cs.RONov 16, 2026

ROSE: A Shared Cross-Embodiment Facial-Motion Latent Space for Humanoid Robot Expression

Authors: Yongji Fu, Man Cao, Yi Zhou, Fei Lin, Mark F. Hansen, Guanqun Cao

Organizations: Department of Engineering Mathematics, University of Bristol, Bristol, BS16 1QY, United Kingdom. · School of Architecture and Design, China University of Mining and Technology, Xuzhou, China. · Department of Computer Science, Cardiff University, Cardiff, CF10 3AT, United Kingdom. · Intelliface, Hangzhou, China · 

Abstract

Natural, coherent full-face dynamic expressions are central to making humanoid robots socially approachable, yet existing systems commonly realize only limited lip motion or scripted expressions. The limitation is both physical and algorithmic. A compact head leaves little room for densely packed, independently controllable actuation; meanwhile, learned systems often generate an avatar video, landmarks, or facial parameters and then infer actuator commands through visual retargeting. This render-and-invert path adds latency and artifacts, and it does not reliably transfer generated behavior to a physical robot. We present ROSE (RObot facial expression through Shared motion Embeddings), a framework that integrates biomimetic hardware, cross-embodiment motion representation learning, and multimodal motion generation. On the hardware side, we build a flexible tendon-sheath transmission structure that integrates 34 actuators into a 19.5 cm biomimetic head. By decoupling actuator placement from facial action points, it enables coordinated full-face expression within a compact volume. On the algorithmic side, ROSE-VAE learns an identity-independent shared facial-motion latent space from human, digital-human, and robot observations. ROSE-Flow directly maps text, audio, or their combination to trajectories in this motion space without using video as a generator input. ROSE-ACT then converts these trajectories into constrained actuator commands. Our system demonstrates how high-density biomimetic hardware and a shared executable facial-motion representation can jointly unify cross-embodiment learning, multimodal generation, and physical robot expression.

Figures & tables

Explore similar work

CardsList
  1. SocialHumanoid: Towards Expressive Humanoid Behavior via One-Step Co-Speech Motion Generation

    Sep 27, 2026Chengqun Yang, Tengjie Zhu, Liang Xu +10Human Motion GenerationCo-Speech Gesture Generation

  2. Emo-H2A: Driving a Facial Robot Directly from LLM Hidden States at Token Rate

    Nov 18, 2026Yige Liu, Jingcheng Huang, Hao Sun +2Facial Expression SynthesisLanguage Model-Based Control