LGC-Net: A Lightweight Gyroscope Calibration Network for Efficient Attitude Estimation
This work addresses the challenge of accurate and efficient attitude estimation for robots using only inertial sensors, offering a lightweight solution that is competitive with visual-inertial systems, though it is incremental in improving existing calibration methods.
The paper tackles the problem of denoising low-cost MEMS gyroscopes for real-time robot attitude estimation by proposing LGC-Net, a lightweight neural network that extracts local and global features from IMU data to dynamically compensate gyroscope errors, achieving state-of-the-art results on EuRoC and TUM-VI datasets with a more efficient model structure.
This paper presents a lightweight, efficient calibration neural network model for denoising low-cost microelectromechanical system (MEMS) gyroscope and estimating the attitude of a robot in real-time. The key idea is extracting local and global features from the time window of inertial measurement units (IMU) measurements to regress the output compensation components for the gyroscope dynamically. Following a carefully deduced mathematical calibration model, LGC-Net leverages the depthwise separable convolution to capture the sectional features and reduce the network model parameters. The Large kernel attention is designed to learn the long-range dependencies and feature representation better. The proposed algorithm is evaluated in the EuRoC and TUM-VI datasets and achieves state-of-the-art on the (unseen) test sequences with a more lightweight model structure. The estimated orientation with our LGC-Net is comparable with the top-ranked visual-inertial odometry systems, although it does not adopt vision sensors. We make our method open-source at: https://github.com/huazai665/LGC-Net