Lighting- and Occlusion-Robust View-Based Teaching/Playback for Model-Free Robot Programming
Lighting- and Occlusion-Robust View-Based Teaching/Playback for Model-Free Robot Programming
复制标题
DOI：
10.1007/978-3-319-48036-7_68
复制
发表时间：
2016-07
期刊：
影响因子：
--
通讯作者：
Y. Maeda;Yoshito Saito
中科院分区：
文献类型：
--
作者：
Y. Maeda;Yoshito Saito
在本文中，我们研究了一种无模型的机器人编程方法，称为基于视图的教学/回放。它使用神经网络将输入图像的因子得分映射到机器人运动上。与传统的教学/回放相比，该方法可以对任务条件的变化（包括对象的初始姿态）实现更大的鲁棒性。我们设计了一种在线算法，用于在基于视图的教学/回放中使用的范围图像和灰度图像之间自适应切换。在使用工业机械手推动任务的应用中，即使在变化的照明条件下，使用所提出的算法进行基于视图的教学/回放也能成功。我们还设计了一种使用子图像来应对遮挡的算法，该算法在实验中取得了成功。
In this paper, we investigate a model-free method for robot programming referred to as view-based teaching/playback. It uses neural networks to map factor scores of input images onto robot motions. The method can achieve greater robustness to changes in the task conditions, including the initial pose of the object, as compared to conventional teaching/playback. We devised an online algorithm for adaptively switching between range and grayscale images used in view-based teaching/playback. In its application to pushing tasks using an industrial manipulator, view-based teaching/playback using the proposed algorithm succeeded even under changing lighting conditions. We also devised an algorithm to cope with occlusions using subimages, which worked successfully in experiments.