论文标题
使用视觉反馈学习用于机器人控制的生成模型
Learning a generative model for robot control using visual feedback
论文作者
论文摘要
我们引入了一种新颖的配方，以将视觉反馈纳入控制机器人。我们将生成模型定义为从动作到最终效应器上特征的图像观测值。模型中的推断使我们能够推断与功能目标位置相对应的机器人状态。反过来，这可以指导机器人的运动，并允许将功能的目标位置与最新的视觉伺服方法相匹配。我们模型的训练程序可以同时有效学习运动学，功能结构和摄像机参数。这可以在没有关于机器人，结构和摄像机观察的事先信息中完成。学习是有效的，并显示出对测试数据的强烈概括。由于我们的配方是模块化的，因此我们可以修改设置的组件，例如摄像机和对象，并快速在线重新学习。我们的方法可以处理与我们相互作用的控制器中观察到的状态和噪声中的噪声。我们通过使用不准确的控制器在机器人上执行抓握和紧密插入来证明我们的方法的有效性。
We introduce a novel formulation for incorporating visual feedback in controlling robots. We define a generative model from actions to image observations of features on the end-effector. Inference in the model allows us to infer the robot state corresponding to target locations of the features. This, in turn, guides motion of the robot and allows for matching the target locations of the features in significantly fewer steps than state-of-the-art visual servoing methods. The training procedure for our model enables effective learning of the kinematics, feature structure, and camera parameters, simultaneously. This can be done with no prior information about the robot, structure, and cameras that observe it. Learning is done sample-efficiently and shows strong generalization to test data. Since our formulation is modular, we can modify components of our setup, like cameras and objects, and relearn them quickly online. Our method can handle noise in the observed state and noise in the controllers that we interact with. We demonstrate the effectiveness of our method by executing grasping and tight-fit insertions on robots with inaccurate controllers.
