Robotic manipulation requires representations that capture both scene geometry and its evolution during interaction. Existing approaches have largely treated these two aspects separately. World action models capture such dynamics by coupling action prediction with future video generation, but their reliance on iterativ...
Wei Lu, Jia-Xin Zhang, Yun-Heng Wang et al.· 0 citations
Humanoid loco-manipulation requires continuous coordination of high-dimensional whole-body motion to realize task objectives. While vision-language-action models and world action models transfer semantic and visual-dynamics priors to robot control, these priors do not necessarily capture the structure of robot motion....
Yun-Heng Wang, Jia-Xin Zhang, Wei Lu et al.· 0 citations
A deterministic 25 Hz tactile reflex controller is used as a collection-time teacher that shapes grasping behavior in demonstrations for policy learning, while disturbance rejection remains controller-dependent, revealing the boundary of tactile-free policy.
Zi-Yang Feng, Zi-Zhao Yuan, Yu-Long Fu et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.