跳到主要导航 跳到搜索 跳到主要内容

A scenario-based method for safety certification of artificial intelligent software

  • Beihang University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Artificial intelligence (AI) is attractive for safetycritical fields. However, there have been few success cases, for the AI technique is usually lack of determinism and predictability, which is usually regarded as a disqualifier in a safety context. Increased researches and supererogatory efforts are providing to incorporate AI into the safety-critical systems in recent years. In this paper, we present a scenario-based method for safety certification, with the method AI modules of system could be evaluated before invoked, if its trustability is satisfied, then the program will be performed for safetycritical systems, otherwise it will be terminated to ask human assistance or postpone the missions.

源语言英语
主期刊名Proceedings - International Conference on Artificial Intelligence and Computational Intelligence, AICI 2010
481-483
页数3
DOI
出版状态已出版 - 2010
活动2010 International Conference on Artificial Intelligence and Computational Intelligence, AICI 2010 - Sanya, 中国
期限: 23 10月 201024 10月 2010

出版系列

姓名Proceedings - International Conference on Artificial Intelligence and Computational Intelligence, AICI 2010
3

会议

会议2010 International Conference on Artificial Intelligence and Computational Intelligence, AICI 2010
国家/地区中国
Sanya
时期23/10/1024/10/10

指纹

探究 'A scenario-based method for safety certification of artificial intelligent software' 的科研主题。它们共同构成独一无二的指纹。

引用此