Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions
Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions
复制标题
用于在遮挡下操纵物体的主动视觉强化学习
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Katerina Fragkiadaki
中科院分区：
文献类型：
--
作者：
Ricson Cheng;Arpit Agarwal;Katerina Fragkiadaki
我们考虑人工智能体，学习联合控制他们的抓手和摄像头，以便在干扰物体遮挡的情况下强化学习操作策略。干扰物常常遮挡感兴趣的物体，使其从视野中消失。我们提出了手/眼控制器，学习移动摄像机以使对象保持在视场内并且可见，与操纵对象以实现期望的目标相协调，例如，将其推到目标位置。我们将以对象为中心的注意的结构性偏差融入到我们的演员-批评者架构中，我们的实验表明这是良好表现的关键。我们的研究结果进一步强调了课程在环境难度方面的重要性。由此产生的主动视觉/操纵策略在各种杂乱环境中的性能优于静态摄像头设置。
We consider artificial agents that learn to jointly control their gripperand camera in order to reinforcement learn manipulation policies in the presenceof occlusions from distractor objects. Distractors often occlude the object of in-terest and cause it to disappear from the field of view. We propose hand/eye con-trollers that learn to move the camera to keep the object within the field of viewand visible, in coordination to manipulating it to achieve the desired goal, e.g.,pushing it to a target location. We incorporate structural biases of object-centricattention within our actor-critic architectures, which our experiments suggest tobe a key for good performance. Our results further highlight the importance ofcurriculum with regards to environment difficulty. The resulting active vision /manipulation policies outperform static camera setups for a variety of clutteredenvironments.
DOI：
--
发表时间：
2018-06
期刊：
--
影响因子：
--
作者：
Marcus Gualtieri;Robert W. Platt
通讯作者：
Marcus Gualtieri;Robert W. Platt
影响因子：
1.8
作者：
Tatler BW;Hayhoe MM;Land MF;Ballard DH
通讯作者：
Ballard DH