Deep Learning with Attention Mechanism for Predicting Driver Intention at Intersection

TL;DR

This paper introduces a deep learning model with attention mechanisms to accurately predict driver intentions at intersections, enhancing safety and decision-making in autonomous and assisted driving systems.

Contribution

It presents a novel sequence-to-sequence LSTM model with attention for driver intention prediction using vehicular time-series data, outperforming existing methods.

Findings

Achieves high prediction accuracy on naturalistic driving data.

Outperforms previous methods in intention prediction tasks.

Potential application in ADAS and autonomous vehicle safety systems.

Abstract

In this paper, a driver's intention prediction near a road intersection is proposed. Our approach uses a deep bidirectional Long Short-Term Memory (LSTM) with an attention mechanism model based on a hybrid-state system (HSS) framework. As intersection is considered to be as one of the major source of road accidents, predicting a driver's intention at an intersection is very crucial. Our method uses a sequence to sequence modeling with an attention mechanism to effectively exploit temporal information out of the time-series vehicular data including velocity and yaw-rate. The model then predicts ahead of time whether the target vehicle/driver will go straight, stop, or take right or left turn. The performance of the proposed approach is evaluated on a naturalistic driving dataset and results show that our method achieves high accuracy as well as outperforms other methods. The proposed solution is promising to be applied in advanced driver assistance systems (ADAS) and as part of active safety system of autonomous vehicles.