AVKG: An Interlinked Cross-Domain Knowledge Graph for Autonomous Vehicle Decision Making

185.8 MB of semantically structured urban data integrated into a machine-readable knowledge graph. The Autonomous Vehicle Knowledge Graph (AVKG) is organized into five subgraphs covering road networks, incidents, activities, points of interest, and operators, stored in a GraphDB triple store. Author Huihai Wang published the dataset on figshare in April 2026 under a CC-BY-4.0 license.

Use Cases

• Risk-aware navigation planning based on integrated road incident and activity data.
• Ride-hailing and logistics optimization based on cross-domain reasoning over the road network and POI subgraphs.
• Spatiotemporal semantic querying for urban awareness using SPARQL and GeoSPARQL support.
• Testing complex reasoning models for autonomous vehicles based on the interlinked graph structure.

Strengths

• Integrates diverse urban contextual data into a single, semantically structured repository of 185.8 MB.
• Includes a developed ontology to capture semantic relations among key concepts.
• Supports advanced querying for spatiotemporal reasoning via SPARQL and GeoSPARQL.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for specific modeling tasks.
• Geographic and temporal coverage of the integrated urban data is not specified.

Provenance

Source

figshare

Collection Method

Developed by integrating diverse urban contextual data sources into a unified knowledge graph schema.

Freshness

Last updated 2026-04-27 23:10:35; freshness should be verified.