Learning to place new objects
Learning to place new objects
复制标题
学习放置新物体
DOI：
10.1109/icra.2012.6224581
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Ashutosh Saxena
中科院分区：
文献类型：
--
作者：
Yun Jiang;Changxi Zheng;Marcus Lim;Ashutosh Saxena
在环境中放置物体的能力是个人机器人的一项重要技能。物体不仅应稳定放置，还应放置在其首选位置/方向。例如，与水平放置在盘架的槽中相比，优选将盘垂直插入盘架的槽中。非结构化环境（诸如家庭）具有各种各样的物体类型以及放置区域。因此，我们的算法应该能够处理放置新的对象类型和新的放置区域。这些原因使得放置成为一项具有挑战性的操纵任务。在这项工作中，我们建议使用监督学习方法来找到良好的位置给定的点云的对象和放置区域。我们的方法结合了捕获支持，稳定性和首选配置的功能，并在其参数中使用共享的稀疏结构。即使对象和放置区域之前都没有在训练集中看到，我们的学习算法也能预测出良好的放置位置。在机器人实验中，我们的方法使机器人能够稳定地放置已知的物体，成功率为98%，并且在考虑语义偏好方向时，成功率为98%。在将新物体放置到新放置区域的情况下，成功率为82%和72%。
The ability to place objects in an environment is an important skill for a personal robot. An object should not only be placed stably, but should also be placed in its preferred location/orientation. For instance, it is preferred that a plate be inserted vertically into the slot of a dish-rack as compared to being placed horizontally in it. Unstructured environments such as homes have a large variety of object types as well as of placing areas. Therefore our algorithms should be able to handle placing new object types and new placing areas. These reasons make placing a challenging manipulation task. In this work, we propose using a supervised learning approach for finding good placements given point-clouds of the object and the placing area. Our method combines the features that capture support, stability and preferred configurations, and uses a shared sparsity structure in its the parameters. Even when neither the object nor the placing area is seen previously in the training set, our learning algorithm predicts good placements. In robotic experiments, our method enables the robot to stably place known objects with a 98% success rate and 98% when also considering semantically preferred orientations. In the case of placing a new object into a new placing area, the success rate is 82% and 72%.