期刊名称：International Journal of Advanced Robotic Systems
印刷版ISSN：1729-8806
电子版ISSN：1729-8814
出版年度：2008
卷号：5
期号：3
DOI：10.5772/5611
语种：English
出版社：SAGE Publications
摘要：In this paper, we deal with the problem of learning by demonstration, task level learning and planning for robotic applications that involve object manipulation. Preprogramming robots for execution of complex domestic tasks such as setting a dinner table is of little use, since the same order of subtasks may not be conceivable in the run time due to the changed state of the world. In our approach, we aim to learn the goal of the task and use a task planner to reach the goal given different initial states of the world. For some tasks, there are underlying constraints that must be fulfille, and knowing just the final goal is not sufficient. We propose two techniques for constraint identification. In the first case, the teacher can directly instruct the system about the underlying constraints. In the second case, the constraints are identified by the robot itself based on multiple observations. The constraints are then considered in the planning phase, allowing the task to be executed without violating any of them. We evaluate our work on a real robot performing pick-and-place tasks.
关键词：Programming by demosntration; task learning; task planning; object manipulation
Loading...
