A Method of Reference Trajectory Construction for the Path-Following of Virtual Rail Train
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Existing methods for train trajectory generation, such as visual tracking, magnetic nail positioning, and fusion with high-definition maps, all rely on infrastructure like ground markings, magnetic nail installations, or global navigation satellite systems (GNSS). Consequently, these approaches are susceptible to environmental interference, which can distort road recognition and destabilize trajectory generation. Furthermore, the high costs of associated infrastructure hinder their widespread engineering adoption. To address these limitations, this paper proposes a novel reference trajectory construction method for path tracking of virtual rail train , which comprises road simplification and segmentation, information processing, and digital construction. Firstly, a framework for reference trajectory construction was established, which supports digital construction of track within a designated distance ahead of and behind the train by acquiring basic road information and combining it with real-time train position and attitude, thereby eliminating the complex road processing required by existing methods. Secondly, a reference trajectory generation algorithm was developed to enable trains for accurate digital construction following the acquisition of basic information. Finally, a virtual simulation platform was built using Matlab, and realistic road environments were created using diverse road segment data to validate the proposed method. Research results demonstrate that the method enables trains to perform real-time digital construction of reference trajectories with excellent response speed.
Fields of Study & Subjects
Vehicle Dynamics and Control Systems
Autonomous Vehicle Technology and Safety
Control and Dynamics of Mobile Robots
Publication details
- Journal / source
- DOAJ (DOAJ: Directory of Open Access Journals)
- Publication date
- 1 February 2026
- Language
- ZH