# Fusion of neural networks, for LIDAR-based evidential road mapping

arXiv: https://arxiv.org/abs/2102.03326 · HTML: https://mlsanity.com/paper/2102.03326/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 53 references that are in the map.
- First posted on arXiv 5 Feb 2021.

## Builds on (most cited first, 17 of 17)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [Progressive LiDAR Adaptation for Road Detection](https://mlsanity.com/paper/1904.01206/) (2019)
- [Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds](https://mlsanity.com/paper/1802.01500/) (2018)
- [A Random Finite Set Approach for Dynamic Occupancy Grid Maps with Real-Time Application](https://mlsanity.com/paper/1605.02406/) (2016)
- [Logistic Regression, Neural Networks and Dempster-Shafer Theory: a New Perspective](https://mlsanity.com/paper/1807.01846/) (2018)
- [ChipNet: Real-Time LiDAR Processing for Drivable Region Segmentation on an FPGA](https://mlsanity.com/paper/1808.03506/) (2018)
- [Evidential Occupancy Grid Map Augmentation using Deep Learning](https://mlsanity.com/paper/1801.05297/) (2018)
- [Automatic Vector-based Road Structure Mapping Using Multi-beam LiDAR](https://mlsanity.com/paper/1804.07028/) (2018)
- [Caroline: An Autonomously Driving Vehicle for Urban Environments](https://mlsanity.com/paper/1409.6584/) (2014)

## Built on by (most cited first, 2 of 2)

- [ROD: RGB-Only Fast and Efficient Off-road Freespace Detection](https://mlsanity.com/paper/2508.08697/) (2025)
- [Uncertainty-Aware Velocity Correction for Proprioceptive Vehicle Localization using Evidential Mamba](https://mlsanity.com/paper/2607.05669/) (2026)

## Abstract (arXiv)

LIDAR sensors are usually used to provide autonomous vehicles with 3D representations of their environment. In ideal conditions, geometrical models could detect the road in LIDAR scans, at the cost of a manual tuning of numerical constraints, and a lack of flexibility. We instead propose an evidential pipeline, to accumulate road detection results obtained from neural networks. First, we introduce RoadSeg, a new convolutional architecture that is optimized for road detection in LIDAR scans. RoadSeg is used to classify individual LIDAR points as either belonging to the road, or not. Yet, such point-level classification results need to be converted into a dense representation, that can be used by an autonomous vehicle. We thus secondly present an evidential road mapping algorithm, that fuses consecutive road detection results. We benefitted from a reinterpretation of logistic classifiers, which can be seen as generating a collection of simple evidential mass functions. An evidential grid map that depicts the road can then be obtained, by projecting the classification results from RoadSeg into grid cells, and by handling moving objects via conflict analysis. The system was trained and evaluated on real-life data. A python implementation maintains a 10 Hz framerate. Since road labels were needed for training, a soft labelling procedure, relying lane-level HD maps, was used to generate coarse training and validation sets. An additional test set was manually labelled for evaluation purposes. So as to reach satisfactory results, the system fuses road detection results obtained from three variants of RoadSeg, processing different LIDAR features.