面向协同AI的风险建模
Towards Risk Modeling for Collaborative AI
摘要：
协作人工智能系统旨在与人类在共享空间中合作，以实现共同目标。由于接触可能会伤害人类，因此这种设置会造成潜在的危险情况。因此，构建此类系统并强有力地保证符合特定于需求领域的标准和法规是最重要的。当这些系统依赖于机器学习组件而不是自上而下的基于规则的AI时，与实现这一目标相关的挑战变得更加严峻。在本文中，我们介绍了一种为协作AI系统量身定制的风险建模方法。风险模型包括目标、风险事件和可能使人类暴露于危险的领域特定指标。然后，利用风险模型来驱动保证方法，这些保证方法通过从运行时证据中提取的洞察力反过来为风险模型提供信息。我们设想的方法是通过在工业4.0领域的一个正在运行的例子来描述的，在这个例子中，一个机器人手臂被赋予了一个视觉感知组件，用机器学习来实现，与人类操作员合作执行与生产相关的任务。
英文摘要：
Collaborative AI systems aim at working together with humans in a shared space to achieve a common goal. This setting imposes potentially hazardous circumstances due to contacts 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. Challenges associated with the achievement of this goal become even more severe when such systems rely on machine learning components rather than such as top-down rule-based AI. In this paper, we introduce a risk modeling approach tailored to Collaborative AI systems. The risk model includes goals, risk events and domain specific indicators that potentially expose humans to hazards. The risk model is then leveraged to drive assurance methods that feed in turn the risk model through insights extracted from run-time evidence. Our envisioned approach is described by means of a running example in the domain of Industry 4.0, where a robotic arm endowed with a visual perception component, implemented with machine learning, collaborates with a human operator for a production-relevant task.
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。
