Communication-Efficient Decision-Making of Digital Twin Assisted Internet of Vehicles: A Hierarchical Multi-Agent Reinforcement Learning Approach

作     者：Xiaoyuan Fu Quan Yuan Shifan Liu Baozhu Li Qi Qi Jingyu Wang Xiaoyuan Fu;Quan Yuan;Shifan Liu;Baozhu Li;Qi Qi;Jingyu Wang

作者机构：State Key Laboratory of Networking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of Integrated Services NetworksXidian UniversityXi’an 710071China Internet of Things&Smart City Innovation PlatformZhuhai Fudan Innovation InstituteZhuhai 519000China State Key Laboratory of High-End Server and Storage TechnologyJinan 250101China 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2023年第20卷第3期

页      面：55-68页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 081001[工学-通信与信息系统] 

基　　金：supported in part by the Natural Science Foundation of China under Grant 62001054,Grant 62272053 and Grant 61901191 in part by the Natural Science Foundation of Shandong Province of China under Grant ZR2020LZH005 in part by the Fundamental Research Funds for the Central Universities 

主　　题：digital twin Internet of Vehicles hierar-chical reinforcement learning 

摘      要：The connected autonomous vehicle is considered an effective way to improve transport safety and *** overcome the limited sensing and computing capabilities of individual vehicles,we design a digital twin assisted decision-making framework for Internet of Vehicles,by leveraging the integration of communication,sensing and *** this framework,the digital twin entities residing on edge can effectively communicate and cooperate with each other to plan sub-targets for their respective vehicles,while the vehicles only need to achieve the sub-targets by generating a sequence of atomic ***,we propose a hierarchical multiagent reinforcement learning approach to implement the framework,which can be trained in an end-to-end *** the proposed approach,the communication interval of digital twin entities could adapt to timevarying *** experiments on driving decision-making have been performed in traffic junction scenarios of different *** experimental results show that the proposed approach can largely improve collaboration efficiency while reducing communication overhead.