arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.19795cs.RO
收藏

学习人类对机器人行为的偏好作为软规划约束

Learning Human Preferences Over Robot Behavior as Soft Planning Constraints

Meta AI;Yale University(耶鲁大学)

Austin Narcomey, Nathan Tsoi, Ruta Desai, Marynel Vázquez

AI总结:

本文提出将人类偏好编码为软规划约束的新问题表述,并通过数据驱动方法在Habitat 2.0重排任务中实现机器人对三类偏好的推断,为自适应规划行为奠定基础。

摘要:

偏好学习长期以来一直在人机交互(HRI)领域被研究,目的是使机器人行为适应特定用户的需求和期望。通常,人类偏好被建模为标量函数;然而,这种表述混淆了对于给定任务机器人应如何行为的关键考虑,以及期望但非必需的机器人行为。在这项工作中,我们通过利用规划框架来区分这种必需的和期望的机器人行为。具体来说,我们提出了一种新的HRI偏好学习问题表述,其中各种类型的人类偏好被编码为软规划约束。然后,我们探索了一种数据驱动的方法,使机器人能够通过询问用户来推断偏好,并在Habitat 2.0模拟器中的重排任务中实例化了该方法。我们表明,所提出的方法即使在模拟用户在潜在机器人行为之间进行选择时存在不同程度噪声的情况下,也有望推断出三种类型的偏好。我们的贡献为未来基于规划的自适应机器人行为开辟了道路。

英文摘要:

Preference learning has long been studied in Human-Robot Interaction (HRI) in order to adapt robot behavior to specific user needs and desires. Typically, human preferences are modeled as a scalar function; however, such a formulation confounds critical considerations on how the robot should behave for a given task, with desired -- but not required -- robot behavior. In this work, we distinguish between such required and desired robot behavior by leveraging a planning framework. Specifically, we propose a novel problem formulation for preference learning in HRI where various types of human preferences are encoded as soft planning constraints. Then, we explore a data-driven method to enable a robot to infer preferences by querying users, which we instantiate in rearrangement tasks in the Habitat 2.0 simulator. We show that the proposed approach is promising at inferring three types of preferences even under varying levels of noise in simulated user choices between potential robot behaviors. Our contributions open up doors to adaptable planning-based robot behavior in the future.

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。

↑