# Robust Contact State Estimation in Humanoid Walking Gaits

arXiv: https://arxiv.org/abs/2208.00278 · HTML: https://mlsanity.com/paper/2208.00278/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 30 Jul 2022.

## Builds on (most cited first, 9 of 9)

- [Whole-Body Nonlinear Model Predictive Control Through Contacts for Quadrupeds](https://mlsanity.com/paper/1712.02889/) (2017)
- [Legged Robot State Estimation using Invariant Kalman Filtering and Learned Contact Events](https://mlsanity.com/paper/2106.15713/) (2021)
- [Stair Climbing Stabilization of the HRP-4 Humanoid Robot using Whole-body Admittance Control](https://mlsanity.com/paper/1809.07073/) (2018)
- [Simultaneous Contact, Gait and Motion Planning for Robust Multi-Legged Locomotion via Mixed-Integer Convex Optimization](https://mlsanity.com/paper/1904.04595/) (2019)
- [Trajectory Optimization Through Contacts and Automatic Gait Discovery for Quadrupeds](https://mlsanity.com/paper/1607.04537/) (2016)
- [Momentum Control with Hierarchical Inverse Dynamics on a Torque-Controlled Humanoid](https://mlsanity.com/paper/1410.7284/) (2014)
- [State Estimation for a Humanoid Robot](https://mlsanity.com/paper/1402.5450/) (2014)
- [Unsupervised Contact Learning for Humanoid Estimation and Control](https://mlsanity.com/paper/1709.07472/) (2017)
- [Humanoid Momentum Estimation Using Sensed Contact Wrenches](https://mlsanity.com/paper/1507.04401/) (2015)

## Built on by (most cited first, 1 of 1)

- [Perception for Humanoid Robots](https://mlsanity.com/paper/2309.15616/) (2023)

## Abstract (arXiv)

In this article, we propose a deep learning framework that provides a unified approach to the problem of leg contact detection in humanoid robot walking gaits. Our formulation accomplishes to accurately and robustly estimate the contact state probability for each leg (i.e., stable or slip/no contact). The proposed framework employs solely proprioceptive sensing and although it relies on simulated ground-truth contact data for the classification process, we demonstrate that it generalizes across varying friction surfaces and different legged robotic platforms and, at the same time, is readily transferred from simulation to practice. The framework is quantitatively and qualitatively assessed in simulation via the use of ground-truth contact data and is contrasted against state of-the-art methods with an ATLAS, a NAO, and a TALOS humanoid robot. Furthermore, its efficacy is demonstrated in base estimation with a real TALOS humanoid. To reinforce further research endeavors, our implementation is offered as an open-source ROS/Python package, coined Legged Contact Detection (LCD).