Autonomous vehicles (AVs) rely on multi-modal fusion for safety, but current visual and optical sensors fail to detect road-induced excitations which are critical for vehicles' dynamic control. Inspired by human synesthesia, we propose the Synesthesia of Vehicles (SoV), a novel framework to predict tactile excitations from visual inputs for autonomous vehicles. We develop a cross-modal spatiotemporal alignment method to address temporal and spatial disparities. Furthermore, a visual-tactile synesthetic (VTSyn) generative model using latent diffusion is proposed for unsupervised high-quality tactile data synthesis. A real-vehicle perception system collected a multi-modal dataset across diverse road and lighting conditions. Extensive experiments show that VTSyn outperforms existing models in temporal, frequency, and classification performance, enhancing AV safety through proactive tactile perception.
@article{arxiv.2602.01832,
title = {Synesthesia of Vehicles: Tactile Data Synthesis from Visual Inputs},
author = {Rui Wang and Yaoguang Cao and Yuyi Chen and Jianyi Xu and Zhuoyang Li and Jiachen Shang and Shichun Yang},
journal= {arXiv preprint arXiv:2602.01832},
year = {2026}
}