Ontology-based context awareness for driving assistance systems
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the challenge of achieving comprehensive situation awareness in Advanced Driving Assistance Systems (ADAS). While modern vehicles utilize sensors to detect the spatio-temporal state of surrounding entities, this data alone is insufficient to infer safe navigation conditions. The authors argue that understanding the interactions between perceived entities (vehicles, pedestrians) and contextual data (digital maps, traffic rules) is essential for predicting entity behavior and its consequences for the subject vehicle. To bridge this gap, the paper proposes an ontology-based framework that provides a conceptual description of road entities and their interactions, enabling the system to infer coherent situational understanding and determine the relevance of specific entities for safe navigation. The methodology involves designing a formal ontology using the Web Ontology Language (OWL) and Semantic Web Rule Language (SWRL). The ontology’s Terminological Box (TBox) defines three primary classes: mobile entities (vehicles, pedestrians), static entities (intersections, crossings), and spatio-temporal context parameters. Object properties define relationships such as "isFollowing" or "isToReach," while data properties assign specific values like distance to the subject vehicle. The Assertional Box (ABox) contains instances of these classes populated by sensor data and map information. The core intelligence resides in 14 SWRL rules that encode traffic laws and interaction logic, allowing the system to infer future behaviors (e.g., deceleration, stopping) and chain reactions (e.g., a following vehicle must stop if the lead vehicle stops). The framework was evaluated through two stages. First, a hand-written context scenario involving three vehicles, a pedestrian, and a stop intersection was processed using the Pellet reasoner. The ontology successfully inferred complex interactions, such as determining that a vehicle following another must stop because the lead vehicle was required to stop for a pedestrian near a crossing. Second, a real-time implementation was tested on a passenger vehicle operating on closed roads. The system integrated perception sensors for detecting vehicles and pedestrians with an electronic horizon derived from Open Street Map data. The ontology was extended to identify the most relevant entities for the driver, classifying situations such as "Stop intersection ahead" or "Pedestrian before 1 leader." The results demonstrate that the ontology-based approach enables human-like reasoning about global road contexts, effectively handling chain reactions and interactions between multiple entities. The real-time application confirmed that the framework can accurately interpret sensor and map data to determine which entities are most relevant for the subject vehicle’s navigation. The authors conclude that this ontology-based method significantly improves situation awareness in ADAS by providing a coherent, extensible structure for inferring entity behaviors and their impact on the subject vehicle, thereby enhancing safety and decision-making capabilities.
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.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-06-25 |
| archive | success | unpaywall | — | — | 2 | 2026-06-26 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-26 |
| chunk | success | chunk | — | — | 1 | 2026-06-26 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-26 |
| enrich | success | openalex | — | — | 1 | 2026-06-26 |
| promote | success | — | — | — | 1 | 2026-06-25 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-26 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; 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).
- Theoretical Contribution: conceptual framework