Drone-Assisted Lane Change Maneuver using Reinforcement Learning with Dynamic Reward Function

被引：1

作者：

Hao, Jialin ^{[1
]}

Naja, Rola ^{[2
,3
]}

Zeghlache, Djamal ^{[1
]}

机构：

[1] Inst Polytech Paris, Telecom SudParis, Palaiseau, France

[2] ECE Paris Res Ctr, Paris, France

[3] Univ Versailles St Quentin, Li Parad Lab, Versailles, France

来源：

2022 18TH INTERNATIONAL CONFERENCE ON WIRELESS AND MOBILE COMPUTING, NETWORKING AND COMMUNICATIONS (WIMOB) | 2022年

关键词：

lane change; reinforcement learning; dynamic reward function;

D O I：

10.1109/WIMOB55322.2022.9941534

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper provides a Lane Change Assistance (LCA) platform that communicates with Unmanned Aerial Vehicles (UAV). The proposed platform is based on a reinforcement learning technique, where a Deep Q-Network (DQN) is trained to make lane change decisions. The reward function of the DQN agent considers safety, comfort and efficiency perspectives. Specifically, the safety reward, based on the road vehicular density, is adapted dynamically by the drone during the training phase. Performance analysis proves that the proposed platform improves the total travel time while reducing the collision rate and responding to urgent lane changes in a timely manner.

引用

页数：7

共 50 条

[11] Drone-assisted adaptive object detection and privacy-preserving surveillance in smart cities using whale-optimized deep reinforcement learning techniques
Ahmed Abu-Khadrah
Ahmad Al-Qerem
Mohammad R. Hassan
Ali Mohd Ali
Muath Jarrah
Scientific Reports, 15 (1)
[12] Deep Reinforcement Learning Reward Function Design for Autonomous Driving in Lane-Free Traffic
Karalakou, Athanasia
Troullinos, Dimitrios
Chalkiadakis, Georgios
Papageorgiou, Markos
SYSTEMS, 2023, 11 (03):
[13] Automated Lane Change Decision Making using Deep Reinforcement Learning in Dynamic and Uncertain Highway Environment
Alizadeh, Ali
Moghadam, Majid
Bicer, Yunus
Ure, Nazim Kemal
Yavas, Ugur
Kurtulus, Can
2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2019, : 1399 - 1404
[14] Reward Function Using Inverse Reinforcement Learning and Fuzzy Reasoning
Kato, Yuta
Kanoh, Masayoshi
Nakamura, Tsuyoshi
2020 JOINT 11TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND INTELLIGENT SYSTEMS AND 21ST INTERNATIONAL SYMPOSIUM ON ADVANCED INTELLIGENT SYSTEMS (SCIS-ISIS), 2020, : 222 - 227
[15] Automatic Lane Change Maneuver in Dynamic Environment Using Model Predictive Control Method
Li, Zhaolun
Jiang, Jingjing
Chen, Wen-Hua
2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 2384 - 2389
[16] Imitation of Real Lane-Change Decisions Using Reinforcement Learning
Zhao, Lu
Farhi, Nadir
Christoforou, Zoi
Haddadou, Nadia
IFAC PAPERSONLINE, 2021, 54 (02): : 203 - 209
[17] Modeling Driver Lane Change Behavior Using Inverse Reinforcement Learning
Zhou, Zhaodong
Chen, Jun
2024 IEEE 3RD INTERNATIONAL CONFERENCE ON COMPUTING AND MACHINE INTELLIGENCE, ICMI 2024, 2024,
[18] Dynamic Lane Reversal: A reinforcement learning approach
Katzilieris, Konstantinos
Kampitakis, Emmanouil
Vlahogianni, Eleni I.
2023 8TH INTERNATIONAL CONFERENCE ON MODELS AND TECHNOLOGIES FOR INTELLIGENT TRANSPORTATION SYSTEMS, MT-ITS, 2023,
[19] A Dynamic Adjusting Reward Function Method for Deep Reinforcement Learning with Adjustable Parameters
Hu, Zijian
Wan, Kaifang
Gao, Xiaoguang
Zhai, Yiwei
MATHEMATICAL PROBLEMS IN ENGINEERING, 2019, 2019
[20] Authenticating Drone-Assisted Internet of Vehicles Using Elliptic Curve Cryptography and Blockchain
El-Zawawy, Mohamed A.
Brighente, Alessandro
Conti, Mauro
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2023, 20 (02): : 1775 - 1789

← 1 2 3 4 5 →