arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.00740cs.HCcs.AIcs.CYcs.SE
收藏

协同人工智能需要更强的风险驱动能力

Collaborative Artificial Intelligence Needs Stronger Assurances Driven by Risks

University of Innsbruck(因斯布鲁克大学);Free University of Bozen-Bolzano(博尔扎诺自由大学);Blekinge Institute of Technology(布莱金厄理工学院);Fraunhofer Italia Research(弗劳恩霍夫意大利研究院);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会)

Jubril Gbolahan Adigun, Matteo Camilli, Michael Felderer, Andrea Giusti, Dominik T Matt, Anna Perini, Barbara Russo, Angelo Susi

摘要:

协作人工智能系统(CAIS)旨在与人类在共享空间中合作,以实现共同目标。这种危急的环境产生了可能伤害人类的危险情况。因此,最重要的是建立这种系统,并有力地保证遵守要求、特定领域的标准和条例。迄今为止,此类系统仅报告了很少的规模影响,因为仍有许多工作要管理可能的风险。我们确定在这种情况下出现的问题,然后我们报告我们的愿景,以及我们的多学科研究团队组成的软件/系统和机电一体化工程师的进展,开发一个风险驱动的保证过程CAIS。

英文摘要:

Collaborative AI systems (CAISs) aim at working together with humans in a shared space to achieve a common goal. This critical setting yields hazardous circumstances that could harm human beings. Thus, building such systems with strong assurances of compliance with requirements, domain-specific standards and regulations is of greatest importance. Only few scale impact has been reported so far for such systems since much work remains to manage possible risks. We identify emerging problems in this context and then we report our vision, as well as the progress of our multidisciplinary research team composed of software/systems, and mechatronics engineers to develop a risk-driven assurance process for CAISs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