Reducing the Sim2Real gap for vacuum grasping in Isaac Sim

This work addresses the problem of reducing the Sim2Real gap of vacuum grasping for physics-based simulated environments. We introduce a grasp contact computational model, integrating it into the recently proposed Nvidia Isaac Sim robotics platform. The proposed approach enables realistic assessment of the seal formation between the gripper’s suction cup and the object of interest, enhancing the simulation of gripper-object attaching and detaching behavior. We define five conditions that must be satisfied to accurately replicate realistic seal formation between the gripper and the object, using a quasi-static spring model for the suction cup and custom rules to detect holes and bulges on the object’s surface. This enhancement is essential for complex object geometries, where default grasp contact models fail to account for seal loss due to surface discontinuities. The grasp contact model is compared to the default Surface Gripper in Isaac Sim. Simulations and real-world experiments show that our approach outperforms the default model in accurately reflecting the real seal formation in the presence of holes, bulges and discontinuities of the object’s surface. A link to the code repository is also provided.