# Capturing Object Detection Uncertainty in Multi-Layer Grid Maps

arXiv: https://arxiv.org/abs/1901.11284 · HTML: https://mlsanity.com/paper/1901.11284/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2019.

## Built on by (most cited first, 10 of 10)

- [Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction](https://mlsanity.com/paper/2403.07263/) (2024)
- [Monte Carlo DropBlock for Modelling Uncertainty in Object Detection](https://mlsanity.com/paper/2108.03614/) (2021)
- [Object Detection as Probabilistic Set Prediction](https://mlsanity.com/paper/2203.07980/) (2022)
- [Uncertainty-Aware Lidar Place Recognition in Novel Environments](https://mlsanity.com/paper/2210.01361/) (2022)
- [Approaching Neural Network Uncertainty Realism](https://mlsanity.com/paper/2101.02974/) (2021)
- [Fast and Reliable Probabilistic Face Embeddings in the Wild](https://mlsanity.com/paper/2102.04075/) (2021)
- [Improving Lidar-Based Semantic Segmentation of Top-View Grid Maps by Learning Features in Complementary Representations](https://mlsanity.com/paper/2203.01151/) (2022)
- [Can Transformer Attention Spread Give Insights Into Uncertainty of Detected and Tracked Objects?](https://mlsanity.com/paper/2210.14391/) (2022)
- [Bayesian Approximation-Based Trajectory Prediction and Tracking with 4D Radar](https://mlsanity.com/paper/2502.01357/) (2025)
- [OFAL: An Oracle-Free Active Learning Framework](https://mlsanity.com/paper/2508.08126/) (2025)

## Abstract (arXiv)

We propose a deep convolutional object detector for automated driving applications that also estimates classification, pose and shape uncertainty of each detected object. The input consists of a multi-layer grid map which is well-suited for sensor fusion, free-space estimation and machine learning. Based on the estimated pose and shape uncertainty we approximate object hulls with bounded collision probability which we find helpful for subsequent trajectory planning tasks. We train our models based on the KITTI object detection data set. In a quantitative and qualitative evaluation some models show a similar performance and superior robustness compared to previously developed object detectors. However, our evaluation also points to undesired data set properties which should be addressed when training data-driven models or creating new data sets.