Traversability analysis for autonomous driving in complex environment: A LiDAR‐based terrain modeling approach

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 accurate models results. As an inherent property environment that does not change with different view angles, our approach adopts multi-frame information fusion strategy for modeling. Specifically, normal distributions transform mapping adopted to accurately model by fusing from consecutive LiDAR frames. Then spatial-temporal Bayesian generalized kernel inference bilateral filtering are utilized promote stability completeness results while simultaneously retaining sharp edges. Based on results, each region obtained performing geometric connectivity between neighboring regions. Experimental show proposed method run in real-time outperforms state-of-the-art approaches.