Semantic Robot Programming for Goal-Directed Manipulation in Cluttered Scenes
Semantic Robot Programming for Goal-Directed Manipulation in Cluttered Scenes
复制标题
DOI：
10.1109/icra.2018.8460538
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
Zhen Zeng;Zheming Zhou;Zhiqiang Sui;O. C. Jenkins
中科院分区：
文献类型：
--
作者：
Zhen Zeng;Zheming Zhou;Zhiqiang Sui;O. C. Jenkins
我们通过演示和语义映射将语义机器人编程（SRP）范式呈现为机器人编程的融合。在 SRP 中，用户可以通过在工作区中演示其预期目标场景的快照来直接对机器人操纵器进行编程。然后，假设已知物体几何形状，机器人将这个目标解析为由物体姿态和物体间关系组成的场景图。然后使用任务和运动规划来从任意初始场景配置实现用户的目标。即使面对不同的初始场景配置，SRP 也能使机器人无缝适应以达到用户演示的目标。对于场景感知，我们提出了场景和变换的判别信息生成估计（DIGEST）方法来从 RGBD 图像推断世界的初始状态和目标状态。 SRP 与 DIGEST 感知的功效在密歇根 Progress Fetch 机器人的托盘设置任务中得到了证明。使用公共家庭遮挡数据集和我们的杂乱场景数据集来评估场景感知和任务执行。
We present the Semantic Robot Programming (SRP) paradigm as a convergence of robot programming by demonstration and semantic mapping. In SRP, a user can directly program a robot manipulator by demonstrating a snapshot of their intended goal scene in workspace. The robot then parses this goal as a scene graph comprised of object poses and inter-object relations, assuming known object geometries. Task and motion planning is then used to realize the user's goal from an arbitrary initial scene configuration. Even when faced with different initial scene configurations, SRP enables the robot to seamlessly adapt to reach the user's demonstrated goal. For scene perception, we propose the Discriminatively-Informed Generative Estimation of Scenes and Transforms (DIGEST) method to infer the initial and goal states of the world from RGBD images. The efficacy of SRP with DIGEST perception is demonstrated for the task of tray-setting with a Michigan Progress Fetch robot. Scene perception and task execution are evaluated with a public household occlusion dataset and our cluttered scene dataset.