IMPROVED REFERENCE KEY FRAME ALGORITHM
Bibliographic record
Abstract
Abstract. The autonomous vehicles, such as wheeled robots and drones, efficiently contribute in the search and rescue operations. Specially for indoor environments, these autonomous vehicles rely on simultaneous localization and mapping approach (SLAM) to construct a map for the unknown environment and simultaneously to estimate the vehicle’s position inside this map. The result of the scan matching process, which is a key step in many of SLAM approaches, has a fundamental role of the accuracy of the map construction. Typically, local and global scan matching approaches, that utilize laser scan rangefinder, suffer from accumulated errors as both approaches are sensitive to previous history. The reference key frame (RKF) algorithm reduces errors accumulation as it decreases the dependency on the accuracy of the previous history. However, the RKF algorithm still suffers; as most of the SLAM approaches, from scale shrinking problem during scanning corridors that exceed the maximum detection range of the laser scan rangefinder. The shrinking in long corridors comes from the unsuccessful estimation of the longitudinal movement from the implemented RKF algorithm and the unavailability of this information from external source as well. This paper proposes an improvement for the RKF algorithm. This is achieved by integrating the outcomes of the optical flow with the RKF algorithm using extended Kalman filter (EKF) to overcome the shrinking problem. The performance of the proposed algorithm is compared with the RKF, iterative closest point (ICP), and Hector SLAM in corridors that exceed the maximum detection range of the laser scan rangefinder.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.012 | 0.009 |
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".