders, improved Kalman filter (KF) and enhanced Sage-Husa adaptive unscented Kalman filter (AUKF) algorithms are used for vertical and horizontal tracking to enhance accuracy. Then, a hybrid method combining detect and avoid alerting logic for unmanned aircraft systems (DAIDALUS) with Markov decision process (MDP) is proposed to solve the UAV collision avoidance decision-making problem. It calculates collision avoidance strategies via the state space, takes them as MDP’s action space, sets up reward functions and state transition probabilities to build an MDP model, and explores the influence of discount factors. Finally, through experimental tests, results show the proposed UAV detection and avoidance decision method has a 27.2% efficiency increase compared to standalone DAIDALUS, the loss of well clear (LoWC) rate is only 5.8%, and the nearest distance between the intruder and the ownship is 343 m, meeting the collision avoidance requirements for UAV flight.
SantosDFMFalcãoDSPintoAMFR, et al.Effect of membrane electrode assembly characteristics on the performance of a proton exchange membrane fuel cell stack designed for unmanned aerial vehicle applications. Int J Green Energy2024; 21(6): 1226–1237.
2.
PrajapatiSThakarPSMarkanaA. Novel custom-made design and analysis of hydrogen PEM fuel cell for high endurance small UAV applications. Environ Sci Pollut Res2023; 32: 1–12.
3.
Diez-TomilloJAlcaraz-CaleroJMWangQ. Face verification algorithms for UAV applications: an empirical comparative analysis. Journal of Communications Software and Systems2024; 20(1): 1–12.
4.
PratsXDelgadoLRamirezJ, et al.Requirements, issues, and challenges for sense and avoid in unmanned aircraft systems. J Aircraft2012; 49(3): 677–687.
5.
OmeriMIsufajROrtizRM. Quantifying well clear for autonomous small UAS. IEEE Access2022; 10: 68365–68383.
6.
KuruKPinderJMWatkinsonBJ, et al.Toward mid-air collision-free trajectory for autonomous and pilot-controlled unmanned aerial vehicles. IEEE Access2023; 11: 100323–100342.
7.
InceBMartinezVCSelvamPK, et al.Sense and avoid considerations for safe sUAS operations in urban environments. IEEE2024: 1–16.
8.
LeeSWuMGConeAC. Evaluating noncooperative detect-and-avoid well clear definitions with alerting performance and surveillance requirement. J Air Transport2021; 29(4): 171–183.
9.
RTCA DO-365B. Minimum operational performance standards (MOPS) for detect and avoid (DAA) systems. RTCA, 2021.
10.
FerreiraNBFMoscatoMMTitoloL, et al.A provably correct floating-point implementation of well clear avionics conceptsIn: 2023 formal methods in computer-aided design (FMCAD). IEEE, 2023: 237–246.
11.
RyuJYLeeHLeeHT. Detect and avoid AI system model using a deep neural network In: 2022 IEEE/AIAA 41st digital avionics systems conference (DASC). IEEE, 2022: 1–8.
12.
GaoY. Research design and implementation on DAA module of UAV system. Master dissertation. University of Electronic Science and Technology of China, 2022, pp. 30–33.
13.
De OliveiraÍRMatsumotoTMayneA, et al.Analyzing the closed-loop performance of detect-and-avoid systems. In: 2023 IEEE 26th international conference on intelligent transportation systems (ITSC). IEEE, 2023, pp. 4947–4952.
14.
SvanströmFAlonso-FernandezFEnglundC. Drone detection and tracking in real-time by fusion of different sensing modalities. Drones2022; 6(11): 317.
15.
YangJTangWDingZ. Long-term target tracking of UAVs based on kernelized correlation filter. Mathematics2021; 9(23): 3006.
16.
ZhuYJiaZWuQ, et al.UAV trajectory tracking via RNN-Enhanced IMM-KF with ADS-B data. In: IEEE wireless communications and networking conference (WCNC). IEEE, 2024, pp. 1–6.
