Pick and Place Without Geometric Object Models
Pick and Place Without Geometric Object Models
复制标题
无需几何对象模型即可拾取和放置
DOI:
10.1109/icra.2018.8460553
复制
发表时间:
2018
期刊:
影响因子:
--
通讯作者:
Platt, Robert
中科院分区:
文献类型:
--
作者:
Gualtieri, Marcus;Pas, Andreas ten;Platt, Robert
We propose a novel formulation of robotic pick and place as a deep reinforcement learning (RL) problem. Whereas most deep RL approaches to robotic manipulation frame the problem in terms of low level states and actions, we propose a more abstract formulation. In this formulation, actions are target reach poses for the hand and states are a history of such reaches. We show this approach can solve a challenging class of pick-place and regrasping problems where the exact geometry of the objects to be handled is unknown. The only information our method requires is: 1) the sensor perception available to the robot at test time; 2) prior knowledge of the general class of objects for which the system was trained. We evaluate our method using objects belonging to two different categories, mugs and bottles, both in simulation and on real hardware. Results show a major improvement relative to a shape primitives baseline.
登录
查看更多内容
DOI:
10.1109/icra.2012.6225116
发表时间:
2012-05
期刊:
2012 IEEE International Conference on Robotics and Automation
影响因子:
--
作者:
W. Wohlkinger;A. Aldoma;R. Rusu;M. Vincze
通讯作者:
W. Wohlkinger;A. Aldoma;R. Rusu;M. Vincze
DOI:
10.1109/iros.2015.7353536
发表时间:
2015-12
期刊:
2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
影响因子:
--
作者:
Karl Pauwels;D. Kragic
通讯作者:
Karl Pauwels;D. Kragic
DOI:
10.1109/icra.2012.6224581
发表时间:
2011
期刊:
2012 IEEE International Conference on Robotics and Automation
影响因子:
--
作者:
Yun Jiang;Changxi Zheng;Marcus Lim;Ashutosh Saxena
通讯作者:
Ashutosh Saxena
DOI:
--
发表时间:
1985
期刊:
Proceedings. 1985 IEEE International Conference on Robotics and Automation
影响因子:
--
作者:
M. T. Mason
通讯作者:
M. T. Mason