具身智能观察

TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction

产业动态

来源:arXiv cs.RO发布时间待核实

arXiv:2607.28391v2 Announce Type: replace Abstract: World Action Models (WAMs) combine future-state prediction with robot action generation, but existing approaches largely rely on visual futures. Visual prediction captures scene structure and object motion, yet provides limited supervision for force, deformation, shear, and slip during contact-rich manipulation.

TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction | 具身智能观察