EDRF: Enhanced Driving Risk Field Based on Multimodal Trajectory Prediction and Its Applications

TL;DR

This paper introduces EDRF, a novel model that combines deep learning multimodal trajectory prediction with Gaussian models to improve traffic risk assessment for autonomous and human-driven vehicles.

Contribution

The paper presents the EDRF model that integrates multimodal trajectory predictions with uncertainty modeling, enhancing driving risk assessment and enabling multiple traffic safety applications.

Findings

EDRF effectively captures traffic entity behavior uncertainty.

The model improves risk monitoring and trajectory planning accuracy.

Applications demonstrate the model's versatility across scenarios.

Abstract

Driving risk assessment is crucial for both autonomous vehicles and human-driven vehicles. The driving risk can be quantified as the product of the probability that an event (such as collision) will occur and the consequence of that event. However, the probability of events occurring is often difficult to predict due to the uncertainty of drivers' or vehicles' behavior. Traditional methods generally employ kinematic-based approaches to predict the future trajectories of entities, which often yield unrealistic prediction results. In this paper, the Enhanced Driving Risk Field (EDRF) model is proposed, integrating deep learning-based multimodal trajectory prediction results with Gaussian distribution models to quantitatively capture the uncertainty of traffic entities' behavior. The applications of the EDRF are also proposed. It is applied across various tasks (traffic risk monitoring, ego-vehicle risk analysis, and motion and trajectory planning) through the defined concept Interaction Risk (IR). Adequate example scenarios are provided for each application to illustrate the effectiveness of the model.