Semantic2D: Enabling Semantic Scene Understanding with 2D Lidar Alone

TL;DR

Semantic2D introduces a novel approach for semantic scene understanding using only 2D lidar data, including a new dataset, a semi-automatic labeling method, and a specialized segmentation algorithm, advancing robotic perception and navigation.

Contribution

It provides the first publicly available 2D lidar semantic dataset, a semi-automatic labeling framework, and a point-wise segmentation algorithm tailored for 2D lidar sensors.

Findings

Effective semantic segmentation of 2D lidar data demonstrated

Improved navigation policies using semantic information shown

Dataset and methods enhance robotic perception pipelines

Abstract

This article presents a complete semantic scene understanding workflow using only a single 2D lidar. This fills the gap in 2D lidar semantic segmentation, thereby enabling the rethinking and enhancement of existing 2D lidar-based algorithms for application in various mobile robot tasks. It introduces the first publicly available 2D lidar semantic segmentation dataset and the first fine-grained semantic segmentation algorithm specifically designed for 2D lidar sensors on autonomous mobile robots. To annotate this dataset, we propose a novel semi-automatic semantic labeling framework that requires minimal human effort and provides point-level semantic annotations. The data was collected by three different types of 2D lidar sensors across twelve indoor environments, featuring a range of common indoor objects. Furthermore, the proposed semantic segmentation algorithm fully exploits raw lidar information -- position, range, intensity, and incident angle -- to deliver stochastic, point-wise semantic segmentation. We present a series of semantic occupancy grid mapping experiments and demonstrate two semantically-aware navigation control policies based on 2D lidar. These results demonstrate that the proposed semantic 2D lidar dataset, semi-automatic labeling framework, and segmentation algorithm are effective and can enhance different components of the robotic navigation pipeline. Multimedia resources are available at: https://youtu.be/P1Hsvj6WUSY.