# There and Back Again: Learning to Simulate Radar Data for Real-World Applications

arXiv: https://arxiv.org/abs/2011.14389 · HTML: https://mlsanity.com/paper/2011.14389/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence](https://mlsanity.com/paper/2110.15245/) (2021)
- [SoK: On the Semantic AI Security in Autonomous Driving](https://mlsanity.com/paper/2203.05314/) (2022)
- [RadSimReal: Bridging the Gap Between Synthetic and Real Data in Radar Object Detection With Simulation](https://mlsanity.com/paper/2404.18150/) (2024)
- [Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges](https://mlsanity.com/paper/2306.09304/) (2023)
- [Radar Occupancy Prediction with Lidar Supervision while Preserving Long-Range Sensing and Penetrating Capabilities](https://mlsanity.com/paper/2112.04282/) (2021)
- [RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes](https://mlsanity.com/paper/2505.20967/) (2025)
- [L2RDaS: Synthesizing 4D Radar Tensors for Model Generalization via Dataset Expansion](https://mlsanity.com/paper/2503.03637/) (2025)
- [Controllable Radar Simulation with Waveform Parameter Embedding](https://mlsanity.com/paper/2506.03134/) (2025)
- [RadarGen: Automotive Radar Point Cloud Generation from Cameras](https://mlsanity.com/paper/2512.17897/) (2025)
- [Deep learning for radar data exploitation of autonomous vehicle](https://mlsanity.com/paper/2203.08038/) (2022)
- [Pointing the Way: Refining Radar-Lidar Localization Using Learned ICP Weights](https://mlsanity.com/paper/2309.08731/) (2023)

## Abstract (arXiv)

Simulating realistic radar data has the potential to significantly accelerate the development of data-driven approaches to radar processing. However, it is fraught with difficulty due to the notoriously complex image formation process. Here we propose to learn a radar sensor model capable of synthesising faithful radar observations based on simulated elevation maps. In particular, we adopt an adversarial approach to learning a forward sensor model from unaligned radar examples. In addition, modelling the backward model encourages the output to remain aligned to the world state through a cyclical consistency criterion. The backward model is further constrained to predict elevation maps from real radar data that are grounded by partial measurements obtained from corresponding lidar scans. Both models are trained in a joint optimisation. We demonstrate the efficacy of our approach by evaluating a down-stream segmentation model trained purely on simulated data in a real-world deployment. This achieves performance within four percentage points of the same model trained entirely on real data.