InEKFormer: A Hybrid State Estimator for Humanoid Robots

TL;DR

This paper introduces InEKFormer, a hybrid state estimator combining an invariant extended Kalman filter and a Transformer network, demonstrating potential improvements in humanoid robot state estimation.

Contribution

The paper presents a novel hybrid approach integrating InEKF and Transformers for improved humanoid robot state estimation, addressing limitations of classical methods.

Findings

Transformers show potential in humanoid state estimation.

Robust autoregressive training is necessary for high-dimensional problems.

InEKFormer outperforms traditional Kalman filter approaches.

Abstract

Humanoid robots have great potential for a wide range of applications, including industrial and domestic use, healthcare, and search and rescue missions. However, bipedal locomotion in different environments is still a challenge when it comes to performing stable and dynamic movements. This is where state estimation plays a crucial role, providing fast and accurate feedback of the robot's floating base state to the motion controller. Although classical state estimation methods such as Kalman filters are widely used in robotics, they require expert knowledge to fine-tune the noise parameters. Due to recent advances in the field of machine learning, deep learning methods are increasingly used for state estimation tasks. In this work, we propose the InEKFormer, a novel hybrid state estimation method that incorporates an invariant extended Kalman filter (InEKF) and a Transformer network. We compare our method with the InEKF and the KalmanNet approaches on datasets obtained from the humanoid robot RH5. The results indicate the potential of Transformers in humanoid state estimation, but also highlight the need for robust autoregressive training in these high-dimensional problems.