Developing Artificial Intelligence Driven Safe Navigation Tool
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This study addresses the critical limitation of current navigation applications, such as Google Maps and Apple Maps, which prioritize distance or travel time without providing real-time risk scoring. Motivated by research indicating that the fastest routes are often the least safe—where an 8% increase in travel time could reduce crash likelihood by 23%—the authors aimed to develop an artificial intelligence (AI)-driven safe navigation tool. The primary objective was to create a system that offers data-driven decisions on the safest path by integrating historical data with real-time inputs, thereby allowing users to make informed choices rather than relying on uninformed route options. The methodology involved a comprehensive literature review to assess existing safety definitions, measurement techniques, and routing algorithms. The team then developed a robust navigation tool using a Texas-based case study, leveraging diverse datasets including the Crash Report Information System (CRIS), Roadway Hierarchical Network (RHiNO), and North American Land Data Assimilation System (NLDAS) for weather data. The development process integrated multiple data sources, such as historical traffic crashes, roadway geometry, weather conditions, and incident information. The tool utilized AI algorithms, including Random Forest, Gradient Boosting, and K-Nearest Neighbors, to predict risk scores. These scores were incorporated into shortest-path algorithms, such as Dijkstra’s and A*, to calculate routes that balance safety, distance, and travel time. The study successfully designed and implemented a user interface for the safe navigation tool that provides real-time risk scoring. Unlike static algorithms that rely solely on historical data, this dynamic tool queries relevant spatiotemporal data to produce updated risk assessments. The interface considers multiple scoring factors, including safety metrics derived from AI models, distance, and travel time, to generate an overall scoring metric for route selection. The tool evaluates roadway and environmental features, such as curvature, lighting conditions, and weather, to determine the safest path from a set of origins and destinations. The significance of this work lies in its contribution to road safety through the creation of a predictive, dynamic navigation system. By leveraging advanced AI algorithms and integrating various data sources, the tool enhances the accuracy and reliability of route selection. It shifts the paradigm from minimizing travel time to optimizing safety, ensuring users can avoid high-risk areas associated with poor geometric design, inadequate signage, or hazardous conditions. This development supports the broader goal of improving overall road safety by providing drivers with informed, data-driven navigation options.
Key finding
The developed AI-driven navigation tool successfully integrates historical and real-time data to provide users with informed, safety-prioritized route recommendations, addressing the gap in existing systems that lack real-time risk scoring.
Methodology
mixed_methods
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: crash risk outcomes
- Methodological Resource: dataset resource