Real-to-Sim Deformable Object Manipulation: Optimizing Physics Models with Residual Mappings for Robotic Surgery

This study focuses on the manipulation of deformable objects in robotic surgery. The authors propose an adaptive parameter tuning approach for simulation optimization, aiming to bridge the real-to-sim gap in physics simulations. This method estimates a residual mapping and optimizes stiffness parameters in real-time, improving the simulation’s predictive capabilities. The research contributes to the advancement of simulation-based deformable tissue manipulation and holds potential for enhancing surgical autonomy.

Publication date: 22 Sep 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2309.11656