Deep-Reinforcement-Learning-Based Distributed Vehicle Position Controls for Coverage Expansion in mmWave V2X

Akihito TAYA; Takayuki NISHIO; Masahiro MORIKURA; Koji YAMAMOTO

doi:10.1587/transcom.2018EBP3299

Deep-Reinforcement-Learning-Based Distributed Vehicle Position Controls for Coverage Expansion in mmWave V2X

Akihito TAYA, Takayuki NISHIO, Masahiro MORIKURA, Koji YAMAMOTO

Full Text Views

0

Cite this

Summary :

In millimeter wave (mmWave) vehicular communications, multi-hop relay disconnection by line-of-sight (LOS) blockage is a critical problem, particularly in the early diffusion phase of mmWave-available vehicles, where not all vehicles have mmWave communication devices. This paper proposes a distributed position control method to establish long relay paths through road side units (RSUs). This is realized by a scheme via which autonomous vehicles change their relative positions to communicate with each other via LOS paths. Even though vehicles with the proposed method do not use all the information of the environment and do not cooperate with each other, they can decide their action (e.g., lane change and overtaking) and form long relays only using information of their surroundings (e.g., surrounding vehicle positions). The decision-making problem is formulated as a Markov decision process such that autonomous vehicles can learn a practical movement strategy for making long relays by a reinforcement learning (RL) algorithm. This paper designs a learning algorithm based on a sophisticated deep reinforcement learning algorithm, asynchronous advantage actor-critic (A3C), which enables vehicles to learn a complex movement strategy quickly through its deep-neural-network architecture and multi-agent-learning mechanism. Once the strategy is well trained, vehicles can move independently to establish long relays and connect to the RSUs via the relays. Simulation results confirm that the proposed method can increase the relay length and coverage even if the traffic conditions and penetration ratio of mmWave communication devices in the learning and operation phases are different.

Publication: IEICE TRANSACTIONS on Communications Vol.E102-B No.10 pp.2054-2065

Publication Date: 2019/10/01

Publicized: 2019/04/17

Online ISSN: 1745-1345

DOI: 10.1587/transcom.2018EBP3299

Type of Manuscript: PAPER

Category: Network Management/Operation

Authors

Akihito TAYA
  Kyoto University
Takayuki NISHIO
  Kyoto University
Masahiro MORIKURA
  Kyoto University
Koji YAMAMOTO
  Kyoto University

Keyword

vehicular networks, autonomous vehicles, mmWave communications, multi-hop relaying, position controls, deep reinforcement learning

Cite this

Copy

Akihito TAYA, Takayuki NISHIO, Masahiro MORIKURA, Koji YAMAMOTO, "Deep-Reinforcement-Learning-Based Distributed Vehicle Position Controls for Coverage Expansion in mmWave V2X" in IEICE TRANSACTIONS on Communications, vol. E102-B, no. 10, pp. 2054-2065, October 2019, doi: 10.1587/transcom.2018EBP3299.
Abstract: In millimeter wave (mmWave) vehicular communications, multi-hop relay disconnection by line-of-sight (LOS) blockage is a critical problem, particularly in the early diffusion phase of mmWave-available vehicles, where not all vehicles have mmWave communication devices. This paper proposes a distributed position control method to establish long relay paths through road side units (RSUs). This is realized by a scheme via which autonomous vehicles change their relative positions to communicate with each other via LOS paths. Even though vehicles with the proposed method do not use all the information of the environment and do not cooperate with each other, they can decide their action (e.g., lane change and overtaking) and form long relays only using information of their surroundings (e.g., surrounding vehicle positions). The decision-making problem is formulated as a Markov decision process such that autonomous vehicles can learn a practical movement strategy for making long relays by a reinforcement learning (RL) algorithm. This paper designs a learning algorithm based on a sophisticated deep reinforcement learning algorithm, asynchronous advantage actor-critic (A3C), which enables vehicles to learn a complex movement strategy quickly through its deep-neural-network architecture and multi-agent-learning mechanism. Once the strategy is well trained, vehicles can move independently to establish long relays and connect to the RSUs via the relays. Simulation results confirm that the proposed method can increase the relay length and coverage even if the traffic conditions and penetration ratio of mmWave communication devices in the learning and operation phases are different.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2018EBP3299/_p

