# Probably Unknown: Deep Inverse Sensor Modelling In Radar

arXiv: https://arxiv.org/abs/1810.08151 · HTML: https://mlsanity.com/paper/1810.08151/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2018.

## Built on by (most cited first, 16 of 16)

- [CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception](https://mlsanity.com/paper/2304.00670/) (2023)
- [Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation](https://mlsanity.com/paper/2203.11160/) (2022)
- [NVRadarNet: Real-Time Radar Obstacle and Free Space Detection for Autonomous Driving](https://mlsanity.com/paper/2209.14499/) (2022)
- [Enabling Visual Recognition at Radio Frequency](https://mlsanity.com/paper/2405.19516/) (2024)
- [Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges](https://mlsanity.com/paper/2306.09304/) (2023)
- [Bootstrapping Autonomous Driving Radars with Self-Supervised Learning](https://mlsanity.com/paper/2312.04519/) (2023)
- [Radar Occupancy Prediction with Lidar Supervision while Preserving Long-Range Sensing and Penetrating Capabilities](https://mlsanity.com/paper/2112.04282/) (2021)
- [Quantification of Uncertainties in Deep Learning-based Environment Perception](https://mlsanity.com/paper/2306.03018/) (2023)
- [RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes](https://mlsanity.com/paper/2505.20967/) (2025)
- [Deep Radar Inverse Sensor Models for Dynamic Occupancy Grid Maps](https://mlsanity.com/paper/2305.12409/) (2023)
- [Sensor Visibility Estimation: Metrics and Methods for Systematic Performance Evaluation and Improvement](https://mlsanity.com/paper/2211.06308/) (2022)
- [ROSS: Radar Off-road Semantic Segmentation](https://mlsanity.com/paper/2310.13551/) (2023)
- [Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling](https://mlsanity.com/paper/2402.17622/) (2024)
- [Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data](https://mlsanity.com/paper/2402.17653/) (2024)
- [RadarLCD: Learnable Radar-based Loop Closure Detection Pipeline](https://mlsanity.com/paper/2309.07094/) (2023)
- [On Learning Spatial Structure from Pre-Beamforming Per-Antenna Range-Doppler Radar Measurements](https://mlsanity.com/paper/2604.01921/) (2026)

## Abstract (arXiv)

Radar presents a promising alternative to lidar and vision in autonomous vehicle applications, able to detect objects at long range under a variety of weather conditions. However, distinguishing between occupied and free space from raw radar power returns is challenging due to complex interactions between sensor noise and occlusion. To counter this we propose to learn an Inverse Sensor Model (ISM) converting a raw radar scan to a grid map of occupancy probabilities using a deep neural network. Our network is self-supervised using partial occupancy labels generated by lidar, allowing a robot to learn about world occupancy from past experience without human supervision. We evaluate our approach on five hours of data recorded in a dynamic urban environment. By accounting for the scene context of each grid cell our model is able to successfully segment the world into occupied and free space, outperforming standard CFAR filtering approaches. Additionally by incorporating heteroscedastic uncertainty into our model formulation, we are able to quantify the variance in the uncertainty throughout the sensor observation. Through this mechanism we are able to successfully identify regions of space that are likely to be occluded.