arXiv Robotics — research abstracts· Yuhang Hu, Junlin Lyu, Yuan Fang, Xiaoying Shen, Lechen Zhang, Jiong Lin, Judah Goldfeder, Steven Tian, Hod Lipson·· 11 hours agoEditorial score48
Learning Expressive Gaze for Humanoid Robots Using VLM-Guided Transformer-VAE
Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE
Summary
A humanoid robot learns gaze dynamics via a vision-language model and Transformer-VAE. RGT-Base achieves the lowest seven-joint MSE in a two-second benchmark.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
Source：arXiv Robotics — research abstracts · arxiv.org