Robustness-Aware 3D Object Detection in Autonomous Driving: A Review and Outlook

TL;DR

This paper reviews 3D object detection methods for autonomous driving, emphasizing their robustness against environmental challenges, and highlights the superiority of multi-modal approaches through comprehensive evaluation.

Contribution

It provides a systematic survey of detection algorithms focusing on robustness, introduces a new taxonomy, and evaluates trade-offs on challenging datasets for practical insights.

Findings

Multi-modal detection approaches show higher robustness.

Robustness is crucial alongside accuracy and latency.

Evaluation on KITTI-C and nuScenes-C datasets highlights current limitations.

Abstract

In the realm of modern autonomous driving, the perception system is indispensable for accurately assessing the state of the surrounding environment, thereby enabling informed prediction and planning. The key step to this system is related to 3D object detection that utilizes vehicle-mounted sensors such as LiDAR and cameras to identify the size, the category, and the location of nearby objects. Despite the surge in 3D object detection methods aimed at enhancing detection precision and efficiency, there is a gap in the literature that systematically examines their resilience against environmental variations, noise, and weather changes. This study emphasizes the importance of robustness, alongside accuracy and latency, in evaluating perception systems under practical scenarios. Our work presents an extensive survey of camera-only, LiDAR-only, and multi-modal 3D object detection algorithms, thoroughly evaluating their trade-off between accuracy, latency, and robustness, particularly on datasets like KITTI-C and nuScenes-C to ensure fair comparisons. Among these, multi-modal 3D detection approaches exhibit superior robustness, and a novel taxonomy is introduced to reorganize the literature for enhanced clarity. This survey aims to offer a more practical perspective on the current capabilities and the constraints of 3D object detection algorithms in real-world applications, thus steering future research towards robustness-centric advancements.