Physics-Informed Neural Networks with Unscented Kalman Filter for Sensorless Joint Torque Estimation in Humanoid Robots

TL;DR

This paper introduces a sensorless torque estimation framework for humanoid robots that combines physics-informed neural networks for friction modeling with Unscented Kalman Filtering, enabling real-time, accurate torque control without joint sensors.

Contribution

The novel integration of PINNs and UKF for sensorless joint torque estimation in humanoid robots, improving accuracy and robustness without additional sensors.

Findings

Enhanced torque tracking accuracy demonstrated on ergoCub robot

Improved energy efficiency and disturbance rejection compared to RNEA

Framework scalable across different robots with similar hardware

Abstract

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 harmonic drives. The approach integrates Physics-Informed Neural Networks (PINNs) for friction modeling and Unscented Kalman Filtering (UKF) for joint torque estimation, within a real-time torque control architecture. PINNs estimate nonlinear static and dynamic friction from joint and motor velocity readings, capturing effects like motor actuation without joint movement. The UKF utilizes PINN-based friction estimates as direct measurement inputs, improving torque estimation robustness. Experimental validation on the ergoCub humanoid robot demonstrates improved torque tracking accuracy, enhanced energy efficiency, and superior disturbance rejection compared to the state-of-the-art Recursive Newton-Euler Algorithm (RNEA), using a dynamic balancing experiment. The framework's scalability is shown by consistent performance across robots with similar hardware but different friction characteristics, without re-identification. Furthermore, a comparative analysis with position control highlights the advantages of the proposed torque control approach. The results establish the method as a scalable and practical solution for sensorless torque control in humanoid robots, ensuring torque tracking, adaptability, and stability in dynamic environments.