Collection and Evaluation of a Long-Term 4D Agri-Robotic Dataset

TL;DR

This paper presents a long-term dataset for agricultural robotics, focusing on mapping and localization in a vineyard over several months, highlighting challenges and potential solutions for persistent autonomy in changing environments.

Contribution

It introduces a long-term 4D agri-robotic dataset and analyzes localization challenges, proposing a novel method for extracting stable features to enhance long-term performance.

Findings

Identified failures in map-based localization due to environmental changes

Demonstrated the potential of stable temporal features for improving localization

Collected multi-month data in a vineyard for long-term autonomy research

Abstract

Long-term autonomy is one of the most demanded capabilities looked into a robot. The possibility to perform the same task over and over on a long temporal horizon, offering a high standard of reproducibility and robustness, is appealing. Long-term autonomy can play a crucial role in the adoption of robotics systems for precision agriculture, for example in assisting humans in monitoring and harvesting crops in a large orchard. With this scope in mind, we report an ongoing effort in the long-term deployment of an autonomous mobile robot in a vineyard for data collection across multiple months. The main aim is to collect data from the same area at different points in time so to be able to analyse the impact of the environmental changes in the mapping and localisation tasks. In this work, we present a map-based localisation study taking 4 data sessions. We identify expected failures when the pre-built map visually differs from the environment's current appearance and we anticipate LTS-Net, a solution pointed at extracting stable temporal features for improving long-term 4D localisation results.