Hostname: page-component-857557d7f7-bkbbk Total loading time: 0 Render date: 2025-11-21T20:13:46.486Z Has data issue: false hasContentIssue false
  • English
  • Français

Real-time autonomous obstacle avoidance method for UAV in a three-dimensional dynamic environment

Published online by Cambridge University Press:  17 November 2025

G. Li Open the ORCID record for G. Li [Opens in a new window] ,
L. Ling Open the ORCID record for L. Ling [Opens in a new window]  and
F. Xu
G. Li*
Affiliation:
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics , Nanjing, China Shenzhen Research Institute, Nanjing University of Aeronautics and Astronautics, Shenzhen, China
L. Ling
Affiliation:
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics , Nanjing, China
F. Xu
Affiliation:
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics , Nanjing, China
*
Corresponding author: G. Li; Email: liguiyi@nuaa.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

Reinforcement learning (RL) has demonstrated computational efficiency and autonomy in solving unmanned aerial vehicle (UAV) obstacle avoidance problems. However, practical applications still remain challenges, such as three-dimensional manoeuvres, dynamic obstacles and kinematic constraints. This paper proposes a real-time obstacle avoidance method based on RL and a kinematic model, where the RL framework outputs 3D-axis velocity to enable continuous UAV manoeuver control. To perceive large-scale, highly dynamic obstacles, we establish a 3D safety separation model and construct a modular observation matrix to enhance perception capability. The Soft Actor-Critic (SAC) algorithm is adopted to enhance stochastic exploration in high-dimensional state space while incorporating flight uncertainty. Under simulation, the proposed method effectively avoids dynamic obstacles. The optimised state space boosts learning speed and performance. This provides an effective solution for UAV autonomous obstacle avoidance in complex environments.

Keywords

air traffic managementreinforcement learningSoft-Actor-Critic algorithmthree-dimensional dynamic environment avoidanceUAV obstacle avoidance method

Information

Type
Research Article
Information
The Aeronautical Journal , First View , pp. 1 - 18
Check for updates
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of Royal Aeronautical Society

