[Paper] [Code] [Toppling Dataset] [Videos]
When robust vacuum suction grasps are not accessible, toppling can change the object's 3D pose to provide access to suction grasps. We extend prior toppling models by characterizing the robustness of toppling a 3D object specified by a triangular mesh, using Monte Carlo sampling to account for uncertainty in pose, friction coefficients, and push direction. The model estimates the resulting distribution of object poses following a topple action. We run ? physical toppling experiments using an ABB YuMi and find that the model outperforms a baseline model by ?? when comparing the total variation distance between each model's predicted probability distribution and the empirical distribution. We use the robust model as the state transition function in a Markov Decision Process to plan optimal sequences of toppling actions. 50,000 simulated rollouts on ?? objects suggest the policy can increase suction grasp reliability by 27.1\%, as computed by the Dexterity Network (Dex-Net) 3.0.
If you use this code or dataset for your research, please consider citing:
@article{correa2019toppling,
title={Robust Toppling for Vacuum Suction Grasping},
author={Correa, Christopher and Mahler, Jeffrey and Danielczuk, Michael and Goldberg, Ken},
journal={},
year={2019}
}