Papers for

maritime navigation teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Multi-agent robot motion planning respects legal rules and detects rule breakers

Auditable and Deployable Multi-Agent Motion Planning via Posetal Games from Legal Guidelines

Abstract: When robots are deployed in the real-world, they must interact with other agents and accomplish their own goals while adhering to legal constraints. These potentially conflicting objectives are often only partially prioritized, making scalarized objectives or fully specified hierarchies unsuitable. We present a framework for multi-agent motion planning under legal requirements based on games with partially ordered preferences (posetal games). Scenario-independent legal guidelines order abstract legal concerns, from which we automatically derive agent preferences and a legal game for any concrete scenario. Agents may refine their legal preferences with private objectives, and regulators may refine the guideline as laws evolve. We prove that such customizations can only remove equilibria and thus preserve legality. To coordinate agents without explicitly communicating private preferences, we introduce belief play, which provably recovers the true equilibria from conservative local games, and a distributed iterative best-response protocol requiring less information. We apply the framework to maritime navigation, systematically lifting pairwise traffic rules to multi-vessel encounters. On seven encounters with up to four vessels, every rule violation of the committed equilibria is certified as forced by the legal hierarchy or unsatisfiable, and defectors are identified from public information in all tested cases. These results indicate that guideline-based posetal games offer an auditable route from partially specified laws to multi-agent motion planning.

Thu 15 OctMultiagent SystemsComputer Science and Game TheoryRobotics
The gist
When robots move around in places like sea lanes, they need to follow laws while achieving their goals alongside others. The authors created a way to turn legal rules into a kind of game where robots plan their movements with partially ranked preferences instead of fixed priorities. This method can find plans where robots follow the law as much as possible and also spot who breaks rules just from public information. They tested their approach with up to four ships navigating together and verified that any rule violations were either forced or clearly identified.
Open → 2610.22277v1

Sea-ice type prediction improved using weakly supervised multi-label learning

Multi-Label Proportion Learning for Sea-Ice Type Prediction

Abstract: Sea-ice type prediction is important for climate monitoring, maritime navigation, and decision-making in polar regions. The main source of label data for this task is the ice chart, produced manually by ice analysts who interpret satellite imagery to delineate ice zones into polygons. Although ice charts are valuable, their production is labor-intensive and expensive, motivating recent efforts to automate the process using deep learning. However, deep learning models require patch-level (or pixel-level) label data for training, while ice charts provide only polygon-level annotations. As a workaround, supervised approaches often create approximate patch-level labels from polygon-level ice chart labels by assigning each sample the dominant ice type of its parent polygon. This approach enables supervised training but creates an ill-posed learning problem with intrinsically approximate solution. In this paper, we redefine sea-ice type prediction as a weakly supervised multi-label proportion learning problem to be able to directly use the polygon-level ice chart labels and avoid unnecessary label approximation for improved prediction accuracy. To address this problem, we propose a two-module framework where first Multiple Instance Learning (MIL) is used for water--ice classification, and then a multi-label proportion learning (MLPL) is introduced for ice-type composition prediction. We further extend this framework with a multimodal model that integrates SAR imagery with AMSR2 brightness temperatures and ERA5 reanalysis data through modality-guided auxiliary regularization. Evaluated on the AI4Arctic dataset, the SAR-only model reduces MAE by 14.5\% and more than doubles mean ice-class F1 over the best supervised baseline. The multimodal model further reduces MAE by 21.5\% and raises mean F1 by 41.2\% over the SAR-only model, and by 52.7\% over the supervised multimodal baseline.

Mon 14 SeptMachine Learning
The gist
Predicting the types of sea ice is important for climate study and safe ship travel but is hard because detailed labels are scarce. The authors propose a new approach that learns directly from less detailed ice chart data without guessing exact labels, improving accuracy. They combine satellite radar images with other climate data to further boost their predictions. Tests showed their method makes fewer mistakes and identifies ice types better than older approaches.
Open → 2609.16347v1