Authors: Genjia Liu, Yue Hu, Chenxin Xu, Weibo Mao, Junhao Ge, Zhengxiang Huang, Yifan Lu, Yinda Xu, Junkai Xia, Yafei Wang, Siheng Chen

Published on: April 15, 2024

Impact Score: 8.0

Arxiv code: Arxiv:2404.09496

Summary

• What is new: Introduction of V2Xverse, a simulation platform, and CoDriving, a new system for collaborative autonomous driving that significantly improves driving performance.
• Why this is important: The potential of vehicle-to-everything-aided autonomous driving (V2X-AD) is underutilized due to lack of optimal information sharing strategies.
• What the research proposes: Introducing a machine learning approach that optimizes the information sharing strategy via a novel simulation platform (V2Xverse) and a collaborative driving system (CoDriving).
• Results: CoDriving improves driving score by 62.49% and reduces pedestrian collision rate by 53.50% compared to state-of-the-art methods under various communication conditions.

Technical Details

Technological frameworks used: V2Xverse simulation platform, CoDriving system for integrated V2X communication

Models used: End-to-end collaborative driving models

Data used: Generated data facilitating the training and testing of V2X-AD

Potential Impact

Automotive and communication technology markets, particularly companies in autonomous driving and vehicle communication systems.

Want to implement this idea in a business?

We have generated a startup concept here: CommuniDrive.