# Probabilistic Traversability Model for Risk-Aware Motion Planning in Off-Road Environments

arXiv: https://arxiv.org/abs/2210.00153 · HTML: https://mlsanity.com/paper/2210.00153/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2022.

## Built on by (most cited first, 13 of 13)

- [RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Driving](https://mlsanity.com/paper/2402.19341/) (2024)
- [Koopman Kernel Regression](https://mlsanity.com/paper/2305.16215/) (2023)
- [EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomy](https://mlsanity.com/paper/2311.06234/) (2023)
- [PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terrain](https://mlsanity.com/paper/2409.03005/) (2024)
- [PhysORD: A Neuro-Symbolic Approach for Physics-infused Motion Prediction in Off-road Driving](https://mlsanity.com/paper/2404.01596/) (2024)
- [Autonomous Driving in Unstructured Environments: How Far Have We Come?](https://mlsanity.com/paper/2410.07701/) (2024)
- [UFO: Uncertainty-aware LiDAR-image Fusion for Off-road Semantic Terrain Map Estimation](https://mlsanity.com/paper/2403.02642/) (2024)
- [Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving](https://mlsanity.com/paper/2504.16923/) (2025)
- [Circular Accessible Depth: A Robust Traversability Representation for UGV Navigation](https://mlsanity.com/paper/2212.13676/) (2022)
- [Learning Autonomy: Off-Road Navigation Enhanced by Human Input](https://mlsanity.com/paper/2502.18760/) (2025)
- [Situationally-Aware Dynamics Learning](https://mlsanity.com/paper/2505.19574/) (2025)
- [METAVerse: Meta-Learning Traversability Cost Map for Off-Road Navigation](https://mlsanity.com/paper/2307.13991/) (2023)
- [Lightweight Uncertainty Quantification with Simplex Semantic Segmentation for Terrain Traversability](https://mlsanity.com/paper/2407.13392/) (2024)

## Abstract (arXiv)

A key challenge in off-road navigation is that even visually similar terrains or ones from the same semantic class may have substantially different traction properties. Existing work typically assumes no wheel slip or uses the expected traction for motion planning, where the predicted trajectories provide a poor indication of the actual performance if the terrain traction has high uncertainty. In contrast, this work proposes to analyze terrain traversability with the empirical distribution of traction parameters in unicycle dynamics, which can be learned by a neural network in a self-supervised fashion. The probabilistic traction model leads to two risk-aware cost formulations that account for the worst-case expected cost and traction. To help the learned model generalize to unseen environment, terrains with features that lead to unreliable predictions are detected via a density estimator fit to the trained network's latent space and avoided via auxiliary penalties during planning. Simulation results demonstrate that the proposed approach outperforms existing work that assumes no slip or uses the expected traction in both navigation success rate and completion time. Furthermore, avoiding terrains with low density-based confidence score achieves up to 30% improvement in success rate when the learned traction model is used in a novel environment.