mlsanityData to 14 Oct 2026

Adaptive Attitude Estimation Using a Hybrid Model-Learning Approach

arXiv 2207.06903 ↗First posted 22 Jun 2022eess.SP cs.LG cs.ROcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 11 of its 47 references that are in the map. First posted on arXiv 22 Jun 2022.

Builds on

11 of 47 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2019RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, and New Methodscited by 73
  4. 2018IONet: Learning to Cure the Curse of Drift in Inertial Odometrycited by 55
  5. 2017RIDI: Robust IMU Double Integrationcited by 41
  6. 2020Denoising IMU Gyroscopes with Deep Learning for Open-Loop Attitude Estimationcited by 26
  7. 2019Deep Convolutional Networks in System Identificationcited by 17
  8. 2021RIANN -- A Robust Neural Network Outperforms Attitude Estimation Filterscited by 6
  9. 2020Neural Networks Versus Conventional Filters for Inertial-Sensor-based Attitude Estimationcited by 4
  10. 2016UAV attitude estimation using Unscented Kalman Filter and TRIADcited by 2
  11. 2020DANAE: a denoising autoencoder for underwater attitude estimationcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1.

4 papers.

  1. 2022Data-Driven Meets Navigation: Concepts, Models, and Experimental Validationcited by 5
  2. 2023Generalizable End-to-End Deep Learning Frameworks for Real-Time Attitude Estimation Using 6DoF Inertial Measurement Unitscited by 4
  3. 2025On Neural Inertial Classification Networks for Pedestrian Activity Recognitioncited by 2
  4. 2024DoorINet: Door Heading Prediction through Inertial Deep Learningcited by 0