A Route Planning Approach with RAG-based LLM and FAISS for Robotic Guide
Bibliographic record
Abstract
This paper presents a system for the automated generation of Cypher queries from natural language to optimize route planning for robotic guidance within a Neo4j database and OpenStreetMap-based graph representation. The proposed system uses a hybrid methodology that integrates RetrievalAugmented Generation (RAG) with local Large Language Models (LLMs) to improve query interpretation and path calculation. Additionally, the integration of Facebook AI Similarity Search (FAISS) for vector search, combined with specialized prompt engineering, facilitates the management of complex queries, such as automated point selection and route construction. The proposed system also incorporates few-shot learning to improve LLM performance in processing routing tasks by recognizing specific amenities and optimizing paths. Natural language queries allow non-expert users to intuitively interact with a robotic guide, requesting destinations, amenities, or optimal paths without technical input. The system has been evaluated as effective in automated systems designed to suggest urban navigation and perform geospatial network analysis, making this approach an innovative solution for dynamic spatial data management in complex environments.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".