Exploring the Benefits of Deep Learning-Based Sensors Error Estimation for Improved Attitude and Position Accuracy
Bibliographic record
Abstract
Inertial Navigation System (INS) is a primary component in various integrated navigation systems. However, the performance of INS is hindered due to the numerical integration of the measurements obtained from the Inertial Measurement Unit (IMU), which are contaminated by various sensor errors, especially with Micro-Electro-Mechanical Systems (MEMS) sensors. To address these challenges, we examine the performance of modern Deep Learning (DL) methods for mitigating such errors. Specifically, we propose a Deep Gyroscope Error (DGE) model designed to estimate and compensate for errors in the gyroscope measurements. The DGE model combines the feature extraction capabilities of a Convolutional Neural Network (CNN) with the sequential data modelling strengths of Long Short-Term Memory (LSTM). Instead of relying on high-grade IMU measurements, we distinctively employ an inverse mechanization algorithm that generates artificial IMU measurements from the integrated navigation solution states. This approach provides accurate ground truth data facilitating direct supervised learning. The proposed model was trained and verified using real data from MEMS-IMU on real road test experiments performed on a land vehicle in Kingston, Ontario, Canada. When subjected to evaluation against unseen data, the DGE model demonstrated significant improvements in standalone inertial navigation scenarios, particularly in mitigating attitude drift errors and subsequently improving position estimation. Over a uniform testing interval, the DGE model achieved an average reduction in attitude RMSE by 43.1% and in position RMSE by 25.4%. This emphasizes the efficacy of the proposed method in improving INS performance, particularly when operating in standalone mode.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".