Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation

TL;DR

This paper introduces a self-supervised lidar segmentation method that automates annotation using SLAM and ray-tracing, enabling robots to improve navigation by learning from multiple sessions without human labels.

Contribution

The authors develop a self-supervised learning framework for lidar segmentation that automatically labels data through SLAM and ray-tracing, enhancing autonomous indoor navigation.

Findings

Improves segmentation accuracy over multiple sessions

Enhances robot navigation in complex environments

Boosts localization performance with semantically filtered point clouds

Abstract

We present a self-supervised learning approach for the semantic segmentation of lidar frames. Our method is used to train a deep point cloud segmentation architecture without any human annotation. The annotation process is automated with the combination of simultaneous localization and mapping (SLAM) and ray-tracing algorithms. By performing multiple navigation sessions in the same environment, we are able to identify permanent structures, such as walls, and disentangle short-term and long-term movable objects, such as people and tables, respectively. New sessions can then be performed using a network trained to predict these semantic labels. We demonstrate the ability of our approach to improve itself over time, from one session to the next. With semantically filtered point clouds, our robot can navigate through more complex scenarios, which, when added to the training pool, help to improve our network predictions. We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.