Real-World Deployment of a Lane Change Prediction Architecture Based on Knowledge Graph Embeddings and Bayesian Inference

2025-06-13

AI Summary

Existing lane-change prediction methods are predominantly evaluated on simulated or offline datasets, limiting their applicability to real-world deployment. This paper addresses the challenge of real-vehicle implementation by proposing an end-to-end lane-change intention prediction system tailored for operational automotive platforms. The method integrates multimodal environmental perception, knowledge graph embedding (KGE), and Bayesian inference, augmented with semantic feature discretization and a closed-loop longitudinal braking response mechanism. To the best of our knowledge, this is the first work to jointly leverage KGE and Bayesian inference for lane-change prediction on a physical vehicle platform, effectively bridging the sim-to-real gap. Real-world experiments demonstrate that the system reliably predicts adjacent vehicles’ lane-change intentions 3–4 seconds in advance, triggering timely braking interventions. This significantly enhances safety and success rates in cooperative lane-changing maneuvers.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Research on lane change prediction has gained a lot of momentum in the last couple of years. However, most research is confined to simulation or results obtained from datasets, leaving a gap between algorithmic advances and on-road deployment. This work closes that gap by demonstrating, on real hardware, a lane-change prediction system based on Knowledge Graph Embeddings (KGEs) and Bayesian inference. Moreover, the ego-vehicle employs a longitudinal braking action to ensure the safety of both itself and the surrounding vehicles. Our architecture consists of two modules: (i) a perception module that senses the environment, derives input numerical features, and converts them into linguistic categories; and communicates them to the prediction module; (ii) a pretrained prediction module that executes a KGE and Bayesian inference model to anticipate the target vehicle's maneuver and transforms the prediction into longitudinal braking action. Real-world hardware experimental validation demonstrates that our prediction system anticipates the target vehicle's lane change three to four seconds in advance, providing the ego vehicle sufficient time to react and allowing the target vehicle to make the lane change safely.

Problem

• Bridging gap between lane change prediction algorithms and real-world deployment
• Predicting lane changes using Knowledge Graph Embeddings and Bayesian inference
• Ensuring safety via longitudinal braking action based on predictions

Innovation

• Uses Knowledge Graph Embeddings for prediction
• Applies Bayesian inference for maneuver anticipation
• Converts predictions into longitudinal braking actions