Copy

@ARTICLE{e102-b_10_2054,
author={Akihito TAYA, Takayuki NISHIO, Masahiro MORIKURA, Koji YAMAMOTO, },
journal={IEICE TRANSACTIONS on Communications},
title={Deep-Reinforcement-Learning-Based Distributed Vehicle Position Controls for Coverage Expansion in mmWave V2X},
year={2019},
volume={E102-B},
number={10},
pages={2054-2065},
abstract={In millimeter wave (mmWave) vehicular communications, multi-hop relay disconnection by line-of-sight (LOS) blockage is a critical problem, particularly in the early diffusion phase of mmWave-available vehicles, where not all vehicles have mmWave communication devices. This paper proposes a distributed position control method to establish long relay paths through road side units (RSUs). This is realized by a scheme via which autonomous vehicles change their relative positions to communicate with each other via LOS paths. Even though vehicles with the proposed method do not use all the information of the environment and do not cooperate with each other, they can decide their action (e.g., lane change and overtaking) and form long relays only using information of their surroundings (e.g., surrounding vehicle positions). The decision-making problem is formulated as a Markov decision process such that autonomous vehicles can learn a practical movement strategy for making long relays by a reinforcement learning (RL) algorithm. This paper designs a learning algorithm based on a sophisticated deep reinforcement learning algorithm, asynchronous advantage actor-critic (A3C), which enables vehicles to learn a complex movement strategy quickly through its deep-neural-network architecture and multi-agent-learning mechanism. Once the strategy is well trained, vehicles can move independently to establish long relays and connect to the RSUs via the relays. Simulation results confirm that the proposed method can increase the relay length and coverage even if the traffic conditions and penetration ratio of mmWave communication devices in the learning and operation phases are different.},
keywords={},
doi={10.1587/transcom.2018EBP3299},
ISSN={1745-1345},
month={October},}

Copy

TY - JOUR
TI - Deep-Reinforcement-Learning-Based Distributed Vehicle Position Controls for Coverage Expansion in mmWave V2X
T2 - IEICE TRANSACTIONS on Communications
SP - 2054
EP - 2065
AU - Akihito TAYA
AU - Takayuki NISHIO
AU - Masahiro MORIKURA
AU - Koji YAMAMOTO
PY - 2019
DO - 10.1587/transcom.2018EBP3299
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E102-B
IS - 10
JA - IEICE TRANSACTIONS on Communications
Y1 - October 2019
AB - In millimeter wave (mmWave) vehicular communications, multi-hop relay disconnection by line-of-sight (LOS) blockage is a critical problem, particularly in the early diffusion phase of mmWave-available vehicles, where not all vehicles have mmWave communication devices. This paper proposes a distributed position control method to establish long relay paths through road side units (RSUs). This is realized by a scheme via which autonomous vehicles change their relative positions to communicate with each other via LOS paths. Even though vehicles with the proposed method do not use all the information of the environment and do not cooperate with each other, they can decide their action (e.g., lane change and overtaking) and form long relays only using information of their surroundings (e.g., surrounding vehicle positions). The decision-making problem is formulated as a Markov decision process such that autonomous vehicles can learn a practical movement strategy for making long relays by a reinforcement learning (RL) algorithm. This paper designs a learning algorithm based on a sophisticated deep reinforcement learning algorithm, asynchronous advantage actor-critic (A3C), which enables vehicles to learn a complex movement strategy quickly through its deep-neural-network architecture and multi-agent-learning mechanism. Once the strategy is well trained, vehicles can move independently to establish long relays and connect to the RSUs via the relays. Simulation results confirm that the proposed method can increase the relay length and coverage even if the traffic conditions and penetration ratio of mmWave communication devices in the learning and operation phases are different.
ER -