Powered by OpenAIRE graph
Found an issue? Give us feedback
OpenMETUarrow_drop_down
OpenMETU
Master thesis . 2025
License: CC BY NC ND
Data sources: OpenMETU
addClaim

Attitude Estimation with an Invariant Extended Kalman Filter Using Learning-Based Covariance Adaptation

Makine Öğrenmesi Tabanlı Kovaryans Adaptasyonu Kullanan Değişmez Genişletilmiş Kalman Filtresi ile Tutum Kestirimi
Authors: Arslan, Mehmet Emir;

Attitude Estimation with an Invariant Extended Kalman Filter Using Learning-Based Covariance Adaptation

Abstract

Bu tez, Değişmez Genişletilmiş Kalman Filtresi (Invariant Extended Kalman Filter, IEKF) çerçevesinde, ölçüm gürültüsü kovaryans matrisini adaptif bir şekilde ayarlayarak tutum kestirim performansını artırmayı amaçlayan veri odaklı bir yöntem önermektedir. Ölçüm kovaryansını, güncel sensör verilerine göre ayarlamak için evrişimli sinir ağı kullanılmakta ve bu sayede filtre, farklı hareket ve çevresel koşullarda ölçümlere olan güvenini dinamik olarak değiştirebilmektedir. Evrişimli sinir ağı jiroskop, ivmeölçer ve manyetometre ölçümleri dâhil olmak üzere ataletsel ve manyetik sensör verilerinden oluşan dizileri işlemektedir. Bu adaptif mekanizma, IEKF’nin yer değiştirme, hızlı dönüşler ve manyetik bozulma gibi zorlu senaryolarla daha iyi başa çıkmasını sağlamaktadır. Yöntemin etkinliği, açık erişimli BROAD veri seti üzerinde değerlendirilmiştir. Deneysel sonuçlar, önerilen yöntemin yalnızca sabit kovaryanslı IEKF’ye kıyasla değil, aynı zamanda geleneksel adaptif yöntemleri kullanan IEKF’lere göre de daha yüksek kestirim doğruluğu sağladığını göstermektedir.

This thesis proposes a data-driven method to improve attitude estimation performance by adaptively scaling the measurement noise covariance matrix within an Invariant Extended Kalman Filter (IEKF) framework. To achieve this, a convolutional neural network (CNN) adjusts the measurement covariance based on recent sensor data, allowing the filter to adapt its reliance in measurements under different motion and environmental conditions. The CNN processes sequences of inertial and magnetic sensor readings, including gyroscope, accelerometer, and magnetometer measurements. This adaptive mechanism allows the IEKF to better handle challenging scenarios such as translations, fast rotations and magnetic disturbance cases. The effectiveness of the method is evaluated on publicly available BROAD dataset. Experimental results demonstrate improved estimation accuracy not only over the fixed-covariance IEKF, but also compared to IEKF with conventional adaptive methods.

Country
Turkey
Related Organizations
Keywords

Attitude Estimation, Convolutional Neural Networks, Invariant Extended Kalman Filter, Adaptive Covariance Estimation

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!