Inertial localisation is an important technique as it enables ego-motion estimation in conditions where external observers are unavailable. However, low-cost inertial sensors are inherently corrupted by bias and noise, which lead to unbound errors, making straight integration for position intractable. Traditional mathematical approaches are reliant on prior system knowledge, geometric theories and are constrained by predefined dynamics. Recent advances in deep learning, that benefit from ever-increasing volumes of data and computational power, allow for data driven solutions that offer more comprehensive understanding. Existing deep inertial odometry solutions rely on estimating the latent states, such as velocity, or are dependant on fixed sensor positions and periodic motion patterns. In this work we propose taking the traditional state estimation recursive methodology and applying it in the deep learning domain. Our approach, which incorporates the true position priors in the training process, is trained on inertial measurements and ground truth displacement data, allowing recursion and to learn both motion characteristics and systemic error bias and drift. We present two end-to-end frameworks for pose invariant deep inertial odometry that utilise self-attention to capture both spatial features and long-range dependencies in inertial data. We evaluate our approaches against a custom 2-layer Gated Recurrent Unit, trained in the same manner on the same data, and tested each approach on a number of different users, devices and activities. Each network had a sequence length weighted relative trajectory error mean $\leq0.4594$m, highlighting the effectiveness of our learning process used in the development of the models.

翻译：摘要：惯性定位是一项重要技术，可在无法使用外部观测器的条件下实现自运动估计。然而，低成本惯性传感器固有地受到偏置和噪声的污染，导致无限误差，使得直接积分进行位置估计难以实现。传统数学方法依赖先验系统知识、几何理论，且受限于预定义动力学模型。近年来，深度学习的发展得益于不断增长的数据量和计算能力，能够提供更全面的数据驱动解决方案。现有深度惯性里程计方法依赖于潜在状态（如速度）的估计，或受限于固定传感器位置和周期性运动模式。本研究提出将传统状态估计递归方法应用于深度学习领域。我们的方法在训练过程中融入真实位置先验，基于惯性测量和地面真实位移数据进行训练，实现递归并同时学习运动特征及系统性误差偏置与漂移。我们提出了两个端到端框架用于姿态不变的深度惯性里程计，利用自注意力机制捕捉惯性数据中的空间特征和长程依赖关系。我们将所提方法与自定义双层门控循环单元进行比较（采用相同数据与训练方式），并在多个用户、设备及活动场景下进行测试。各网络的序列长度加权相对轨迹误差均值均≤0.4594米，凸显了模型开发中训练过程的有效性。