Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Liang Jiaen, Weihuang, Yining Wang, Junnan Zhu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

We present Pluskin, a machine-embroidered plush skin that transforms the surface of a companion robot dog into a soft tactile sensing interface. Fabricated via digital loop-pile embroidery, Pluskin provides a scalable sensing solution that integrates the softness and familiarity of plush materials with textile-based sensing. We implemented a 4 × 3 sensing array on the dorsal surface of a Petoi Bittle robotic dog to validate the system. Using a Support Vector Machine (SVM) classifier on extracted spatiotemporal voltage features, the system identifies five natural touch gestures and maps them to corresponding embodied robot behaviors. By integrating plush materiality, tactile sensing, and embodied robot feedback, this work demonstrates a feasible approach toward a more natural and affective human-robot interaction interface.