paperbot · PL 论文追踪

全部论文 待读 收藏

P2 MultiTest: Physical-Aware Object Insertion for Testing Multi-sensor Fusion Perception Systems

MultiTest:面向多传感器融合感知系统测试的物理感知对象插入方法
ICSE Proceedings of the IEEE/ACM 46th International Conference on Software Engineering2024匹配度 3/10 · 该论文聚焦多传感器融合感知系统的测试用例生成,属于AI/ML系统测试与软件测试范畴,但未涉及静态分析、Agentic程序、LLM辅助形式化验证、浮点程序分析或贝叶斯程序分析等用户核心方向。仅与“机器学习系统质量保障”有边缘关联。引用 16 inbox
Xinyu Gao, Zhijie Wang, Yang Feng, Lei Ma, Zhenyu Chen, Baowen Xu
crossref: 2026-09-12

AI 速览

一句话:提出物理感知的对象插入方法 MultiTest,为多传感器融合感知系统生成多模态测试用例。

多传感器融合(MSF)是自动驾驶、自动机械臂等安全攸关应用的关键技术,随着数据驱动人工智能的持续进步,MSF 感知与理解复杂外部环境的能力不断增强。与传统软件一样,AI 使能的 MSF 系统同样需要充分测试,但现有测试方法主要面向单传感器感知系统,例如基于图像或基于点云的目标检测系统,针对 MSF 系统的多模态测试用例生成研究仍显不足。为此,本文提出 MultiTest,一种物理感知(physical-aware)的对象插入方法,用于为 MSF 感知系统构造多模态测试用例,以弥补多传感器场景下测试用例生成能力的缺失。摘要未报告具体的实验数据与结果,论文评估应围绕该方法在多传感器融合感知系统测试中的实际效果展开。

问题
现有测试方法主要集中于单传感器感知系统(如图像或点云目标检测),缺乏面向多传感器融合(MSF)系统的多模态测试用例生成手段。
方法
提出 MultiTest,采用物理感知(physical-aware)的对象插入方式,为 MSF 感知系统生成多模态测试用例。
评估
摘要未给出具体实验设置与数据;从标题与摘要看,评估针对多传感器融合感知系统,检验所生成多模态测试用例的测试效果。
原文摘要(Abstract)

Multi-sensor fusion stands as a pivotal technique in addressing numerous safety-critical tasks and applications, e.g., self-driving cars and automated robotic arms. With the continuous advancement in data-driven artificial intelligence (AI), MSF's potential for sensing and understanding intricate external environments has been further amplified, bringing a profound impact on intelligent systems and specifically on their perception systems. Similar to traditional software, adequate testing is also required for AI-enabled MSF systems. Yet, existing testing methods primarily concentrate on single-sensor perception systems (e.g., image-based and point cloud-based object detection systems). There remains a lack of emphasis on generating multi-modal test cases for MSF systems.

链接与引用

DOI 原文 ·

BibTeX
@inproceedings{paperbot11430,
  title = {MultiTest: Physical-Aware Object Insertion for Testing Multi-sensor Fusion Perception Systems},
  author = {Xinyu Gao and Zhijie Wang and Yang Feng and Lei Ma and Zhenyu Chen and Baowen Xu},
  booktitle = {ICSE},
  year = {2024},
  doi = {10.1145/3597503.3639191}
}