LTS-NET: End-to-end Unsupervised Learning of Long-Term 3D Stable objects

TL;DR

This paper introduces LTS-NET, an end-to-end neural network that uses continuous point-wise labels derived from historical data to determine long-term object stability in environments, aiding long-term robot localization.

Contribution

The paper proposes a novel point cloud regression approach with continuous labels for stability assessment, improving over traditional classification methods.

Findings

Outperforms classification-based methods in stability detection

Effective on real-world parking lot datasets

Utilizes historical data for label generation

Abstract

In this research, we present an end-to-end data-driven pipeline for determining the long-term stability status of objects within a given environment, specifically distinguishing between static and dynamic objects. Understanding object stability is key for mobile robots since long-term stable objects can be exploited as landmarks for long-term localisation. Our pipeline includes a labelling method that utilizes historical data from the environment to generate training data for a neural network. Rather than utilizing discrete labels, we propose the use of point-wise continuous label values, indicating the spatio-temporal stability of individual points, to train a point cloud regression network named LTS-NET. Our approach is evaluated on point cloud data from two parking lots in the NCLT dataset, and the results show that our proposed solution, outperforms direct training of a classification model for static vs dynamic object classification.