Programming by Demonstration of Pick-and-Place Tasks for Industrial Manipulators using Task Primitives
Programming by Demonstration of Pick-and-Place Tasks for Industrial Manipulators using Task Primitives
复制标题
DOI：
10.1109/cira.2007.382863
复制
发表时间：
2007-06
期刊：
影响因子：
--
通讯作者：
Alexander Skoglund;B. Iliev;B. Kadmiry;R. Palm
中科院分区：
文献类型：
--
作者：
Alexander Skoglund;B. Iliev;B. Kadmiry;R. Palm
为了简化工业机械臂的编程，提出了一种基于演示的编程方法。通过使用一组已知任务类型的任务原语，可以解释演示并自动生成操纵器程序。基于速度分布分析了拾取任务，并将其分解为任务原语。任务原语是机器人/抓取器的基本动作，可以按顺序执行，形成一个完整的任务。对于演示轨迹的建模和生成，采用模糊时间聚类，使运动平滑准确。为了说明我们的方法，我们在一个真实的工业机械手上进行了实验。
This article presents an approach to Programming by Demonstration (PbD) to simplify programming of industrial manipulators. By using a set of task primitives for a known task type, the demonstration is interpreted and a manipulator program is automatically generated. A pick-and-place task is analyzed, based on the velocity profile, and decomposed in task primitives. Task primitives are basic actions of the robot/gripper, which can be executed in a sequence to form a complete a task. For modeling and generation of the demonstrated trajectory, fuzzy time clustering is used, resulting in smooth and accurate motions. To illustrate our approach, we carried out our experiments on a real industrial manipulator.