2 papers
cs.RO2025
Physics-Informed Neural Networks with Unscented Kalman Filter for Sensorless Joint Torque Estimation in Humanoid Robots
Ines Sorrentino, Giulio Romualdi, Lorenzo Moretti +2
This paper presents a novel framework for whole-body torque control of humanoid robots without joint torque sensors, designed for systems with electric motors and high-ratio harmon…
cs.RO2024
Online DNN-driven Nonlinear MPC for Stylistic Humanoid Robot Walking with Step Adjustment
Giulio Romualdi, Paolo Maria Viceconte, Lorenzo Moretti +4
This paper presents a three-layered architecture that enables stylistic locomotion with online contact location adjustment. Our method combines an autoregressive Deep Neural Networ…