M. K. Abdel-Aziz, S. Samarakoon, C. Perfecto and M. Bennis, "Cooperative perception in Vehicular Networks using Multi-Agent Reinforcement Learning," 2020 54th Asilomar Conference on Signals, Systems, and Computers, 2020, pp. 408-412, doi: 10.1109/IEEECONF51394.2020.9443539
Cooperative perception in vehicular networks using multi-agent reinforcement learning
|Author:||Abdel-Aziz, Mohamed K.1; Samarakoon, Sumudu1; Perfecto, Cristina2;|
1Centre for Wireless Communications, University of Oulu, Finland
2University of the Basque Country UPV/EHU, Spain
|Online Access:||PDF Full Text (PDF, 3.9 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2021082744479
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2021-08-27
Cooperative perception plays a vital role in extending a vehicle’s sensing range beyond its line-of-sight. However, exchanging raw sensory data under limited communication resources is infeasible. Towards enabling an efficient cooperative perception, vehicles need to address fundamental questions such as: what sensory data needs to be shared? at which resolution? In this view, this paper proposes a reinforcement learning (RL)-based content selection of cooperative perception messages by utilizing a quadtree-based point cloud compression mechanism. Furthermore, we investigate the role of federated RL to enhance the training process. Simulation results show the ability of the RL agents to efficiently learn the message content selection that maximizes the satisfaction of the vehicles in terms of the received sensory information. It is also shown that federated RL improves the training process, where better policies can be achieved within the same amount of time compared to the non-federated approach.
Asilomar Conference on Signals, Systems & Computers
|Pages:||408 - 412|
54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020
Asilomar Conference on Signals, Systems and Computers
|Type of Publication:||
A4 Article in conference proceedings
|Field of Science:||
113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
This work was supported in part by the Academy of Finland project CARMA, and 6Genesis Flagship (grant no. 318927), in part by the INFOTECH project NOOR, in part by the EU-CHISTERA projects LeadingEdge and CONNECT, and in part by the Kvantum Institute strategic project SAFARI.
|Academy of Finland Grant Number:||
318927 (Academy of Finland Funding decision)
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.