论文标题
使用混合模型学习方法进行自适应态度估算
Adaptive Attitude Estimation Using a Hybrid Model-Learning Approach
论文作者
论文摘要
使用智能手机的惯性传感器的态度确定构成了一个重大挑战，这是由于传感器的表现低级别和步行行人的变化性质。在本文中，采用数据驱动技术来应对这一挑战。为此，提出了用于态度估计的混合深度学习和基于模型的解决方案。在这里，基于经典模型的方程式用于形成自适应互补滤波器结构。每个轴中的加速度计，而不是使用恒定或基于模型的自适应权重，而是由唯一的神经网络确定。使用实验数据对基于流行模型的方法进行了评估所提出的混合方法的性能。
Attitude determination using the smartphone's inertial sensors poses a major challenge due to the sensor low-performance grade and variate nature of the walking pedestrian. In this paper, data-driven techniques are employed to address that challenge. To that end, a hybrid deep learning and model based solution for attitude estimation is proposed. Here, classical model based equations are applied to form an adaptive complementary filter structure. Instead of using constant or model based adaptive weights, the accelerometer weights in each axis are determined by a unique neural network. The performance of the proposed hybrid approach is evaluated relative to popular model based approaches using experimental data.
