Autonomous Ship Navigation in Ice-Covered Waters Demo

This demonstration showcases Diffusion Model Predictive Control (DMPC) for safe and efficient navigation in stochastic ice environments. Our approach leverages real-world data to create an accurate simulation environment. We utilize real satellite imagery data to generate the ice map, which provides a realistic representation of ice floe distributions in the Arctic region. Additionally, we employ satellite imagery to detect ice ridges and generate a real ice ridge density map, enabling precise modeling of ice structure and navigation hazards. The simulation also incorporates real ocean current data to accurately model the dynamic marine environment. Together, these real-world data sources create a comprehensive and realistic testing environment for autonomous navigation algorithms in ice-covered waters.

Authors: Diego Calanzone, Gabriel Sasseville, Akash Karthikeyan

See full repo for implementation details: https://github.com/GabrielSasseville01/AUTO-IceNav.

Simulation of autonomous vessel navigation through ice floes using Diffusion MPC.
Real-time cost-map visualization showing navigation constraints.

Analysis Plots

Google Earth View
Satellite view of the Arctic region showing the ice floe region
Google Earth View
Ridge Density Map
Ridge detection and density analysis of ice floes
Ridge Density Map
Simulation Overview
Overall simulation visualization
Simulation Overview
State vs Time
System state evolution over time
State vs Time
Control Inputs vs Time
Control signal analysis over time
Control Inputs vs Time
Kinetic Energy Impulse vs Time
Kinetic energy impulse analysis
Kinetic Energy Impulse vs Time
Impact Locations and Impulse
Ship-ice collision impact analysis
Impact Locations and Impulse
Floe Mass Histogram
Distribution of ice floe masses
Floe Mass Histogram
Ridging Statistics
Ice ridging analysis and statistics
Ridging Statistics

References

de Schaetzen, R., Botros, A., Zhong, N., Murrant, K., Gash, R., & Smith, S. L. (2024). AUTO-IceNav: A Local Navigation Strategy for Autonomous Surface Ships in Broken Ice Fields. arXiv preprint arXiv:2411.17155.
https://arxiv.org/abs/2411.17155
Pan, C., Yi, Z., Shi, G., & Qu, G. (2024). Model-Based Diffusion for Trajectory Optimization. arXiv preprint arXiv:2407.01573.
https://arxiv.org/abs/2407.01573
https://tc.copernicus.org/articles/16/4363/2022/
https://tc.copernicus.org/articles/12/343/2018/
https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2022MS003247
https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2024GL110552
https://tc.copernicus.org/articles/16/1563/2022/
https://www.sciencedirect.com/science/article/abs/pii/S0021999121002576
https://www.thearcticinstitute.org/future-northern-sea-route-golden-waterway-niche/
https://www.nature.com/articles/s41467-025-64437-4