VTire: A Bimodal Visuotactile Tire with High-Resolution Sensing Capability

Tires are one of the most important components of vehicles, and developing a smart tire equipped with high-resolution and multi-modal sensing capabilities is vital for enhancing a vehicle’s ability to sense and search its environment. This paper introduces a novel sensing tire that leverages visuotactile sensing, enabling terrain recognition, crack detection, load sensing, and breakage detection. This tire can simultaneously capture tactile information, RGB data, and depth data. We optimize the material and structure of the tire to ensure it possesses outstanding elasticity, toughness, hardness, and transparency. In terms of algorithms, we have developed a transformer-based multimodal classification algorithm, a load detection method based on finite element analysis, and a contact segmentation algorithm. Furthermore, we constructed an intelligent mobile platform to validate the system's effectiveness and developed visual and tactile datasets in complex terrains. The experimental results show that our multimodal terrain sensing algorithm can achieve a classification accuracy of 99.2%, a 98% success rate in object search, and the ability to withstand tire loading weights exceeding 35kg.