Grasping the Inconspicuous
This addresses a specific challenge in robotics for applications involving transparent objects, but it is incremental as it builds on existing pose estimation methods.
The paper tackled the problem of robot grasping for transparent objects by proposing a deep learning 6D pose estimation method using only RGB images, and it demonstrated effectiveness through experiments on a newly constructed dataset.
Transparent objects are common in day-to-day life and hence find many applications that require robot grasping. Many solutions toward object grasping exist for non-transparent objects. However, due to the unique visual properties of transparent objects, standard 3D sensors produce noisy or distorted measurements. Modern approaches tackle this problem by either refining the noisy depth measurements or using some intermediate representation of the depth. Towards this, we study deep learning 6D pose estimation from RGB images only for transparent object grasping. To train and test the suitability of RGB-based object pose estimation, we construct a dataset of RGB-only images with 6D pose annotations. The experiments demonstrate the effectiveness of RGB image space for grasping transparent objects.