Robust Contact State Estimation in Humanoid Walking Gaits
This work addresses a critical challenge in humanoid robotics for enabling stable walking, though it is incremental as it builds on existing methods with a unified approach.
The authors tackled the problem of leg contact detection in humanoid robot walking gaits by proposing a deep learning framework that accurately estimates contact state probabilities, achieving robust generalization across different friction surfaces and robotic platforms with demonstrated efficacy in simulation and real-world tests.
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).