Denoising IMU Gyroscopes with Deep Learning for Open-Loop Attitude Estimation

Abstract

This paper proposes a learning method for denoising gyroscopes of Inertial Measurement Units (IMUs) using ground truth data, and estimating in real time the orientation (attitude) of a robot in dead reckoning. The obtained algorithm outperforms the state-of-the-art on the (unseen) test sequences. The obtained performances are achieved thanks to a well-chosen model, a proper loss function for orientation increments, and through the identification of key points when training with high-frequency inertial data. Our approach builds upon a neural network based on dilated convolutions, without requiring any recurrent neural network. We demonstrate how efficient our strategy is for 3D attitude estimation on the EuRoC and TUM-VI datasets. Interestingly, we observe our dead reckoning algorithm manages to beat top-ranked visual-inertial odometry systems in terms of attitude estimation although it does not use vision sensors. We believe this paper offers new perspectives for visual-inertial localization and constitutes a step toward more efficient learning methods involving IMUs. Our open-source implementation is available at https://github.com/mbrossar/denoise-imu-gyro.

IEEE Robotics and Automation Letters, IEEE In press

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
• Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
• Using Inertial Sensors for Position and Orientation Estimation
• Visual-Inertial Odometry of Aerial Robots
• RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, and New Methods
• SelfVIO: Self-Supervised Deep Monocular Visual-Inertial Odometry and Depth Estimation

Cited by in corpus (11)

• Inertial Navigation Meets Deep Learning: A Survey of Current Trends and Future Directions
• A Hybrid Model and Learning-Based Adaptive Navigation Filter
• Deep IMU Bias Inference for Robust Visual-Inertial Odometry with Factor Graphs
• Neural Networks Versus Conventional Filters for Inertial-Sensor-based Attitude Estimation
• PyPose: A Library for Robot Learning with Physics-based Optimization
• Data-Driven Denoising of Stationary Accelerometer Signals
• TransFusionOdom: Interpretable Transformer-based LiDAR-Inertial Fusion Odometry Estimation
• Adaptive Attitude Estimation Using a Hybrid Model-Learning Approach
• IDOL: Inertial Deep Orientation-Estimation and Localization
• RIANN -- A Robust Neural Network Outperforms Attitude Estimation Filters
• Adaptive Step Size Learning with Applications to Velocity Aided Inertial Navigation System