Yifei Dong*, Shaohang Han*, Xianyi Cheng, Werner Friedl, Rafael I. Cabral Muchacho, Máximo A. Roa, Jana Tumova, and Florian T. Pokorny
Uncertainties in contact dynamics and object geometry remain significant barriers to robust robotic manipulation. Caging mitigates these uncertainties by constraining an object's mobility without requiring precise contact modeling. However, existing caging research has largely treated morphology and policy optimization as separate problems, overlooking their inherent synergy. In this paper, we introduce CageCoOpt, a hierarchical framework that jointly optimizes manipulator morphology and control policy for robust manipulation. The framework employs reinforcement learning for policy optimization at the lower level and multi-task Bayesian optimization for morphology optimization at the upper level. A robustness metric in caging, Minimum Escape Energy, is incorporated into the objectives of both levels to promote caging configurations and enhance manipulation robustness. The evaluation results through four manipulation tasks demonstrate that co-optimizing morphology and policy improves success rates under uncertainties, establishing caging-guided co-optimization as a viable approach for robust manipulation.
@article{dong2024co,
title={Co-Designing Tools and Control Policies for Robust Manipulation},
author={Dong, Yifei and Han, Shaohang and Cheng, Xianyi and Friedl, Werner and Muchacho, Rafael I Cabral and Roa, M{\'a}ximo A and Tumova, Jana and Pokorny, Florian T},
journal={arXiv preprint arXiv:2409.11113},
year={2024}
}
Thanks to Mengyuan Zhao, Kei Ikemura and Alon Shirizly for proofreading and Zahid Muhammad and Haofei Lu for assistance with the experiments.