期刊
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
卷 24, 期 8, 页码 8580-8591出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2022.3202225
关键词
Target tracking; Sensors; Pollution; Oceans; Control systems; Collaboration; Training; Autonomous underwater vehicle; software-defined networking; centralized training decentralized execution; multiagent reinforcement learning; intelligent transportation systems
This paper presents how to use AUV swarm or multi-AUVs system to track underwater diffusion pollution and optimize the network architecture using SDN technology. The proposed CTDE architecture and self-attention-based SAC algorithm optimize system control and management. Evaluation results demonstrate the effectiveness of our approach in tracking equipotential lines and system performance compared to classical schemes.
The rapid development of intelligent underwater devices promotes marine exploitation activities, including marine resource exploitation, marine target tracking, etc. This work will present how to utilize the Autonomous Underwater Vehicle (AUV) swarm or multi-AUVs system to track the underwater diffusion pollution, especially the equipotential line of particular concentration. Different from most of the current research, in this work, we take the AUV swam as a network system and utilize the Software-Defined Networking (SDN) technique to optimize the network architecture, constructing an SDN-enabled AUV network Intelligent Transportation Systems (ITS). With the centralized management ability of the SDN technique, we propose the software-defined Centralized Training Decentralized Execution (CTDE) architecture based on the graph-based Soft Actor-Critic (SAC) algorithm to optimize the system control and management. To improve the computing and training efficiency, we embed the self-attention mechanism into the critic network construction, leading to a self-attention-based SAC algorithm. Evaluation results demonstrate that our proposed approach is able to exactly track the equipotential lines of a particular concentration in many categories (with different types of equipotential lines (including the shape, noise, and diffusion value)) of underwater diffusion fields. Meanwhile, our proposed approaches outperform some classical schemes in system awards, tracking errors, etc.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据