Traversability Analysis for Autonomous Driving in Complex Environment: A LiDAR-based Terrain Modeling Approach

TL;DR

This paper introduces a LiDAR-based terrain modeling method for autonomous driving that fuses multi-frame data to produce stable, complete terrain maps and assesses traversability in real-time, outperforming existing methods.

Contribution

A novel multi-frame LiDAR terrain modeling approach using normal distributions transform and Bayesian inference for accurate, stable, and complete terrain analysis in complex environments.

Findings

Real-time performance demonstrated in experiments.

Outperforms state-of-the-art terrain modeling methods.

Provides reliable traversability analysis for autonomous driving.

Abstract

For autonomous driving, traversability analysis is one of the most basic and essential tasks. In this paper, we propose a novel LiDAR-based terrain modeling approach, which could output stable, complete and accurate terrain models and traversability analysis results. As terrain is an inherent property of the environment that does not change with different view angles, our approach adopts a multi-frame information fusion strategy for terrain modeling. Specifically, a normal distributions transform mapping approach is adopted to accurately model the terrain by fusing information from consecutive LiDAR frames. Then the spatial-temporal Bayesian generalized kernel inference and bilateral filtering are utilized to promote the stability and completeness of the results while simultaneously retaining the sharp terrain edges. Based on the terrain modeling results, the traversability of each region is obtained by performing geometric connectivity analysis between neighboring terrain regions. Experimental results show that the proposed method could run in real-time and outperforms state-of-the-art approaches.