Semantic-Geometric Task Representations for Bimanual Manipulation from Human Demonstrations to Robot Action Planning

ArXi:2601.11460v2 Announce Type: replace-cross Learning structured task representations from human nstrations is essential for bimanual manipulation, where action ordering, object involvement, and interaction geometry vary significantly across executions. A key challenge lies in jointly capturing the discrete semantic task structure and the temporal evolution of object-centric geometric relations in a form that s reasoning over task progression. We