FASTC: A Fast Attentional Framework for Semantic Traversability Classification Using Point Cloud

TL;DR

This paper introduces FASTC, a computationally efficient attentional framework that improves semantic traversability classification from point clouds by combining novel feature extraction and spatio-temporal attention modules, outperforming existing methods.

Contribution

The paper presents a new pillar feature extraction module using PointNet and a spatio-temporal attention mechanism for better traversability assessment from point clouds.

Findings

Achieves superior accuracy on Semantic KITTI and RELLIS-3D datasets.

Reduces computational cost compared to 3D convolution methods.

Effectively handles varying density in LIDAR point clouds.

Abstract

Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature extraction module that utilizes PointNet to capture features from point clouds organized in vertical volume and a 2D encoder-decoder structure to conduct traversability classification instead of the widely used 3D convolutions. This results in less computational cost while even better performance is achieved at the same time. We then propose a new spatio-temporal attention module to fuse multi-frame information, which can properly handle the varying density problem of LIDAR point clouds, and this makes our module able to assess distant areas more accurately. Comprehensive experimental results on augmented Semantic KITTI and RELLIS-3D datasets show that our method is able to achieve superior performance over existing approaches both quantitatively and quantitatively.