17.
SunXShiCZhouJ. Intelligent decision-making algorithm for anti-UAV swarm based on convolutional neural networks. In: 2024 photonics & electromagnetics research symposium (PIERS). IEEE, 2024, pp. 1–8.
18.
LiuHJinJLiuK, et al.Research on UAV air combat maneuver decision based on decision tree CART algorithm. In: International conference on autonomous unmanned systems. Springer Nature Singapore, 2022, pp. 2638–2650.
19.
HuSRuLLvM, et al.Evolutionary game analysis of behaviour strategy for UAV swarm in communication‐constrained environments. IET Control Theory & Appl2024; 18(3): 350–363.
20.
ChangZDengHYouL, et al.Trajectory design and resource allocation for multi-UAV networks: deep reinforcement learning approaches. IEEE Trans Netw Sci Eng2022; 10(5): 2940–2951.
21.
ShenYWangXWangH, et al.A dynamic task assignment model for aviation emergency rescue based on multi-agent reinforcement learning. Journal of Safety Science and Resilience2023; 4(3): 284–293.
22.
KatzSMAlvarezLEOwenM, et al.Collision risk and operational impact of speed change advisories as aircraft collision avoidance maneuvers. AIAA AVIATION 2022 Forum. AIAA, 2022. pp. 3824.
23.
HeDYangYDengS, et al.Comparison of collision avoidance logic between ACAS X and TCAS II in general aviation flight. In: 2023 IEEE 5th international conference on civil aviation safety and information technology (ICCASIT). IEEE, 2023, pp. 568–573.
24.
YangSMengZChenX, et al.Real-time obstacle avoidance with deep reinforcement learning three-dimensional autonomous obstacle avoidance for UAV. In: Proceedings of the 2019 international conference on robotics, intelligent control and artificial intelligence. ACM, 2019, pp. 324–329.
25.
RubíBMorcegoBPérezR. Quadrotor path following and reactive obstacle avoidance with deep reinforcement learning. J Intell Rob Syst2021; 103(4): 62.
26.
KatzSMJulianKDStrongCA, et al.Generating probabilistic safety guarantees for neural network controllers. Mach Learn2023; 112(8): 2903–2931.
27.
TangLLiZPuH, et al.A dynamic pre-deployment strategy of UAVs based on multi-agent deep reinforcement learning. J Electron Inf Technol2023; 45(06): 2007–2015.
28.
MoonCAhnJ. Markov decision process-based potential field technique for UAV planning. Journal of the Korean Society for Industrial and Applied Mathematics2021; 25(4): 149–161.
29.
LiMBaiHKrishnamurthiN. A Markov decision process for the interaction between autonomous collision avoidance and delayed pilot commands. IFAC-PapersOnLine2019; 51(34): 378–383.
30.
BoutonMTumovaJKochenderferMJ. Point-based methods for model checking in partially observable Markov decision processes. Proc AAAI Conf Artif Intell2020; 34(06): 10061–10068.
31.
ChomikG. The future of collision avoidance ACAS X. Int J Eng Trends Technol2016; 39(5): 284–287.
32.
RTCA DO-260C. Minimum operational performance standards for 1090 MHz extended squitter automatic dependent surveillance - broadcast (ADS-B) and traffic information services - broadcast (TIS-B). Radio Technical Commission for Aeronautics, 2020. The RTCA DO-260C standard document is available for download via the following link: https://store.accuristech.com/standards/rtca-do-260c?product_id=2259818
33.
RTCA DO-386. Minimum operational performance standards for airborne collision avoidance system Xu (ACAS Xu). Radio Technical Commission for Aeronautics, 2020.
ZitarRAMohsenASeghrouchniAEF, et al.Intensive review of drones detection and tracking: Linear kalman filter versus nonlinear regression, an analysis case. Arch Comput Methods Eng2023; 30(5): 2811–2830.
