Autonomous Navigation in Ice-Covered Waters with Learned Predictions on Ship-Ice Interactions

TL;DR

This paper introduces a deep learning-based navigation system for ships in ice-covered waters that predicts ice movements to minimize collisions, validated through simulation and physical tests.

Contribution

It presents a novel deep learning model for predicting ice dynamics and integrates it into a real-time graph search planner for improved navigation.

Findings

Significantly reduces collisions with ice compared to existing methods.

Effective in both simulation and physical test environments.

Real-time performance achieved through caching intermediate predictions.

Abstract

Autonomous navigation in ice-covered waters poses significant challenges due to the frequent lack of viable collision-free trajectories. When complete obstacle avoidance is infeasible, it becomes imperative for the navigation strategy to minimize collisions. Additionally, the dynamic nature of ice, which moves in response to ship maneuvers, complicates the path planning process. To address these challenges, we propose a novel deep learning model to estimate the coarse dynamics of ice movements triggered by ship actions through occupancy estimation. To ensure real-time applicability, we propose a novel approach that caches intermediate prediction results and seamlessly integrates the predictive model into a graph search planner. We evaluate the proposed planner both in simulation and in a physical testbed against existing approaches and show that our planner significantly reduces collisions with ice when compared to the state-of-the-art. Codes and demos of this work are available at https://github.com/IvanIZ/predictive-asv-planner.