V2X Communication and LLM-Based Driver Training System: Providing Scenario Semantic Explanations and Challenge Task Generation for Novice Drivers

Zihuan Cao

doi:10.47297/taposatWSP2633-456943.20250610

PDF
Export
Share
Collection
Album

V2X Communication and LLM-Based Driver Training System: Providing Scenario Semantic Explanations and Challenge Task Generation for Novice Drivers

Volume 6, Issue 10

Views: 0 Downloads: 0

V2X Communication and LLM-Based Driver Training System: Providing Scenario Semantic Explanations and Challenge Task Generation for Novice Drivers
V2X Communication and LLM-Based Driver Training System: Providing Scenario Semantic Explanations and Challenge Task Generation for Novice Drivers
Portland College, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, 210023, China
Vol. 6, Issue 10, Pages: 219-223(2025)
Published：30 October 2025
DOI：10.47297/taposatWSP2633-456943.20250610
Accepted：

Scan QR Code

Cao Zihuan.V2X Communication and LLM-Based Driver Training System: Providing Scenario Semantic Explanations and Challenge Task Generation for Novice Drivers[J].Theory and Practice of Science and Technology,2025,06(10):219-223.
DOI：

Cao Zihuan.V2X Communication and LLM-Based Driver Training System: Providing Scenario Semantic Explanations and Challenge Task Generation for Novice Drivers[J].Theory and Practice of Science and Technology,2025,06(10):219-223. DOI： 10.47297/taposatWSP2633-456943.20250610.

摘要

Abstract

In today's era

autonomous driving technology

semantic communication

and large language models are advancing rapidly. Against this backdrop

driving training systems face both unprecedented opportunities and new challenges. Novice drivers

who are just beginning to learn

often encounter situations where they do not know how to respond or lack sufficient reaction time in complex and dynamic traffic environments. Traditional driving training methods are relatively rigid and struggle to meet the specific needs of novice drivers in these areas. This paper proposes an innovative dynamic driving task generation training system based on the integration of V2X communication and lightweight large language models. This system processes V2X communication data in real-time

converts it into natural language scenario explanations

and dynamically generates personalized driving tasks. It enhances novice drivers' comprehension of complex driving scenarios

thereby improving the timeliness and effectiveness of driving training. This paper details the system architecture

research methodology

and experimental results

validating its practicality and demonstrating its potential in novice driver training.

关键词

Keywords

references

Bintoro, K.B.Y., Overview of Vehicle-to-Everything Communication: Technological Advancements, Applications, and Future Prospects in Intelligent Transportation Systems. JISA (Journal of Informatics and Science), 2025.8 (1): pp. 31-41.

Ibrahim Ali, Q. and H. M. Mohammed, Enhancing Road Safety and Network Intelligence through Vehicle-to-Everything (V2X) Communication: Architectures, Models, and Performance Analysis. Transportation Development R esearch, 2025.3 (1): p. 1-13.

Krasniuk, S., et al., The effectiveness of driving simulator training on driving skills and safety in young novice drivers: A systematic review of interventions. Journal of Safety Research, 2024.91 : pp. 20-37.

Gangadharaiah, R., et al., Exploring the Benefits of a Simulator-Based Emergency Braking Exercise with Novice Teen Drivers. Safety, 2024.10 (1): p. 14.

Xu, Z., et al., Personalizing Driver Agent Using Large Language Models for Driving Safety and Smarter Human–Machine Interactions. IEEE Intelligent Transportation Systems Magazine, 2025.17 (4): pp. 96-111.

Yadav, S. and R. Rishi, Joint mode selection and resource allocation for cellular V2X communication using distributed deep reinforcement learning under 5G and beyond networks. Computer Communications, 2024.221 : pp. 54-65.

Jung, C., et al., V2X-Communication-Aided Autonomous Driving: System Design and Experimental Validation. Sensors, 2020.20 (10): p. 2903.

Ziwen, L., Review of C-V2X Research on Intelligent Connected Vehicles. Computer Science and Technology, 2023.

Muslam, M.M.A., Enhancing Security in Vehicle-to-Vehicle Communication: A Comprehensive Review of Protocols and Techniques. Vehicles, 2024.6 (1): pp. 450-467.

Chen, J., Comparison and Optimization of DSRC and C-V2X Technologies: Current Status, Challenges, and Future Prospects. Academic Journal of Science and Technology, 2024.13 (2): pp. 42-50.

Miao, L., et al., How Does C-V2X Help Autonomous Driving to Avoid Accidents? Sensors, 2022.22 (2): p. 686.

You, J., et al., V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models. undefined, 2024.

Even-Mendoza, K., et al., LLM-Guided Genetic Improvement: Envisioning Semantic Aware Automated Software Evolution. undefined, 2025.

Tang, W., Analysis of Communication Requirements and Key Technologies for V2X in Autonomous Driving. Science and Technology of Engineering, Chemistry and Environmental Protection, 2025. 1(4).

Xu, Z., et al., DriveGPT4-V2: Harnessing Large Language Model Capabilities for Enhanced Closed-Loop Autonomous Driving. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025: pp. 17261-17270.

Dosovitskiy, A., et al., CARLA: An Open Urban Driving Simulator. undefined, 2017.

Czechowski, P., et al., Deep Reinforcement and IL for Autonomous Driving: A Review in the CARLA Simulation Environment. Applied Sciences, 2025.15 (16): p. 8972.

Alert me when the article has been cited

Submit

No data

Related Author

No data

Related Institution

No data

⁰