AI RESEARCH
RAFL: Generalizable Sim-to-Real of Soft Robots with Residual Acceleration Field Learning
arXiv CS.LG
•
ArXi:2603.22039v1 Announce Type: cross Differentiable simulators enable gradient-based optimization of soft robots over material parameters, control, and morphology, but accurately modeling real systems remains challenging due to the sim-to-real gap. This issue becomes pronounced when geometry is itself a design variable.