Autonomous Driving at Unsignalized Intersections: A Review of Decision-Making Challenges and Reinforcement Learning-Based Solutions

TL;DR

This survey reviews reinforcement learning and deep learning techniques for autonomous vehicle decision-making at unsignalized intersections, highlighting current limitations and proposing future research directions for safer, more effective solutions.

Contribution

It provides a comprehensive comparison of existing RL-based decision-making methods and identifies key challenges and research gaps in autonomous driving at unsignalized intersections.

Findings

Current schemes lack robustness for real-world deployment.

Reinforcement learning approaches vary widely in assumptions and algorithms.

A robust, safe decision-making system for real-world intersections is yet to be developed.

Abstract

Autonomous driving at unsignalized intersections is still considered a challenging application for machine learning due to the complications associated with handling complex multi-agent scenarios characterized by a high degree of uncertainty. Automating the decision-making process at these safety-critical environments involves comprehending multiple levels of abstractions associated with learning robust driving behaviors to enable the vehicle to navigate efficiently. In this survey, we aim at exploring the state-of-the-art techniques implemented for decision-making applications, with a focus on algorithms that combine Reinforcement Learning (RL) and deep learning for learning traversing policies at unsignalized intersections. The reviewed schemes vary in the proposed driving scenario, in the assumptions made for the used intersection model, in the tackled challenges, and in the learning algorithms that are used. We have presented comparisons for these techniques to highlight their limitations and strengths. Based on our in-depth investigation, it can be discerned that a robust decision-making scheme for navigating real-world unsignalized intersection has yet to be developed. Along with our analysis and discussion, we recommend potential research directions encouraging the interested players to tackle the highlighted challenges. By adhering to our recommendations, decision-making architectures that are both non-overcautious and safe, yet feasible, can be trained and validated in real-world unsignalized intersections environments.