Action sequence reproduction based on automatic segmentation and Object-Action Complexes
Action sequence reproduction based on automatic segmentation and Object-Action Complexes
复制标题
基于自动分割和对象动作复合体的动作序列再现
DOI：
10.1109/humanoids.2013.7029975
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
R. Dillmann
中科院分区：
文献类型：
--
作者：
M. Wachter;Sebastian Schulz;T. Asfour;E. Aksoy;F. Worgotter;R. Dillmann
教授机器人对象操作技能是一项复杂的任务，涉及多模态感知和有关处理传感器数据的知识。在本文中，我们展示了一个概念，在家庭环境中的人形机器人与各种相关的对象和行动。示范编程（PbD）的范例之后，我们提供了一个灵活的方法，使机器人能够自适应地再现由人类演示的动作序列。通过检测对象与动作者之间的关系，将所获得的包含对象的人体运动数据分割成语义决定性的子动作。匹配的动作是从对象-动作复合体（OAC）库中选择的，使用每个子动作的前提条件和效果。所得到的OAC序列的参数化的执行上的人形机器人取决于所观察到的动作序列和在执行过程中的环境的状态。这种方法的可行性在示例性厨房场景中示出，其中机器人必须准备面团。
Teaching robots object manipulation skills is a complex task that involves multimodal perception and knowledge about processing the sensor data. In this paper, we show a concept for humanoid robots in household environments with a variety of related objects and actions. Following the paradigms of Programming by Demonstration (PbD), we provide a flexible approach that enables a robot to adaptively reproduce an action sequence demonstrated by a human. The obtained human motion data with involved objects is segmented into semantic conclusive sub-actions by the detection of relations between the objects and the human actor. Matching actions are chosen from a library of Object-Action Complexes (OACs) using the preconditions and effects of each sub-action. The resulting sequence of OACs is parameterized for the execution on a humanoid robot depending on the observed action sequence and on the state of the environment during execution. The feasibility of this approach is shown in an exemplary kitchen scenario, where the robot has to prepare a dough.