Semantic knowledge graph maps vehicle intentions in driving scenes
A Semantic Knowledge Graph Construction Pipeline for Vehicle Intention Prediction in nuScenes
Artificial IntelligenceMachine Learning
Summary
Understanding what vehicles plan to do next is important for safe self-driving cars. The authors created a special knowledge graph that represents vehicle intentions using data from the nuScenes driving dataset. This graph captures how vehicles move relative to the self-driving car, their positions, and risks of collision over time. They also provide tools to build and check this graph, which can help with further AI analysis and prediction. Their tests show the graph’s motion labels are very consistent and reliable.
What this means in practice
- •For autonomous vehicle engineers: Create detailed semantic models of surrounding vehicles’ intentions to improve predictive driving algorithms from ego-centric sensor data.
- •For traffic management software teams: Integrate explicit semantic relations about vehicle motion and collision risk into traffic scene understanding tools for real-time analysis.
Tested on one dataset.
Authors
Khaled Nowara, Mohamed Manzour, Catherine Elias
Abstract
Knowledge graphs (KGs) are increasingly used in autonomous driving (AD) to make traffic scene entities and relations explicit for prediction and reasoning. Existing traffic-scene KGs, however, primarily emphasize trajectory forecasting or general scene understanding. This paper presents the nuScenes Intention Knowledge Graph (NIKG), a focused Web Ontology Language (OWL)-based semantic representation and construction pipeline for ego-centric vehicle intention context. NIKG instantiates nuScenes scenes as a self-describing Turtle graph and promotes three intention-relevant relations to first-class properties of each scene participant: ego-relative motion, spatial configuration, and time to collision (TTC) risk. The pipeline uses a small input contract available in many ego-centric driving datasets: ego pose, tracked object annotations, and temporal keyframe order. NIKG is released as an ontology-backed, self-describing graph artifact together with a reproducible construction pipeline and validation protocol for ego-centric intention context. Applying this pipeline to nuScenes mini yields a graph of 211,335 triples across 404 keyframes; under the validation protocol, ego-relative motion labels achieve 92.5% forward consistency. Coverage, semantic consistency, and temporal coherence analyses over this artifact are further reported. NIKG occupies the space between scene-oriented traffic KGs and intention-prediction models: a small, explicit semantic layer intended to support downstream work such as knowledge graph embedding (KGE), SPARQL-based feature extraction, or hybrid neuro-symbolic reasoning.