Rob Weston
Here you will find a landing page supporting the project "There and Back Again: Learning to Simulate Radar For Real World Applications" presented at the International Conference on Robotics and Automation (ICRA) 2021.
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.
This work was carried out by myself, Oiwi Parker Jones and Ingmar Posner at the Applied Artificial Intelligence Lab University of Oxford and presented at the International Conference on Robotics and Automation (ICRA) 2021.
@article{weston2020there,
title={There and Back Again: Learning to Simulate Radar Data for Real-World Applications},
author={Weston, Rob and Jones, Oiwi Parker and Posner, Ingmar},
journal={arXiv preprint arXiv:2011.14389},
year={2020}
}
If you have any other questions, drop me an email.