Learning of Planning Models for Dexterous Manipulation Based on Human Demonstrations
Learning of Planning Models for Dexterous Manipulation Based on Human Demonstrations
复制标题
基于人体演示的灵巧操作规划模型的学习
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
R. Dillmann
中科院分区：
文献类型：
--
作者：
Rainer Jäkel;Sven R. Schmidt;S. Rühl;Alexander Kasper;Zhixing Xue;R. Dillmann
在人类环境中，服务机器人必须能够自主地操纵工作空间中的各种对象，这些对象受到与障碍物的碰撞、自碰撞和任务限制的限制。规划使机器人系统能够将预定义或学习的操作知识推广到新的环境中。对于灵活的操作任务，手动定义规划模型既耗时又容易出错。在这项工作中，灵活任务的规划模型基于多个人类演示，使用包括自动生成的接触约束的一般特征空间来学习，这些特征空间被自动放松以考虑对应问题。为了对不同的对象执行学习的规划模型，使用变形将接触位置转换为给定的对象几何。使用前面描述的并行优化算法来推广初始的过度专门化计划模型，其目标是找到任务约束的最大子集，其允许对一组测试问题的解。在两个不同的灵巧任务上的实验表明，该学习方法对灵巧操作任务是适用的。
In the human environment service robots have to be able to manipulate autonomously a large variety of objects in a workspace restricted by collisions with obstacles, self-collisions and task constraints. Planning enables the robot system to generalize predefined or learned manipulation knowledge to new environments. For dexterous manipulation tasks the manual definition of planning models is time-consuming and error-prone. In this work, planning models for dexterous tasks are learned based on multiple human demonstrations using a general feature space including automatically generated contact constraints, which are automatically relaxed to consider the correspondence problem. In order to execute the learned planning model with different objects, the contact location is transformed to given object geometry using morphing. The initial, overspecialized planning model is generalized using a previously described, parallelized optimization algorithm with the goal to find a maximal subset of task constraints, which admits a solution to a set of test problems. Experiments on two different, dexterous tasks show the applicability of the learning approach to dexterous manipulation tasks.
DOI：
10.1109/ichr.2010.5686830
发表时间：
2010-12
期刊：
2010 10th IEEE-RAS International Conference on Humanoid Robots
影响因子：
--
作者：
Jan Steffen;Christof Elbrechter;R. Haschke;H. Ritter
通讯作者：
Jan Steffen;Christof Elbrechter;R. Haschke;H. Ritter