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Guebsi, R., et al. Drones in precision agriculture: A comprehensive review of applications, technologies, and challenges, Drones, 2024, 8, p 686.10.3390/drones8110686CrossRefGoogle Scholar
Jahani, H., et al. Exploring the role of drones and UAVs in logistics and supply chain management: a novel text-based literature review, Int. J. Prod. Res., 2025, 63, pp 1873–1897.10.1080/00207543.2024.2373425CrossRefGoogle Scholar
Zhang, N., et al. End-to-end nano-drone obstacle avoidance for indoor exploration, Drones, 2024, 8, p 33. https://doi.org/10.3390/drones8020033 CrossRefGoogle Scholar
Liu, Y., Bai, J. and Sun, F. Visual localization method for unmanned aerial vehicles in urban scenes based on shape and spatial relationship matching of buildings, Remote Sens., 2024, 16, p 3065.CrossRefGoogle Scholar
Wang, K., et al. UAV-based simultaneous localization and mapping in outdoor environments: A systematic scoping review, J. Field Rob., 2024, 41, pp 1617–1642.10.1002/rob.22325CrossRefGoogle Scholar
Nithasree, S., et al. Path planning method for static obstacle avoidance using bezier spline interpolation in UAVs, J. Mines Metals Fuels, 2025, 71, pp 47–52.10.18311/jmmf/2023/47976CrossRefGoogle Scholar
Yang, F., et al. Obstacle avoidance path planning for UAV based on improved RRT algorithm, Discrete Dyn. Nat. Soc., 2022, 2022, pp 1–9.10.1155/2022/4544499CrossRefGoogle Scholar
Jayaweera, H.M. and Hanoun, S. Real-time obstacle avoidance for Unmanned Aerial Vehicles (UAVs), 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2021 of Conference, pp 2622–2627.10.1109/SMC52423.2021.9659197CrossRefGoogle Scholar
Choi, Y., Jimenez, H. and Mavris, D.N. Two-layer obstacle collision avoidance with machine learning for more energy-efficient unmanned aircraft trajectories, Rob. Auton. Syst., 2017, 98, pp 158–173.10.1016/j.robot.2017.09.004CrossRefGoogle Scholar
Yu, X. and Luo, W. Reinforcement learning-based multi-strategy cuckoo search algorithm for 3D UAV path planning, Expert Syst. Appl., 2023, 223, p 119910. 10.1016/j.eswa.2023.119910CrossRefGoogle Scholar
Mao, J., Jia, Z. and Gu, H. Robust UAV Path Planning with Obstacle Avoidance for Emergency Rescue, 2025, arXiv preprint arXiv:2501.09338.10.1109/WCNC61545.2025.10978825CrossRefGoogle Scholar
Xu, X., et al. A multi-objective evolutionary algorithm based on dimension exploration and discrepancy evolution for UAV path planning problem, Inf. Sci., 2024, 657, p 119977.10.1016/j.ins.2023.119977CrossRefGoogle Scholar
Farooq, F., et al. Intelligent planning of UAV flocks via transfer learning and multi-objective optimization, Arabian J. Sci. Eng., 2025, pp 1–18.Google Scholar
Wang, J., et al. An autonomous UAV obstacle avoidance trajectory planning method based on convex optimized particle Swarm algorithm, Int. J. High Speed Electron. Syst., 2025, p 2540246.10.1142/S0129156425402463CrossRefGoogle Scholar
Aldao, E., et al. UAV obstacle avoidance algorithm to navigate in dynamic building environments, Drones, 2022, 6, p 16.10.3390/drones6010016CrossRefGoogle Scholar
Jia, T., et al. Dynamic obstacle avoidance path planning for UAV, International Conference on Unmanned Systems (ICUS), 2020, pp 814–818.CrossRefGoogle Scholar
Ouahouah, S., et al. Deep-reinforcement-learning-based collision avoidance in UAV environment, IEEE Internet Things J., 2022, 9, pp 4015–4030.10.1109/JIOT.2021.3118949CrossRefGoogle Scholar
Krishnany, S., et al. Air Learning: A Deep Reinforcement Learning Gym for Autonomous Aerial Robot Visual Navigation, 2022, 110, pp 2501–2540.10.1007/s10994-021-06006-6CrossRefGoogle Scholar
Cetin, E., et al. Drone navigation and avoidance of obstacles through deep reinforcement learning, IEEE/AIAA 38th Digital Avionics Systems Conference 2019 of Conference, pp 1–7.10.1109/DASC43569.2019.9081749CrossRefGoogle Scholar
Sonny, A., Yeduri, S.R. and Cenkeramaddi, L.R. Q-learning-based unmanned aerial vehicle path planning with dynamic obstacle avoidance, Appl. Soft Comput., 2023, 147, p 110773.10.1016/j.asoc.2023.110773CrossRefGoogle Scholar
Kalidas, A.P., et al. Deep reinforcement learning for vision-based navigation of UAVs in avoiding stationary and mobile obstacles, Drones, 2023, 7, p 245.10.3390/drones7040245CrossRefGoogle Scholar
Gao, Y., et al. Autonomous obstacle avoidance algorithm for unmanned aerial vehicles based on deep reinforcement learning, Eng. Lett., 2024, 32, pp 650–660.Google Scholar
Wang, J., et al. Vision-based deep reinforcement learning of Unmanned Aerial Vehicle (UAV) autonomous navigation using privileged information, Drones, 2024, 8, p 782.10.3390/drones8120782CrossRefGoogle Scholar
Sabzekar, S., et al. A deep reinforcement learning approach for UAV path planning incorporating vehicle dynamics with acceleration control, Unmanned Syst., 2023, 12, pp 477–498.10.1142/S2301385024420044CrossRefGoogle Scholar
Li, X., et al. UAV obstacle avoidance by human-in-the-loop reinforcement in arbitrary 3D environment, 2023 42nd Chinese Control Conference (CCC) 2023 of Conference, pp 2589–2695.10.23919/CCC58697.2023.10240962CrossRefGoogle Scholar
Gao, H., et al. Learning based multi-obstacle avoidance of unmanned aerial vehicles with a novel reward, Complex Eng. Syst., 2023, 3, p 21.10.20517/ces.2023.24CrossRefGoogle Scholar
Chen, Y., et al. General real-time three-dimensional multi-aircraft conflict resolution method using multi-agent reinforcement learning, Transp. Res. Part C: Emerg. Technol., 2023, 157, pp 104367–104395.10.1016/j.trc.2023.104367CrossRefGoogle Scholar