Automating Node Pruning for LiDAR-Based Topometric Maps in the Context of Teach-and-Repeat
Bibliographic record
Abstract
Maps are a vital component in autonomous mobile systems. However, they can be computationally expensive to build, particularly in the case of globally-consistent ones. To circumvent this issue, topometric approaches have been proposed, especially in the context of the Teach and Repeat paradigm. These topometric maps are graphs, where nodes are local maps and edges are the known transform between these nodes. When building these topometric maps, one important question is how far apart should these local maps be collected in the environment. On one hand, a densely sampled topometric map will be more robust, but at the cost of an increased database size. On the other hand, fewer local maps mean a more efficient topometric map. Traditional approaches record these local maps at a fixed, regular intervals. In this paper, we propose an offline algorithm that automatically prunes nodes in a way that offers some empirical guarantees on localization errors. In particular, our approach is based on first collecting a densely sampled topometric map, then finding a minimal subset of nodes using a cost-based approach via Dijkstra's Algorithm. Offline experiments on three datasets confirmed the ability of our approach to minimize the size of topometric maps, and showed that the size of the map will vary given a certain demanded localization error tolerance and environment complexity.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| 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 | 0.001 | 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".