Simulation of Parallel-Jaw Grasping using Incremental Potential Contact Models

Soft compliant jaw tips are almost universally used with parallel-jaw robot grippers due to their ability to increase contact area and friction between the jaws and the object to be manipulated. However, interactions between the compliant surfaces and rigid objects are notoriously difficult to model. We introduce IPC-GraspSim, a novel simulator using Incremental Potential Contact (IPC) -- a deformation model developed in 2020 for computer graphics -- that models both the dynamics and the deformation of compliant jaw tips during grasping. IPC-GraspSim is evaluated using a set of 2,625 physical grasps across 21 adversarial objects where standard analytic models perform poorly. In comparison to both analytic contact models (soft point contact, REACH, 6DFC) and dynamic grasp simulators (Isaac Gym with FleX backend), initial results suggest that IPC-GraspSim more accurately models real-world grasps, increasing F1 score by 9%.

The IPC-GraspSim paper presents grasp robustness values predicted by IPC-GraspSim (top row) and observed from physical experiments (bottom row) for the "vase" object. Further comparisons for each individual object in the dataset are available available at this link (Google Sheets).

Successful Grasp: Cat

Successful Grasp: Vase

Failed Grasp: Pawn

Failed Grasp: Fan Extruder

If you use this code or paper for your research, please consider citing:

@unpublished{kim2022ipcgraspsim,

title={Simulation of Parallel-Jaw Grasping using Incremental Potential Contact Models},

author={Kim, Chung Min and Danielczuk, Michael and Huang, Isabella and Goldberg, Ken},

note={Submitted to 2022 IEEE International Conference on Robotics and Automation. Philadelphia, PA.},

year={2022}

}