AI on the Water: Applying DRL to Autonomous Vessel Navigation

TL;DR

This paper investigates the use of Deep Q-Learning to enable an autonomous vessel to follow paths and avoid obstacles in unknown environments, aiming to improve marine navigation safety.

Contribution

It demonstrates the feasibility of applying deep reinforcement learning for autonomous vessel control, specifically for obstacle avoidance and path following in marine settings.

Findings

DRL successfully enables collision avoidance and path following.

The approach shows potential for achieving human-level decision-making.

The study uses a benchmark ship model with available hydrodynamic data.

Abstract

Human decision-making errors cause a majority of globally reported marine accidents. As a result, automation in the marine industry has been gaining more attention in recent years. Obstacle avoidance becomes very challenging for an autonomous surface vehicle in an unknown environment. We explore the feasibility of using Deep Q-Learning (DQN), a deep reinforcement learning approach, for controlling an underactuated autonomous surface vehicle to follow a known path while avoiding collisions with static and dynamic obstacles. The ship's motion is described using a three-degree-of-freedom (3-DOF) dynamic model. The KRISO container ship (KCS) is chosen for this study because it is a benchmark hull used in several studies, and its hydrodynamic coefficients are readily available for numerical modelling. This study shows that Deep Reinforcement Learning (DRL) can achieve path following and collision avoidance successfully and can be a potential candidate that may be investigated further to achieve human-level or even better decision-making for autonomous marine vehicles.