Lightweight Semantic-Aided Localization With Spinning LiDAR Sensor
Bibliographic record
Abstract
Autonomous driving demands robust and precise vehicle localization in complex environments with limited on-board computational resources. Incorporating reliable semantic information with localization algorithms can increase accuracy remarkably, however, the process of extracting semantic information from LiDAR point clouds and matching it to semantic maps is computationally intensive. Moreover, pure semantic localization cannot achieve the robustness requirements for safe self-driving as the necessary quantity of semantic landmarks cannot be guaranteed under extreme conditions. In this paper, we present a lightweight semantic-aided localization method that improves upon traditional techniques in two ways. First, we propose a highly efficient pipeline to extract three semantic classes from a LiDAR scan. Second, instead of semantic 3D point cloud registration, map matching is performed through 2D key point matching. We then integrate these two functions into a dynamic semantic aided localization framework. Our on-road experiments demonstrate that the proposed method achieves both the high accuracy of semantic localization and the robustness of non-semantic localization. With our algorithm consuming under 10% of CPU resources, we observe reduced positioning error, especially peak error, when comparing to non-semantic counterparts.
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) | 0.001 | 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 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".