Robotics: Science and Systems XXII

CoCo-InEKF: State Estimation with Learned Contact Covariances in Dynamic, Contact-Rich Scenarios

Michael Baumgartner, David Müller, Agon Serifi, Ruben Grandia, Espen Knoop, Markus Gross, Moritz Bächer

Abstract:

Robust state estimation for highly dynamic motion of legged robots remains challenging, especially in dynamic, contact-rich scenarios. Traditional approaches often rely on binary contact states that fail to capture the nuances of partial contact or directional slippage. This paper presents CoCo-InEKF, a differentiable Invariant Extended Kalman Filter that utilizes continuous contact velocity covariances instead of binary contact states. These learned covariances allow the method to dynamically modulate contact confidence, representing states ranging from firm contact to directional slippage or no contact. To predict these covariances for a set of predefined contact candidate points, we employ a lightweight neural network trained end-to-end using a state-error loss. This approach eliminates the need for heuristic ground-truth contact labels. In addition, we propose an automated contact candidate selection procedure and demonstrate that our method is insensitive to their exact placement. Experiments on a bipedal robot demonstrate superior linear velocity estimation compared to baseline methods, enabling robust execution of challenging motions, including dancing and complex ground interactions.

Download:

Bibtex:

  
@INPROCEEDINGS{BaumgartnerM-RSS-26, 
    AUTHOR    = {Michael Baumgartner AND David Müller AND Agon Serifi AND Ruben Grandia AND Espen Knoop AND Markus Gross AND Moritz Bächer}, 
    TITLE     = {{CoCo-InEKF: State Estimation with Learned Contact Covariances in Dynamic, Contact-Rich Scenarios}}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2026}, 
    ADDRESS   = {Sydney, Australia}, 
    MONTH     = {July}, 
    DOI       = {10.15607/RSS.2026.XXII.178} 
}