# Uncertainty-aware Perception Models for Off-road Autonomous Unmanned Ground Vehicles

arXiv: https://arxiv.org/abs/2209.11115 · HTML: https://mlsanity.com/paper/2209.11115/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 22 Sep 2022.

## Builds on (most cited first, 19 of 19)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments](https://mlsanity.com/paper/1811.10200/) (2018)
- [RELLIS-3D Dataset: Data, Benchmarks and Analysis](https://mlsanity.com/paper/2011.12954/) (2020)
- [Masksembles for Uncertainty Estimation](https://mlsanity.com/paper/2012.08334/) (2020)
- [ORFD: A Dataset and Benchmark for Off-Road Freespace Detection](https://mlsanity.com/paper/2206.09907/) (2022)
- [Risk-Aware Off-Road Navigation via a Learned Speed Distribution Map](https://mlsanity.com/paper/2203.13429/) (2022)
- [A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios](https://mlsanity.com/paper/2103.13109/) (2021)
- [Memory-based Semantic Segmentation for Off-road Unstructured Natural Environments](https://mlsanity.com/paper/2108.05635/) (2021)
- [Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images](https://mlsanity.com/paper/2109.07245/) (2021)
- [Explicit-risk-aware Path Planning with Reward Maximization](https://mlsanity.com/paper/1903.03187/) (2019)

## Built on by (most cited first, 1 of 1)

- [How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environments](https://mlsanity.com/paper/2605.29599/) (2026)

## Abstract (arXiv)

Off-road autonomous unmanned ground vehicles (UGVs) are being developed for military and commercial use to deliver crucial supplies in remote locations, help with mapping and surveillance, and to assist war-fighters in contested environments. Due to complexity of the off-road environments and variability in terrain, lighting conditions, diurnal and seasonal changes, the models used to perceive the environment must handle a lot of input variability. Current datasets used to train perception models for off-road autonomous navigation lack of diversity in seasons, locations, semantic classes, as well as time of day. We test the hypothesis that model trained on a single dataset may not generalize to other off-road navigation datasets and new locations due to the input distribution drift. Additionally, we investigate how to combine multiple datasets to train a semantic segmentation-based environment perception model and we show that training the model to capture uncertainty could improve the model performance by a significant margin. We extend the Masksembles approach for uncertainty quantification to the semantic segmentation task and compare it with Monte Carlo Dropout and standard baselines. Finally, we test the approach against data collected from a UGV platform in a new testing environment. We show that the developed perception model with uncertainty quantification can be feasibly deployed on an UGV to support online perception and navigation tasks.