ME4VIO: Manifold Encapsulation for Visual Inertial Odometry with Application to Vehicle Navigation in Urban Environments
Bibliographic record
Abstract
Visual-inertial odometry (VIO) is a technique that uses data from both cameras and inertial sensors to estimate the pose of a moving vehicle. VIO is a promising technology for autonomous navigation, as it can provide accurate and reliable pose estimates even in challenging environments, such as those with limited or no GPS coverage or in the case of modern self-driving cars with HD-maps capabilities within a map outage or update. This paper proposes a novel VIO algorithm that uses a manifold encapsulation approach to represent and mitigate uncertainty. The proposed algorithm, Manifold Encapsulation for Visual Inertial Odometry (ME4VIO), is based on the ?-manifold, a mathematical structure that can represent the uncertainty associated with pose estimates. The ?-manifold approach has several advantages over traditional VIO methods, including (i) It can more accurately represent the uncertainty associated with pose estimates. (ii) It can be more robust to noise and outliers. (iii) It can be more efficient to compute. The proposed algorithm was evaluated on a dataset collected from an actual road test in Kingston, Ontario. The results showed that ME4VIO achieved more accurate and reliable pose estimates than traditional VIO methods. In particular, ME4VIO could maintain accurate pose estimates even in challenging conditions, such as fast motion, low-textured environments, and sensor drifts. The results of this paper demonstrate that the proposed ME4VIO algorithm is a promising approach for VIO, even in challenging conditions. This qualifies ME4VIO as a potential solution for various autonomous navigation applications.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| 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".