Road Scene Understanding by Occupancy Grid Learning from Sparse Radar Clusters using Semantic Segmentation
This addresses the problem of robust road scene understanding for autonomous vehicles using radar, though it is incremental by applying existing segmentation techniques to a new sensor modality.
The paper tackled occupancy grid mapping from sparse radar data for autonomous driving by learning an inverse sensor model as a semantic segmentation task, showing that their learned occupancy net outperforms classic methods by a large margin on the NuScenes dataset.
Occupancy grid mapping is an important component in road scene understanding for autonomous driving. It encapsulates information of the drivable area, road obstacles and enables safe autonomous driving. Radars are an emerging sensor in autonomous vehicle vision, becoming more widely used due to their long range sensing, low cost, and robustness to severe weather conditions. Despite recent advances in deep learning technology, occupancy grid mapping from radar data is still mostly done using classical filtering approaches.In this work, we propose learning the inverse sensor model used for occupancy grid mapping from clustered radar data. This is done in a data driven approach that leverages computer vision techniques. This task is very challenging due to data sparsity and noise characteristics of the radar sensor. The problem is formulated as a semantic segmentation task and we show how it can be learned using lidar data for generating ground truth. We show both qualitatively and quantitatively that our learned occupancy net outperforms classic methods by a large margin using the recently released NuScenes real-world driving data.