Deep-Reinforcement-Learning-Based Reactive Collision Avoidance Controller for an Underactuated AUV Using Multibeam Forward-Looking Sonar
IEEE Internet of Things Journal · 01.09.2025 · 12 (17) · 36604-36616
DOI: 10.1109/jiot.2025.3583015 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.09.2025. Verfasst von Fei Huang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: National Science and Technology Major Project, National Natural Science Foundation of China, Shanghai Science and Technology program.
Abstract (Originalsprache)
This article investigates the application of deep reinforcement learning (RL) in the reactive collision avoidance control of an autonomous underwater vehicle (AUV) using multibeam forward-looking sonar (MBFLS). First, an efficient encoding method based on prior knowledge is proposed, which can extract low dimensional representations of obstacles from massive MBFLS detection data, thereby reducing the inference time of the reactive collision avoidance control policy represented by a neural network and improving their collision avoidance effect. On this basis, a state space, action space, and multiobjective reward function are customized for the reactive collision avoidance task of the AUV, and a simulation training environment is constructed. Considering that the contradiction between policy training and deployment is caused by unknown total disturbances, disturbance estimators based on the extended state observer is constructed, and a deployment scheme is designed to compensate for disturbances through both feedforward and feedback channels, ensuring that the policy learned in simulation can be applied to an actual AUV. Finally, combining the above components, a novel reactive collision avoidance method based on deep RL is proposed, and the effectiveness of the proposed method for obstacles of various shapes (both static and dynamic) is fully verified in three different unknown environments.
Förderung
- National Science and Technology Major Project
- National Natural Science Foundation of China
- Shanghai Science and Technology program
- Hainan Province Science and Technology Special Fund
Zitieren
APA
Huang, F., Cui, Y., Zhang, W., & Xu, J. (2025). Deep-Reinforcement-Learning-Based Reactive Collision Avoidance Controller for an Underactuated AUV Using Multibeam Forward-Looking Sonar. IEEE Internet of Things Journal, 12(17), 36604-36616. https://doi.org/10.1109/jiot.2025.3583015
Vancouver
Huang F, Cui Y, Zhang W, Xu J. Deep-Reinforcement-Learning-Based Reactive Collision Avoidance Controller for an Underactuated AUV Using Multibeam Forward-Looking Sonar. IEEE Internet of Things Journal. 2025;12(17):36604-36616. doi:10.1109/jiot.2025.3583015
BibTeX
@article{Huang2025,
author = {Huang, Fei and Cui, Yunfei and Zhang, Weidong and Xu, Jian},
title = {Deep-Reinforcement-Learning-Based Reactive Collision Avoidance Controller for an Underactuated AUV Using Multibeam Forward-Looking Sonar},
journal = {IEEE Internet of Things Journal},
year = {2025},
volume = {12},
number = {17},
pages = {36604--36616},
doi = {10.1109/jiot.2025.3583015}
}
EUVIMED