Inertial Measurement Units (IMU) are commonly used in inertial attitude estimation from engineering to medical sciences. There may be disturbances and high dynamics in the environment of these applications. Also, their motion characteristics and patterns also may differ. Many conventional filters have been proposed to tackle the inertial attitude estimation problem based on IMU measurements. There is no generalization over motion and environmental characteristics in these filters. As a result, the presented conventional filters will face various motion characteristics and patterns, which will limit filter performance and need to optimize the filter parameters for each situation. In this paper, two end-to-end deep-learning models are proposed to solve the problem of real-time attitude estimation by using inertial sensor measurements, which are generalized to motion patterns, sampling rates, and environmental disturbances. The proposed models incorporate accelerometer and gyroscope readings as inputs, which are collected from a combination of seven public datasets. The models consist of convolutional neural network (CNN) layers combined with Bi-Directional Long-Short Term Memory (LSTM) followed by a Fully Forward Neural Network (FFNN) to estimate the quaternion. To evaluate the validity and reliability, we have performed an extensive and comprehensive evaluation over seven publicly available datasets, which consist of more than 120 hours and 200 kilometers of IMU measurements. The results show that the proposed method outperforms the state-of-the-art methods in terms of accuracy and robustness. Furthermore, it demonstrates that this model generalizes better than other methods over various motion characteristics and sensor sampling rates.

翻译：惯性测量单元（IMU）在工程与医学领域的惯性姿态估计中应用广泛。其应用环境可能存在干扰与高动态特性，且运动特征与模式也各不相同。传统方法中已提出多种滤波器来解决基于IMU测量的惯性姿态估计问题，但这些滤波器对运动与环境特征缺乏泛化能力。因此，现有滤波器在面对不同运动特征与模式时性能受限，需要针对每种场景优化滤波器参数。本文提出两种端到端深度学习模型，利用惯性传感器测量解决实时姿态估计问题，这些模型对运动模式、采样率及环境干扰具有泛化能力。所提模型将加速度计与陀螺仪读数作为输入，数据来自七个公开数据集的组合。模型包含卷积神经网络（CNN）层与双向长短期记忆网络（LSTM），其后连接全前馈神经网络（FFNN）以估计四元数。为验证有效性与可靠性，我们在七个公开数据集上进行了广泛而全面的评估，这些数据集包含超过120小时、200公里的IMU测量数据。结果表明，所提方法在精度与鲁棒性方面优于现有最优方法。此外，该模型在不同运动特征与传感器采样率下的泛化能力也优于其他方法。