TE-NeXt: A LiDAR-Based 3D Sparse Convolutional Network for Traversability Estimation

TL;DR

TE-NeXt is an innovative LiDAR-based 3D sparse convolutional network that improves traversability estimation across diverse environments, combining attention mechanisms and residual blocks for enhanced accuracy and robustness.

Contribution

The paper introduces TE-NeXt, a novel architecture integrating attention and residual 3D sparse convolutions for improved traversability estimation from LiDAR data.

Findings

Outperforms state-of-the-art in semantic segmentation

Demonstrates high generalization in urban and natural environments

Maintains robustness and reliability in unstructured settings

Abstract

This paper presents TE-NeXt, a novel and efficient architecture for Traversability Estimation (TE) from sparse LiDAR point clouds based on a residual convolution block. TE-NeXt block fuses notions of current trends such as attention mechanisms and 3D sparse convolutions. TE-NeXt aims to demonstrate high capacity for generalisation in a variety of urban and natural environments, using well-known and accessible datasets such as SemanticKITTI, Rellis-3D and SemanticUSL. Thus, the designed architecture ouperforms state-of-the-art methods in the problem of semantic segmentation, demonstrating better results in unstructured environments and maintaining high reliability and robustness in urbans environments, which leads to better abstraction. Implementation is available in a open repository to the scientific community with the aim of ensuring the reproducibility of results.