Learning Transferable Motor Skills for Geometry-Aware Robotic Surface Tasks
For robotic surface-interaction tasks requiring both geometric planning and expert motor patterns, this framework improves transferability across different geometries, though it is evaluated only in simulation.
The paper proposes a modular framework that decouples geometric motion planning from execution-level expertise for robotic surface tasks, using interpretable atomic motor rules inferred by a multimodal neural network. The approach is evaluated on L-shaped and window-shaped objects, showing successful extraction of velocity and orientation rules across both topologies.
Robotic surface-interaction tasks, such as spray painting or welding, require both accurate geometric planning and precise motion execution. While modern motion planners generate valid geometric paths, they often lack the expert motor patterns observed in human operators. Conversely, learning from demonstration often tightly couples task execution to the specific training geometry, limiting transferability. We propose a modular framework that decouples geometric motion planning from execution-level expertise. Expert behavior is represented as a vocabulary of interpretable, atomic motor rules, such as velocity scaling and orientation offsets, that systematically modify a geometrically planned reference path. We train a multimodal neural network to infer rule parameters jointly from kinematic trajectory data and CAD model geometry. We evaluate our approach through dynamic simulation on L-shaped and window-shaped objects, demonstrating on simulated data that the model successfully extracts velocity and orientation rules across both topologies.