SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions

TL;DR

This paper introduces a new fusion module for multimodal sensor data in autonomous vehicles that maintains high performance even when one sensor modality is missing or corrupted, improving robustness in adverse conditions.

Contribution

We develop a framework-agnostic fusion module that enhances robustness against sensor failures and corruptions, demonstrated within the BEVFusion framework for 3D object detection.

Findings

Our module improves detection accuracy under sensor corruption scenarios.

It outperforms existing methods in handling missing or noisy sensor data.

Achieves state-of-the-art results in extreme weather and sensor failure conditions.

Abstract

Multimodal sensor fusion has demonstrated remarkable performance improvements over unimodal approaches in 3D object detection for autonomous vehicles. Typically, existing methods transform multimodal data from independent sensors, such as camera and LiDAR, into a unified bird's-eye view (BEV) representation for fusion. Although effective in ideal conditions, this strategy suffers from substantial performance deterioration when camera or LiDAR data are missing, corrupted, or noisy. To address this vulnerability, we develop a framework-agnostic fusion module for camera and LiDAR data that allows for handling cases when one of the two modalities is missing or corrupted. To demonstrate the effectiveness of our module, we instantiate it in BEVFusion [1], a well-established framework to combine camera and LiDAR data for 3D object detection. By means of quantitative experiments on the MultiCorrupt dataset, we demonstrate that our module achieves favorable performance improvements under scenarios of missing and corrupted modalities, substantially outperforming existing unified representation approaches across a wide range of sensor deterioration scenarios and reaching state-of-the-art performance in scenarios of corrupted modality due to extreme weather conditions and sensor failure.