Marine Autonomous Vehicle Fleet Scheduling to Maximise Scientific Impact

Summary

The marine science community increasingly relies on Marine Autonomous Vehicles (MAVs) to collect the critical environmental data required to understand global ocean systems.

Abstract Summary

The marine science community increasingly relies on Marine Autonomous Vehicles (MAVs) to collect the critical environmental data required to understand global ocean systems. However, as these operations scale, manually routing and planning large autonomous fleets becomes exponentially complex and time-consuming. To address this, we propose a mixed-integer linear programming (MILP) model designed to automate and optimise MAV deployment schedules. The model accounts for strict operational constraints, including battery capacities and time windows for data collection, while aiming to maximise total data collection and minimise both the number of deployed vehicles and their energy consumption. A key novelty of this framework is integrating conventional ship itineraries, allowing MAVs to support vessels with mid-mission battery swapping or accelerated transit between waypoints. Computational experiments demonstrate that the model is highly scalable, solving routing problems for fleets of dozens of MAVs in seconds, and scaling to hundreds of vehicles in only a few minutes. Beyond operational scheduling, the framework serves as a robust simulation tool for evaluating 'what-if' scenarios and analysing the impact of varying parameters on deployment strategies. Finally, the solution generates a suite of visualisations designed to enhance explainability and support strategic decision-making for stakeholders.

Key Points

The marine science community increasingly relies on Marine Autonomous Vehicles (MAVs) to collect the critical environmental data required to understand global ocean systems.
However, as these operations scale, manually routing and planning large autonomous fleets becomes exponentially complex and time-consuming.
To address this, we propose a mixed-integer linear programming (MILP) model designed to automate and optimise MAV deployment schedules.
The model accounts for strict operational constraints, including battery capacities and time windows for data collection, while aiming to maximise total data collection and minimise both the number of deployed vehicles and their energy consumption.
A key novelty of this framework is integrating conventional ship itineraries, allowing MAVs to support vessels with mid-mission battery swapping or accelerated transit between waypoints.

Literature Review

Marine Autonomous Vehicles (MAVs) are indispensable tools for marine science and naval operations, enabling data collection in environments where human presence is impractical or hazardous ( Bovio et al.,, 2006 ) . Their navigation and operational systems face unique challenges, including limited underwater communication, dynamic ocean currents, and strict energy constraints ( Zhang et al.,, 2023 ) .

Problem Formulation

This work distinguishes itself by tackling the joint routing of autonomous fleets and conventional support vessels—a problem previously avoided because of its inherent complexity. Rather than relying on stationary infrastructure or heuristic approximations, our framework introduces a highly scalable MILP model that explicitly incorporates discrete, scheduled ship itineraries.

Summary of notations

To transition seamlessly from the conceptual problem formulation to the rigorous mixed-integer linear programming model, we compile a comprehensive summary of all mathematical notations used throughout the rest of this paper. This reference is organised into three primary modules.

Mathematical Model

The problem has five objectives defined in the following order: Maximise the number of MAV assignments to task requirements in the different stations: This is the main objective of the problem: maximising the number of science reviews comes before any other objective.

Case studies and Results

In this section, we present four case studies that leverage the proposed MILP model to plan MAV fleets, maximising the number of science tasks completed while minimising the number of assets deployed and their battery consumption.

The case studies vary in location, science requirements, and fleet size; each is inspired by real MAV science missions but deliberately expanded with additional task requirements and fleet assets.

Case studies and Results — Marine Autonomous Vehicle Fleet Scheduling to Maximise Scientific Impact — Figure 5: Heatmaps of completion rates of task requirements for the deployment around South Georgia and the Falklands: (a) with the research ship and mixed initial battery levels, and (b) without the research ship and with all MAVs deployed at 100% of battery

Sources and Demonstrations

Figures are reproduced from Krari et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.