KJCKorea
Journal Central

@article{ART002398204},
author={Seungyoon Choi and Tuyen Le Pham and CHUNG TAECHOONG},
title={Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2018},
volume={23},
number={10},
pages={23-31},
doi={10.9708/jksci.2018.23.10.023}

TY - JOUR
AU - Seungyoon Choi
AU - Tuyen Le Pham
AU - CHUNG TAECHOONG
TI - Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms
JO - Journal of The Korea Society of Computer and Information
PY - 2018
VL - 23
IS - 10
PB - The Korean Society Of Computer And Information
SP - 23
EP - 31
SN - 1598-849X
AB - Recently, there have been many studies on machine learning. Among them, studies on reinforcement learning are actively worked. In this study, we propose a controller to control bicycle using DDPG (Deep Deterministic Policy Gradient) algorithm which is the latest deep reinforcement learning method. In this paper, we redefine the compensation function of bicycle dynamics and neural network to learn agents. When using the proposed method for data learning and control, it is possible to perform the function of not allowing the bicycle to fall over and reach the further given destination unlike the existing method. For the performance evaluation, we have experimented that the proposed algorithm works in various environments such as fixed speed, random, target point, and not determined. Finally, as a result, it is confirmed that the proposed algorithm shows better performance than the conventional neural network algorithms NAF and PPO.
KW - Reinforcement Learning;DDPG;Machine Learning;Bicycle Self Balancing;Deep Learning
DO - 10.9708/jksci.2018.23.10.023
ER -

Seungyoon Choi, Tuyen Le Pham and CHUNG TAECHOONG. (2018). Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms. Journal of The Korea Society of Computer and Information, 23(10), 23-31.

Seungyoon Choi, Tuyen Le Pham and CHUNG TAECHOONG. 2018, "Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms", Journal of The Korea Society of Computer and Information, vol.23, no.10 pp.23-31. Available from: doi:10.9708/jksci.2018.23.10.023

Seungyoon Choi, Tuyen Le Pham, CHUNG TAECHOONG "Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms" Journal of The Korea Society of Computer and Information 23.10 pp.23-31 (2018) : 23.

Seungyoon Choi, Tuyen Le Pham, CHUNG TAECHOONG. Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms. 2018; 23(10), 23-31. Available from: doi:10.9708/jksci.2018.23.10.023

Seungyoon Choi, Tuyen Le Pham and CHUNG TAECHOONG. "Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms" Journal of The Korea Society of Computer and Information 23, no.10 (2018) : 23-31.doi: 10.9708/jksci.2018.23.10.023

Seungyoon Choi; Tuyen Le Pham; CHUNG TAECHOONG. Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms. Journal of The Korea Society of Computer and Information, 23(10), 23-31. doi: 10.9708/jksci.2018.23.10.023

Seungyoon Choi; Tuyen Le Pham; CHUNG TAECHOONG. Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms. Journal of The Korea Society of Computer and Information. 2018; 23(10) 23-31. doi: 10.9708/jksci.2018.23.10.023

Seungyoon Choi, Tuyen Le Pham, CHUNG TAECHOONG. Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms. 2018; 23(10), 23-31. Available from: doi:10.9708/jksci.2018.23.10.023

Seungyoon Choi, Tuyen Le Pham and CHUNG TAECHOONG. "Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms" Journal of The Korea Society of Computer and Information 23, no.10 (2018) : 23-31.doi: 10.9708/jksci.2018.23.10.023