RGB-D Video Generation for Improving Human-to-Robot Object Handover Prediction

来源：arXiv cs.RO·2026-09-02 12:00发布时间待核实

arXiv:2608.13028v2 Announce Type: replace-cross Abstract: Human-to-robot (H2R) object handover is a fundamental capability for human-robot collaboration, yet progress is hindered by the scarcity of large-scale, human-centric datasets and the significant sim-to-real gap.