The Method of Intelligent Railway Alignment Path Generation Based on Deep Q Network

DOI

10.2991/978-94-6463-449-5_14How to use a DOI?

Keywords

Deep reinforcement learning; Intelligent line selection; Optimal path; DQN algorithm

Abstract

Traditional railway route selection requires manual fieldwork over long periods, which is physically demanding and subject to seasonal weather conditions, leading to an uneven annual production cycle and low efficiency. With the introduction of high-tech methods and the significant development of artificial intelligence, AI has become practical. Deep reinforcement learning, with its perceptual and decision-making capabilities, is well-suited to address route planning problems. It can be applied to modern route selection techniques by training the exploration ability of the established model using the DQN algorithm. The intelligent agent receives positive rewards when approaching the target point and negative rewards when moving away from it, aiming to optimize construction costs. Experimental results demonstrate that compared to manual selection, the intelligent route selection approach yields similar paths while significantly reducing labor costs and saving approximately 11.3% in construction expenses.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Tianxi Wang
AU  - Baocheng Wang
PY  - 2024
DA  - 2024/06/30
TI  - The Method of Intelligent Railway Alignment Path Generation Based on Deep Q Network
BT  - Proceedings of the 2024 8th International Conference on Civil Architecture and Structural Engineering (ICCASE 2024)
PB  - Atlantis Press
SP  - 142
EP  - 151
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-449-5_14
DO  - 10.2991/978-94-6463-449-5_14
ID  - Wang2024
ER  -