An Indoor Navigation System using Stereo Vision, IMU and UWB Sensor Fusion
Bibliographic record
Abstract
In recent years, indoor localization has found many applications in civil and military fields. As Global Navigation Satellite Systems (GNSS) are not available indoors, the state-of-art trend is to fuse low-cost/low-power accelerometer/gyroscope with other sensors such as vision sensors. To further enhance the accuracy, ranging technologies such as Ultra-wide-band (UWB) radio ranging have been introduced as an indoor replacement of GNSS. However, robust localization continues to be challenging as accelerometer/gyroscope sensors suffer from random biases. Similarly, UWB ranging suffers from noise and multipath. Visual sensors depend upon lighting conditions and they suffer from odometry drifts. To accurately and efficiently fuse these sensors, this paper presents a robust fusion framework based on Extended-Kalman Filter (EKF). The proposed design applies non-holonomic speed-aided motion constraints to minimize positional errors. This design enabled the direct fusion of speed estimated from stereo vision into EKF which is more immune to vision-related orientation errors. The overall positional drifts are further controlled by positional updates whenever a reliable UWB solution is available. Our developed system was tested in typical indoor environment using physical data and the experimental results showed robust sub-meter localization accuracy even under multiple outages.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".