Prediction Based Decision Making for Autonomous Highway Driving

TL;DR

This paper introduces a prediction-based deep reinforcement learning model for autonomous highway driving that anticipates surrounding vehicle intentions to improve decision-making safety.

Contribution

It presents a novel PDRL model that incorporates intention prediction into reinforcement learning for autonomous highway driving, trained on real traffic data.

Findings

Reduces collision rates compared to standard DRL models

Enhances decision-making safety in complex traffic scenarios

Validated through simulation with various traffic conditions

Abstract

Autonomous driving decision-making is a challenging task due to the inherent complexity and uncertainty in traffic. For example, adjacent vehicles may change their lane or overtake at any time to pass a slow vehicle or to help traffic flow. Anticipating the intention of surrounding vehicles, estimating their future states and integrating them into the decision-making process of an automated vehicle can enhance the reliability of autonomous driving in complex driving scenarios. This paper proposes a Prediction-based Deep Reinforcement Learning (PDRL) decision-making model that considers the manoeuvre intentions of surrounding vehicles in the decision-making process for highway driving. The model is trained using real traffic data and tested in various traffic conditions through a simulation platform. The results show that the proposed PDRL model improves the decision-making performance compared to a Deep Reinforcement Learning (DRL) model by decreasing collision numbers, resulting in safer driving.