Manipulation LfDExpert
Interaction-Stiffness-Guided Basis Allocation in Dynamic Movement Primitives for Efficient Skill Transfer
Reports an IEEE Transactions on Industrial Informatics-accepted method, SC-DMPs, that redistributes dynamic-movement-primitive basis functions according to a stage-criticality index built from operator-robot interaction stiffness and cross-demonstration trajectory variability. On handwriting and three real-robot tasks, it reduces task-critical trajectory error (e.g., 32.5% lower RMSE at geometric hotspots versus classical DMPs across letter settings) while keeping a roughly 1 kB model and millisecond adaptation. This provides a compact, task-aware trajectory representation for precision assembly and other tight-tolerance motions.