Neural Networks Versus Conventional Filters for Inertial-Sensor-based Attitude Estimation

• URL: http://arxiv.org/abs/2005.06897v2
• Date: Wed, 3 Jun 2020 20:50:55 GMT
• Title: Neural Networks Versus Conventional Filters for Inertial-Sensor-based Attitude Estimation
• Authors: Daniel Weber, Clemens G\"uhmann and Thomas Seel
• Abstract summary: Inertial measurement units are commonly used to estimate the attitude of moving objects. nonlinear filter approaches have been proposed for solving the inherent sensor fusion problem. We investigate what extent these limitations can be overcome by means of artificial neural networks.
• Score: 1.0957528713294873
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inertial measurement units are commonly used to estimate the attitude of moving objects. Numerous nonlinear filter approaches have been proposed for solving the inherent sensor fusion problem. However, when a large range of different dynamic and static rotational and translational motions is considered, the attainable accuracy is limited by the need for situation-dependent adjustment of accelerometer and gyroscope fusion weights. We investigate to what extent these limitations can be overcome by means of artificial neural networks and how much domain-specific optimization of the neural network model is required to outperform the conventional filter solution. A diverse set of motion recordings with a marker-based optical ground truth is used for performance evaluation and comparison. The proposed neural networks are found to outperform the conventional filter across all motions only if domain-specific optimizations are introduced. We conclude that they are a promising tool for inertial-sensor-based real-time attitude estimation, but both expert knowledge and rich datasets are required to achieve top performance.

Related papers

• Physics-Enhanced Graph Neural Networks For Soft Sensing in Industrial Internet of Things [6.374763930914524]
  The Industrial Internet of Things (IIoT) is reshaping manufacturing, industrial processes, and infrastructure management. achieving highly reliable IIoT can be hindered by factors such as the cost of installing large numbers of sensors, limitations in retrofitting existing systems with sensors, or harsh environmental conditions that may make sensor installation impractical. We propose physics-enhanced Graph Neural Networks (GNNs), which integrate principles of physics into graph-based methodologies.
  arXiv  Detail & Related papers  (2024-04-11T18:03:59Z)
• Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking [3.5693768338940304]
  We propose two innovative data-driven filtering methods for tracking-by-detection systems. The first method employs a Bayesian filter with a trainable motion model to predict an object's future location. The second method, an end-to-end trainable filter, goes a step further by learning to correct detector errors.
  arXiv  Detail & Related papers  (2024-02-15T10:47:44Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• RIOT: Recursive Inertial Odometry Transformer for Localisation from Low-Cost IMU Measurements [5.770538064283154]
  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.
  arXiv  Detail & Related papers  (2023-03-03T00:20:01Z)
• Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth [92.25666446274188]
  sinusoidal neural networks with activations have been proposed as an alternative to networks with traditional activation functions. We first propose a simplified version of such sinusoidal neural networks, which allows both for easier practical implementation and simpler theoretical analysis. We then analyze the behavior of these networks from the neural tangent kernel perspective and demonstrate that their kernel approximates a low-pass filter with an adjustable bandwidth.
  arXiv  Detail & Related papers  (2022-11-26T07:41:48Z)
• Sensor-Guided Optical Flow [53.295332513139925]
  This paper proposes a framework to guide an optical flow network with external cues to achieve superior accuracy on known or unseen domains. We show how these can be obtained by combining depth measurements from active sensors with geometry and hand-crafted optical flow algorithms.
  arXiv  Detail & Related papers  (2021-09-30T17:59:57Z)
• Robust Neural Networks Outperform Attitude Estimation Filters [0.3867363075280543]
  RIANN is a real-time-capable neural network for robust IMU-based attitude estimation. We exploit two publicly available datasets for the method development and the training. We add four completely different datasets for evaluation of the trained neural network in three different test scenarios.
  arXiv  Detail & Related papers  (2021-04-15T11:40:25Z)
• Revisiting Initialization of Neural Networks [72.24615341588846]
  We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
  arXiv  Detail & Related papers  (2020-04-20T18:12:56Z)
• Distance-Based Regularisation of Deep Networks for Fine-Tuning [116.71288796019809]
  We develop an algorithm that constrains a hypothesis class to a small sphere centred on the initial pre-trained weights. Empirical evaluation shows that our algorithm works well, corroborating our theoretical results.
  arXiv  Detail & Related papers  (2020-02-19T16:00:47Z)
• Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread [136.2224792151324]
  We propose a new deep learning algorithm for fast salient object detection. The proposed algorithm achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
  arXiv  Detail & Related papers  (2020-01-22T15:23:48Z)
• Development of Use-specific High Performance Cyber-Nanomaterial Optical Detectors by Effective Choice of Machine Learning Algorithms [14.569246848322983]
  We show the best choice of ML algorithm in a cyber-nanomaterial detector is mainly determined by specific use considerations. We show by tracking/modeling the long-term drifts of the detector performance over large (1year) period,it is possible to improve the predictive accuracy with no need for recalibration.
  arXiv  Detail & Related papers  (2019-12-26T02:44:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.