Train Station Parking Approach Based on Fuzzy Reinforcement Learning Algorithms

Train station parking (TSP) accuracy is important to enhance the efficiency of train operation and the safety of passengers for urban rail transit, while TSP is always subject to a series of uncertain factors. To increase the parking accuracy, robustness and self-learning ability, we propose a new t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE International Conference on Control and Automation (Print) S. 1411 - 1416
Hauptverfasser: Yin, Jiateng, Su, Shuai, Li, Kaicheng, Tang, Tao
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.07.2019
Schlagworte:
Adaptation models
Computational modeling
fuzzy function
Q-learning
Rails
Reinforcement learning
Resistance
Safety
Silicon
Train station parking
ISSN:1948-3457
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Train station parking (TSP) accuracy is important to enhance the efficiency of train operation and the safety of passengers for urban rail transit, while TSP is always subject to a series of uncertain factors. To increase the parking accuracy, robustness and self-learning ability, we propose a new train parking approach by using the reinforcement learning (RL) theory. Three algorithms were developed, involving a stochastic optimal selection algorithm (SOSA), a Q-learning algorithm (QLA) and a fuzzy function based Q-learning algorithm (FQLA) in order to reduce the parking error in urban rail transit. Meanwhile, five braking rates are adopted as the action vector of the three algorithms and some statistical indices are developed to evaluate parking errors. Parking results show that the parking errors of the three algorithms are all within the ±30cm, which meet the requirement of urban rail transit.
ISSN:1948-3457
DOI:10.1109/ICCA.2019.8899712