Explainable Lane Change Prediction for Near-Crash Scenarios Using Knowledge Graph Embeddings and Retrieval Augmented Generation

TL;DR

This paper presents an explainable AI model that predicts risky and safe lane changes using knowledge graph embeddings and retrieval augmented generation, achieving high accuracy and providing natural language explanations to improve interpretability.

Contribution

The work introduces a novel approach combining knowledge graphs, Bayesian inference, and RAG for explainable lane change prediction in near-crash scenarios, utilizing specialized datasets.

Findings

Achieved 91.5% F1-score for risky lane change prediction with 4 seconds anticipation

Achieved 90.0% F1-score for safe lane change prediction with 4 seconds anticipation

Validated model performance in CARLA simulator scenarios involving risky lane changes

Abstract

Lane-changing maneuvers, particularly those executed abruptly or in risky situations, are a significant cause of road traffic accidents. However, current research mainly focuses on predicting safe lane changes. Furthermore, existing accident datasets are often based on images only and lack comprehensive sensory data. In this work, we focus on predicting risky lane changes using the CRASH dataset (our own collected dataset specifically for risky lane changes), and safe lane changes (using the HighD dataset). Then, we leverage KG and Bayesian inference to predict these maneuvers using linguistic contextual information, enhancing the model's interpretability and transparency. The model achieved a 91.5% f1-score with anticipation time extending to four seconds for risky lane changes, and a 90.0% f1-score for predicting safe lane changes with the same anticipation time. We validate our model by integrating it into a vehicle within the CARLA simulator in scenarios that involve risky lane changes. The model managed to anticipate sudden lane changes, thus providing automated vehicles with further time to plan and execute appropriate safe reactions. Finally, to enhance the explainability of our model, we utilize RAG to provide clear and natural language explanations for the given prediction.