Approximating Global Contact-Implicit MPC via Sampling and Local Complementarity

May 2025   Bianchini

We uploaded to arXiv our project on approximating global contact-implicit model predictive control (CI-MPC). My co-authors are Penn masters graduate Sharanya Venkatesh, our advisor Professor Michael Posa, and two PhD alumni of our lab: Alp Aydinoglu and Will Yang. Our project presents a novel combination of local control and global sampling to achieve a real-time controller capable of complex, generalizable contact-rich tasks, including SE(3) and SE(2) object reconfiguration in a tabletop setting. Our experiments include a 3D jack for SE(3) goals and planar push T for SE(2) goals.

Video 1:  Motivation for and explanation of our approach, accompanied by experimental results on hardware.

Our official webpage

Our official webpage is located here and embedded below for ease-of-viewing.

Paper abstract

To achieve general-purpose dexterous manipulation, robots must rapidly devise and execute contact-rich behaviors. Existing model-based controllers are incapable of globally optimizing in real-time over the exponential number of possible contact sequences. Instead, recent progress in contact-implicit control has leveraged simpler models that, while still hybrid, make local approximations. However, the use of local models inherently limits the controller to only exploit nearby interactions, potentially requiring intervention to richly explore the space of possible contacts. We present a novel approach which leverages the strengths of local complementarity-based control in combination with low-dimensional, but global, sampling of possible end-effector locations. Our key insight is to consider a contact-free stage preceding a contact-rich stage at every control loop. Our algorithm, in parallel, samples end effector locations to which the contact-free stage can move the robot, then considers the cost predicted by contact-rich MPC local to each sampled location. The result is a globally-informed, contact-implicit controller capable of real-time dexterous manipulation. We demonstrate our controller on precise, non-prehensile manipulation of non-convex objects using a Franka Panda arm.

Citation

@inproceedings{venkatesh2025approximating,
  title={Approximating Global Contact-Implicit MPC via Sampling and Local Complementarity},
  author={Sharanya Venkatesh* and Bibit Bianchini* and Alp Aydinoglu and William Yang and Michael Posa},
  year={2025},
  journal={arXiv preprint arXiv:2505.13350},
  website={https://approximating-global-ci-mpc.github.io/}
}