稳健性(进化)
标杆管理
水准点(测量)
计算机科学
传感器融合
感知
人工智能
数据挖掘
目标检测
工程类
机器学习
激光雷达
计算机安全
风险分析(工程)
航空
数据建模
实时计算
编码(集合论)
对象(语法)
数据收集
作者
Xiaoshuai Hao,Guanqun Liu,Yuting Zhao,Yuheng Ji,Mengchuan Wei,Haimei Zhao,Lingdong Kong,Rong Yin,Yü Liu
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-06-30
卷期号:: 1-6
被引量:35
标识
DOI:10.1109/icme59968.2025.11209381
摘要
Multi-sensor fusion models play a crucial role in autonomous driving perception, particularly in tasks like 3D object detection and HD map construction. These models provide essential and comprehensive static environmental information for autonomous driving systems. While camera-LiDAR fusion methods have shown promising results by integrating data from both modalities, they often depend on complete sensor inputs. This reliance can lead to low robustness and potential failures when sensors are corrupted or missing, raising significant safety concerns. To tackle this challenge, we introduce the Multi-Sensor Corruption Benchmark (MSC-Bench), the first comprehensive benchmark aimed at evaluating the robustness of multi-sensor autonomous driving perception models against various sensor corruptions. Our benchmark includes 16 combinations of corruption types that disrupt both camera and LiDAR inputs, either individually or concurrently. Extensive evaluations of six 3D object detection models and four HD map construction models reveal substantial performance degradation under adverse weather conditions and sensor failures, underscoring critical safety issues. The benchmark toolkit and affiliated code and model checkpoints have been made publicly accessible. Project website: MSC-Bench.
科研通智能强力驱动
Strongly Powered by AbleSci AI