Title: A travel planning method for intelligent networked vehicles at unsignallised intersections based on transformer algorithm

Authors: Miao Wang; Chen Sun

Addresses: School of Transportation, Xinxiang Vocational and Technical College, Xinxiang, Henan, China ' College of Air and Missile Defense, Air Force Engineering University, Xi'an, Shaanxi, China

Abstract: In an environment without signal intersections, in order to improve the success rate of conflict avoidance and the cumulative value return of routes, this paper designs a travel planning method for intelligent networked vehicles based on transformer algorithm. The intersection environment information is collected by multi-sensor, and the high-precision environment map is generated by filtering and calibration. A predictive model is built, using TCN to capture local spatiotemporal features, and transformer analyses global dependencies to accurately predict the driving intentions of other vehicles. Based on the prediction results, the safe travel path is generated through multi-modal intention fusion, space-time collaborative trajectory generation, safety boundary adjustment and real-time planning. Experiments show that the conflict avoidance success rate of the vehicle is always 100%, and accumulated value return of the travelling path is closer to 1, indicating that the method realises the safe driving of the vehicle in the unsignalled traffic environment.

Keywords: unsignallised intersection; intelligent networked vehicles; travel planning; temporal convolutional network; transformer; multimodal intent fusion.

DOI: 10.1504/IJIPT.2025.150241

International Journal of Internet Protocol Technology, 2025 Vol.18 No.4, pp.220 - 227

Received: 31 Mar 2025
Accepted: 16 May 2025
Published online: 04 Dec 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article