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

arXiv: https://arxiv.org/abs/2307.02060 · HTML: https://mlsanity.com/paper/2307.02060/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2023.

## Built on by (most cited first, 9 of 9)

- [RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Driving](https://mlsanity.com/paper/2402.19341/) (2024)
- [DTG : Diffusion-based Trajectory Generation for Mapless Global Navigation](https://mlsanity.com/paper/2403.09900/) (2024)
- [Autonomous Driving in Unstructured Environments: How Far Have We Come?](https://mlsanity.com/paper/2410.07701/) (2024)
- [Outlier-Robust Long-Term Robotic Mapping Leveraging Ground Segmentation](https://mlsanity.com/paper/2405.11176/) (2024)
- [ROLO-SLAM: Rotation-Optimized LiDAR-Only SLAM in Uneven Terrain with Ground Vehicle](https://mlsanity.com/paper/2501.02166/) (2025)
- [Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process](https://mlsanity.com/paper/2503.04134/) (2025)
- [Scene-Agnostic Traversability Labeling and Estimation via a Multimodal Self-supervised Framework](https://mlsanity.com/paper/2508.18249/) (2025)
- [ProTerrain: Probabilistic Physics-Informed Rough Terrain World Modeling](https://mlsanity.com/paper/2510.19364/) (2025)
- [Wild-Drive: Off-Road Scene Captioning and Path Planning via Robust Multi-modal Routing and Efficient Large Language Model](https://mlsanity.com/paper/2603.00694/) (2026)

## Abstract (arXiv)

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.