Teaching robots social autonomy from in situ human guidance
Teaching robots social autonomy from in situ human guidance
复制标题
在人类现场指导下教导机器人进行社会自主
作者：
Emmanuel Senft;Séverin Lemaignan;Paul E. Baxter;Madeleine E. Bartlett;Tony Belpaeme
一个机器人被编程为逐步学习适当的社会自主行为，从现场的人类示范和指导。在机器人自主性和人类控制之间取得适当的平衡是社会机器人技术的核心挑战，无论是在技术上还是在道德上。一方面，机器人自主性的扩展为提高人类生产力和减轻体力和认知任务提供了潜力。另一方面，最大限度地利用人类的技术和社会专门知识以及保持问责制是非常可取的。这在医疗和教育等领域尤其重要，在这些领域，社交机器人有很大的希望，但性能不佳的自主系统成本很高，加上道德问题。我们提出了一个领域的研究，我们评估的机器人能力（监督逐步自主），一种创新的方法来解决这一挑战，使机器人逐步学习适当的自主行为，从现场的人类示范和指导。使用在线机器学习技术，我们证明了机器人可以有效地获得清晰和一致的社会政策，在高维的儿童辅导的情况下，只需要有限数量的演示，同时保留人类的监督，只要需要。通过利用人类的专业知识，我们的技术可以在复杂和不确定的环境中快速学习自主的社会和特定领域的政策。最后，我们强调的通用属性的机器人，并讨论这种模式是如何相关的一个广泛的困难的人机交互场景。
A robot was programmed to progressively learn appropriate social autonomous behavior from in situ human demonstrations and guidance. Striking the right balance between robot autonomy and human control is a core challenge in social robotics, in both technical and ethical terms. On the one hand, extended robot autonomy offers the potential for increased human productivity and for the off-loading of physical and cognitive tasks. On the other hand, making the most of human technical and social expertise, as well as maintaining accountability, is highly desirable. This is particularly relevant in domains such as medical therapy and education, where social robots hold substantial promise, but where there is a high cost to poorly performing autonomous systems, compounded by ethical concerns. We present a field study in which we evaluate SPARC (supervised progressively autonomous robot competencies), an innovative approach addressing this challenge whereby a robot progressively learns appropriate autonomous behavior from in situ human demonstrations and guidance. Using online machine learning techniques, we demonstrate that the robot could effectively acquire legible and congruent social policies in a high-dimensional child-tutoring situation needing only a limited number of demonstrations while preserving human supervision whenever desirable. By exploiting human expertise, our technique enables rapid learning of autonomous social and domain-specific policies in complex and nondeterministic environments. Last, we underline the generic properties of SPARC and discuss how this paradigm is relevant to a broad range of difficult human-robot interaction scenarios.