RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar

TL;DR

RadarOcc introduces a novel 3D occupancy prediction method using 4D imaging radar sensors, enhancing robustness in autonomous driving especially under adverse weather conditions by directly processing radar data with innovative techniques.

Contribution

The paper presents RadarOcc, a new approach that leverages 4D radar data for 3D occupancy prediction, overcoming limitations of sparse and noisy radar point clouds with novel processing techniques.

Findings

RadarOcc achieves state-of-the-art radar-based 3D occupancy prediction performance.

RadarOcc outperforms traditional LiDAR and camera methods in adverse weather conditions.

The method demonstrates robustness and effectiveness through extensive benchmarking and ablation studies.

Abstract

3D occupancy-based perception pipeline has significantly advanced autonomous driving by capturing detailed scene descriptions and demonstrating strong generalizability across various object categories and shapes. Current methods predominantly rely on LiDAR or camera inputs for 3D occupancy prediction. These methods are susceptible to adverse weather conditions, limiting the all-weather deployment of self-driving cars. To improve perception robustness, we leverage the recent advances in automotive radars and introduce a novel approach that utilizes 4D imaging radar sensors for 3D occupancy prediction. Our method, RadarOcc, circumvents the limitations of sparse radar point clouds by directly processing the 4D radar tensor, thus preserving essential scene details. RadarOcc innovatively addresses the challenges associated with the voluminous and noisy 4D radar data by employing Doppler bins descriptors, sidelobe-aware spatial sparsification, and range-wise self-attention mechanisms. To minimize the interpolation errors associated with direct coordinate transformations, we also devise a spherical-based feature encoding followed by spherical-to-Cartesian feature aggregation. We benchmark various baseline methods based on distinct modalities on the public K-Radar dataset. The results demonstrate RadarOcc's state-of-the-art performance in radar-based 3D occupancy prediction and promising results even when compared with LiDAR- or camera-based methods. Additionally, we present qualitative evidence of the superior performance of 4D radar in adverse weather conditions and explore the impact of key pipeline components through ablation studies.