Highlight

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

A paper on predicting lane changes using knowledge graphs and retrieval augmented generation.

Based on

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

By M. Manzour, Augusto Luis Ballardini, Rubén Izquierdo, Miguel Ángel Sotelo
Read original article →

This paper presents a model for predicting lane changes in near-crash scenarios. It uses the CARLA Risky-lane-change Anticipation in Simulated Highways dataset and leverages knowledge graphs and Bayesian inference to predict lane changes.

The model achieves high accuracy and provides clear explanations for its predictions using retrieval augmented generation.

Abstract

This paper presents a model for predicting lane changes in near-crash scenarios. It uses the CARLA Risky-lane-change Anticipation in Simulated Highways dataset and leverages knowledge graphs and Bayesian inference to predict lane changes. The model achieves high accuracy and provides clear explanations for its predictions using retrieval augmented generation.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

lane change predictionknowledge graph embeddingsretrieval augmented generationexplainable ainear-crash scenariosKnowledge GraphsAI AgentsLarge Language ModelsRetrieval & RAG
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources
Explainable Lane Change Prediction for Near-Crash Scenarios Using Knowledge Graph Embeddings and Retrieval Augmented Generation | Aramai