Interactive Policy Shaping for Human-Robot Collaboration with Transparent Matrix Overlays
Interactive Policy Shaping for Human-Robot Collaboration with Transparent Matrix Overlays
复制标题
DOI：
10.1145/3568162.3576983
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Jake Brawer;Debasmita Ghose;Kate Candon;Meiying Qin;A. Roncone;Marynel Vázquez;B. Scassellati
中科院分区：
文献类型：
--
作者：
Jake Brawer;Debasmita Ghose;Kate Candon;Meiying Qin;A. Roncone;Marynel Vázquez;B. Scassellati
有效的人机协作的一个重要方面是机器人快速适应人类需求的能力。虽然像深度强化学习这样的技术已经证明了作为学习机器人策略的复杂工具的成功，但人机协作的流畅性往往受到这些策略无法整合用户对任务偏好变化的限制。为了解决这些缺点，我们提出了一种新的方法，可以在执行时通过象征性的if-this-then-that规则来修改学习到的策略，这些规则对应于机器人策略上的一组模块化和可叠加的低级约束。这些规则，我们称之为透明矩阵叠加，不仅作为机器人当前策略的简洁和可解释的描述，而且作为一个接口，人类合作者可以通过口头命令轻松改变机器人的策略。我们在模拟和物理机器人上执行的一系列概念验证烹饪任务中证明了这种方法的有效性。
One important aspect of effective human--robot collaborations is the ability for robots to adapt quickly to the needs of humans. While techniques like deep reinforcement learning have demonstrated success as sophisticated tools for learning robot policies, the fluency of human-robot collaborations is often limited by these policies' inability to integrate changes to a user's preferences for the task. To address these shortcomings, we propose a novel approach that can modify learned policies at execution time via symbolic if-this-then-that rules corresponding to a modular and superimposable set of low-level constraints on the robot's policy. These rules, which we call Transparent Matrix Overlays, function not only as succinct and explainable descriptions of the robot's current strategy but also as an interface by which a human collaborator can easily alter a robot's policy via verbal commands. We demonstrate the efficacy of this approach on a series of proof-of-concept cooking tasks performed in simulation and on a physical robot.