Asynchronous Deep Reinforcement Learning for the Mobile Robot Navigation with Supervised Auxiliary Tasks

被引：0

作者：

Tongloy, T. ^{[1
]}

Chuwongin, S. ^{[1
]}

Jaksukam, K. ^{[1
]}

Chousangsuntorn, C. ^{[2
]}

Boonsang, S. ^{[2
]}

机构：

[1] King Mongkuts Inst Technol Ladkrabang, Coll Adv Mfg Innovat AMI, Ctr Ind Robots & Automat CiRA, Bangkok, Thailand

[2] King Mongkuts Inst Technol Ladkrabang, Fac Engn, Dept Elect Engn, Bangkok, Thailand

来源：

2017 2ND INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION ENGINEERING (ICRAE) | 2017年

关键词：

component; asynchronous reinforcement learning; GA3C; ROS; supervised auxiliary tasks; mobile robot navigation;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we present the method based on asynchronous deep reinforcement learning adapted for the mobile robot navigation with supervised auxiliary tasks. We apply the hybrid Asynchronous Advantage Actor-Critic (A3C) algorithm CPU/GPU based on TensorFlow. The mobile robot is simulated as the navigation tasks on the OpenAI-Gym-Gazebo-based environment with the collaboration with ROS Multimaster. The supervised auxiliary tasks include the depth predictions and the robot position estimation. The simulated mobile robot shows the capability to learn to navigate only the input from raw RGB-image and also perform recognition of the place on the map. We also show that the combination of all possible auxiliary tasks leads to the different learning rate.

引用

页码：68 / 72

页数：5

共 50 条

[41] Deep Reinforcement Learning For Visual Navigation of Wheeled Mobile Robots
Nwaonumah, Ezebuugo
Samanta, Biswanath
[J]. IEEE SOUTHEASTCON 2020, 2020,
[42] Mapless navigation based on deep reinforcement learning for mobile robots
Hu, Gao-Ming
Cai, Ke-Wei
Wang, Fang
Kang, Yu-Wei
Zhang, Jia-Xu
Jin, Zhaoyi
Lin, Yuan-Shan
[J]. Kongzhi yu Juece/Control and Decision, 2024, 39 (03): : 985 - 993
[43] The strategy entropy of reinforcement learning for mobile robot navigation in complex environments
Zhuang, X
[J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-4, 2005, : 1742 - 1747
[44] Fuzzy Genetic Network Programming with Reinforcement Learning for Mobile Robot Navigation
Sendari, Siti
Mabu, Shingo
Hirasawa, Kotaro
[J]. 2011 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2011, : 2243 - 2248
[45] Socially compliant mobile robot navigation via inverse reinforcement learning
Kretzschmar, Henrik
Spies, Markus
Sprunk, Christoph
Burgard, Wolfram
[J]. INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2016, 35 (11): : 1352 - 1370
[46] A reinforcement learning with adaptive state space construction for mobile robot navigation
Li, Guizhi
Pang, Jie
[J]. PROCEEDINGS OF THE 2006 IEEE INTERNATIONAL CONFERENCE ON NETWORKING, SENSING AND CONTROL, 2006, : 84 - 88
[47] MOBILE ROBOT NAVIGATION IN HILLY TERRAIN USING REINFORCEMENT LEARNING TECHNIQUES
Tennety, Srinivas
Kumar, Manish
[J]. PROCEEDINGS OF THE ASME DYNAMIC SYSTEMS AND CONTROL CONFERENCE AND BATH/ASME SYMPOSIUM ON FLUID POWER AND MOTION CONTROL (DSCC 2011), VOL 2, 2012, : 81 - 86
[48] Self-Learning Robot Autonomous Navigation with Deep Reinforcement Learning Techniques
Pintos Gomez de las Heras, Borja
Martinez-Tomas, Rafael
Cuadra Troncoso, Jose Manuel
[J]. APPLIED SCIENCES-BASEL, 2024, 14 (01):
[49] Deep reinforcement learning for indoor mobile robot path planning
[J]. Guo, Jing (jing.guo@gdut.edu.cn), 1600, MDPI AG (20):
[50] Supervised Deep Learning with Auxiliary Networks
Zhang, Junbo
Tian, Guangjian
Mu, Yadong
Fan, Wei
[J]. PROCEEDINGS OF THE 20TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (KDD'14), 2014, : 353 - 361

← 1 2 3 4 5 →