arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.09159cs.AI
收藏

智能自治系统的反脆弱性

Antifragility for Intelligent Autonomous Systems

Ericsson Research(爱立信研究院)

Anusha Mujumdar, Swarup Kumar Mohalik, Ramamurthy Badrinath

摘要:

反脆弱系统在危险存在的情况下成长得更好。这与脆弱的系统相反,脆弱的系统在危险的存在下崩溃,健壮的系统在一定程度上容忍危险,弹性系统-如自我修复系统-在一段时间的恢复后恢复到早期预期的行为。反脆弱性的概念是塔勒布为经济系统引入的,但它的适用性也在生物和工程领域得到了说明。在本文中,我们提出了一种架构,赋予智能自治系统反脆弱性,特别是那些目标驱动和基于AI规划的系统。我们认为,这种架构允许系统通过发现新的能力,通过危险本身(机会主义)或通过审议(战略)获得自我改进。提出了一种基于人工智能规划的自主轮式机器人的案例研究。我们表明,与建议的架构,机器人开发反脆弱性行为方面的溢油危险。

英文摘要:

Antifragile systems grow measurably better in the presence of hazards. This is in contrast to fragile systems which break down in the presence of hazards, robust systems that tolerate hazards up to a certain degree, and resilient systems that -- like self-healing systems -- revert to their earlier expected behavior after a period of convalescence. The notion of antifragility was introduced by Taleb for economics systems, but its applicability has been illustrated in biological and engineering domains as well. In this paper, we propose an architecture that imparts antifragility to intelligent autonomous systems, specifically those that are goal-driven and based on AI-planning. We argue that this architecture allows the system to self-improve by uncovering new capabilities obtained either through the hazards themselves (opportunistic) or through deliberation (strategic). An AI planning-based case study of an autonomous wheeled robot is presented. We show that with the proposed architecture, the robot develops antifragile behaviour with respect to an oil spill hazard.

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。

↑