Real-Time Implementation of INS/GPS Data Fusion Utilizing Adaptive Neuro-Fuzzy Inference system
Bibliographic record
Abstract
Presently, Kalman filter (KF) is used to fuse data from both inertial navigation systems (INS) and global positioning systems (GPS) to provide position, velocity and attitude information. However, several drawbacks associated with KF like its immunity to noise, its dependency on predefined errors models, has encouraged research activates towards investigation of other integration techniques. This study proposes and discusses the real-time implementation of adaptive neuro-fuzzy inference system (ANFIS) to fuse GPS and INS data for vehicular navigation applications. The ANFIS model is designed to process the INS position component at its input and provide the corresponding INS position error at its output. This model is based on the Tagaki-Sugeno-Kang (TSK) fuzzy logic inference system. During the availability of the GPS signal, the ANFIS module processes the INS position components and the model parameters are updated towards their optimal values while minimizing the root mean square estimation error between the ANFIS output and the difference between the GPS and INS position components. The INS error provided by the ANFIS model is continuously removed from the corresponding INS position component. The proposed method is implemented for real-time applications through a data window of appropriate size that processes the INS position component and the corresponding INS error referenced to GPS position. This window slides along the INS and the GPS data over the entire navigation mission. During the prediction mode (upon losing the GPS satellite signal), the navigation system relies on the ANFIS module to predict INS errors and remove them from their corresponding INS position components. The proposed method was examined and compared to KF when applied to Ashtech Z12 GPS receiver and a navigation-grade INS (Honeywell LRF-III) that have been utilized inside a land vehicle. The system is evaluated while considering several intentionally introduced GPS outages for periods of 20 seconds. The ANFIS-based navigation system was able to provide the vehicle position with errors, which were below 2 m. The experimental results demonstrated the advantages of the proposed AIbased INS/GPS integration techniques in regards of robustness while ensuring system position accuracy in real-time.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".