Safety Challenges of AI in Autonomous Systems Design - Solutions from Human Factors Perspective Emphasizing AI Awareness

被引：7

作者：

Karvonen, Hannu ^{[1
]}

Heikkila, Eetu ^{[1
]}

Wahlstrom, Mikael ^{[1
]}

机构：

[1] VTT Tech Res Ctr Finland Ltd, POB 1000, Espoo 02044, Finland

来源：

ENGINEERING PSYCHOLOGY AND COGNITIVE ERGONOMICS. COGNITION AND DESIGN, EPCE 2020, PT II | 2020年 / 12187卷

关键词：

Artificial intelligence; Autonomous systems; Human factors; Safety; Systems engineering; NETWORKS;

D O I：

10.1007/978-3-030-49183-3_12

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Artificial intelligence (AI) is a key technology that is utilized in autonomous systems. However, using AI in such systems introduces also several safety challenges, many of which are related to complex human-AI interactions. In general, these challenges relate to the changing roles of the people who interact with the increasingly autonomous systems in various ways. In this paper, we consider a set of practical safety challenges related to applying advanced AI to autonomous machine systems and present solutions from the perspective of human factors. We apply the novel concept of AI awareness (AIA) to discuss the challenges in detail, and based on this, provide suggestions and guidelines for mitigating the AI safety risks with autonomous systems. In addition, we briefly consider the system design process to identify the actions that should be taken to ensure AIA throughout the different systems engineering design phases. The theoretical research presented in this paper aims to provide the first steps towards considering AIA in autonomous systems and understanding the human factors perspective viewpoint on AI safety for autonomous systems.

引用

页码：147 / 160

页数：14

共 29 条

[11]

Forsberg K., 1992, Engineering Management Journal, V4, P36, DOI [DOI 10.1080/10429247.1992.11414684, https://doi.org/10.1080/10429247.1992.11414684]

[12] Generative Adversarial Networks in Al-Enabled Safety Critical Systems: Friend or Foe? [J].

Fournaris, Apostolos P. ;

Lalos, Aris S. ;

Serpanos, Dimitrios .

COMPUTER, 2019, 52 (09) :78-81

[13]

Karvonen H., 2014, SAFIR2014 research report, VTT Research Report VTT-R-05997-14

[14]

Karvonen H., 2019, HWID 2018., V544, P175, DOI [10.1007/978-3-030-05297-312, DOI 10.1007/978-3-030-05297-312]

[15]

Karvonen H., 2015, AUT 21 C, V44

[16] Developing artificial neural networks for safety critical systems [J].

Kurd, Zeshan ;

Kelly, Tim ;

Austin, Jim .

NEURAL COMPUTING & APPLICATIONS, 2007, 16 (01) :11-19

[17] Trust in automation: Designing for appropriate reliance [J].

Lee, JD ;

See, KA .

HUMAN FACTORS, 2004, 46 (01) :50-80

[18]

Miranda D., 2020, NASA Technology Taxonomy 2019

[19]

Mohseni S, 2019, Arxiv, DOI arXiv:1912.09630

[20]

Moore A., 2017, Forbes

← 1 2 3 →