AMP2026: A Multi-Platform Marine Robotics Dataset for Tracking and Mapping

TL;DR

AMP2026 is a comprehensive multi-platform marine robotics dataset that facilitates research in marine perception, tracking, and mapping by providing synchronized data from aerial, surface, and submerged sensors across multiple deployments.

Contribution

The paper introduces AMP2026, a novel multi-platform dataset with synchronized multi-modal marine sensor data, supporting advanced perception and mapping research in complex marine environments.

Findings

Dataset includes synchronized aerial, surface, and submerged sensor data.

Supports research in multi-view tracking and marine environment mapping.

Enables development of perception algorithms for dynamic marine settings.

Abstract

Marine environments present significant challenges for perception and autonomy due to dynamic surfaces, limited visibility, and complex interactions between aerial, surface, and submerged sensing modalities. This paper introduces the Aerial Marine Perception Dataset (AMP2026), a multi-platform marine robotics dataset collected across multiple field deployments designed to support research in two primary areas: multi-view tracking and marine environment mapping. The dataset includes synchronized data from aerial drones, boat-mounted cameras, and submerged robotic platforms, along with associated localization and telemetry information. The goal of this work is to provide a publicly available dataset enabling research in marine perception and multi-robot observation scenarios. This paper describes the data collection methodology, sensor configurations, dataset organization, and intended research tasks supported by the dataset.