To show or hide the keywords and abstract text summary of a paper if available , click on the paper title Open all abstracts Close all abstracts.
Approaches often aim to obtain high-quality scene observations while reducing the number of views, travel distance and computational cost. Considering occlusions and scene coverage can significantly reduce the number of views and travel distance required to obtain an observation. Structured representations e. Unstructured representations e.
This paper presents proactive solutions for handling occlusions and considering scene coverage with an unstructured representation. Experiments show that these techniques allow an unstructured representation to observe scenes with fewer views and shorter distances while retaining high observation quality and low computational cost. 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.
