The advancement of self-driving technology is driven by the need for robust and efficient perception systems along with frameworks for End-to-End testing, enabled by the CARLA simulator. We introduce C-Shenron, a novel integration of a realistic radar sensor model within CARLA, enabling researchers to develop and test navigation algorithms using radar data. It is the first realistic radar simulator which utilizes LiDAR and camera sensors to generate high-fidelity radar ADC measurements from physics based modeling of the environment. Utilizing this radar sensor and showcasing its capabilities in simulation, we demonstrate improved performance in end-to-end driving scenarios. Our setup aims to rekindle the interest in radar-based self-driving research and promote the development of algorithms that leverages its strengths.

The advancement of self-driving technology is driven by the need for robust perception and navigation systems. Simulators for autonomous driving facilitate the rapid development and testing of navigation algorithms; however, a key issue for most is their inaccurate modeling of the radar sensor. This is a significant drawback as radars offer robust sensing capabilities in adverse weather conditions and occlusions. CARLA, a widely adopted open-source simulator, provides a simplistic radar model that fails to capture the complex physical and material-dependent behavior of real-world radar. To address these limitations, we present CShenron, a radar simulation framework integrated into CARLA, which generates realistic radar measurements by fusing LiDAR and camera data. C-Shenron also supports configurable radar parameters, multiple sensor placements, and scalable dataset generation. Our evaluations demonstrate that radar-camera fusion models, trained with C-Shenron’s generated data, achieve performance equivalent to traditional LiDAR-camera baselines on key metrics from the CARLA leaderboard.

Given partial measurements of a time-varying graph signal, we propose an algorithm to simultaneously estimate both the underlying graph topology and the missing measurements. The proposed algorithm operates by training an interpretable neural network, designed from the unrolling framework. The proposed technique can be used as a graph learning and/or a graph signal reconstruction algorithm. This work builds on prior work in graph learning by tailoring the learned graph to the signal reconstruction task; and also enhances prior work in graph signal reconstruction by allowing the underlying graph to be unknown.