外部単眼RGBカメラからの間接的な物体-ロボット姿勢推定
Indirect Object-to-Robot Pose Estimation from an External Monocular RGB Camera
単一の外部RGBカメラから物体とロボットの相対姿勢を2つのニューラルネットで間接的に推定し、把持を行うシステムを提案。合成データとドメインランダム化で学習し、カメラを自由に動かせる。
著者: Jonathan Tremblay, Stephen Tyree, Terry Mosier, Stan Birchfield
分類: cs.RO
原文アブストラクト
We present a robotic grasping system that uses a single external monocular RGB camera as input. The object-to-robot pose is computed indirectly by combining the output of two neural networks: one that estimates the object-to-camera pose, and another that estimates the robot-to-camera pose. Both networks are trained entirely on synthetic data, relying on domain randomization to bridge the sim-to-real gap. Because the latter network performs online camera calibration, the camera can be moved freely during execution without affecting the quality of the grasp. Experimental results analyze the effect of camera placement, image resolution, and pose refinement in the context of grasping several household objects. We also present results on a new set of 28 textured household toy grocery objects, which have been selected to be accessible to other researchers. To aid reproducibility of the research, we offer 3D scanned textured models, along with pre-trained weights for pose estimation.
