Planning and Learning: Path-Planning for Autonomous Vehicles, a Review of the Literature

TL;DR

This review paper surveys recent advances in path-planning for autonomous vehicles, covering planning algorithms, neural networks, graph neural networks, reinforcement learning, and handling uncertainty in temporal planning.

Contribution

It provides a comprehensive overview of current methods and recent developments in neural network-based path-planning and learning approaches for autonomous vehicles.

Findings

Graph neural networks are effective for processing structured path data

Reinforcement learning approaches are increasingly applied to path planning

Handling uncertainty remains a key challenge in temporal planning

Abstract

This short review aims to make the reader familiar with state-of-the-art works relating to planning, scheduling and learning. First, we study state-of-the-art planning algorithms. We give a brief introduction of neural networks. Then we explore in more detail graph neural networks, a recent variant of neural networks suited for processing graph-structured inputs. We describe briefly the concept of reinforcement learning algorithms and some approaches designed to date. Next, we study some successful approaches combining neural networks for path-planning. Lastly, we focus on temporal planning problems with uncertainty.