Learning to Singulate Objects using a Push Proposal Network
share
A key challenge for manipulation in unstructured environments is action selection. We present a novel neural network-based approach that separates unknown objects in clutter by selecting favourable push actions. Our network is trained from data collected through large-scale interaction of a PR2 robot with randomly organized tabletop scenes. The model is designed to propose meaningful push actions based on segmented RGB-D images. We evaluate our approach by singulating up to six unknown objects in clutter. We demonstrate that our method enables the robot to perform the task with a high success rate and a low number of required push actions. Our results based on real-world experiments show that our network is able to generalize to novel objects of various sizes and shapes, as well as to arbitrary object configurations. Highlights of our experiments can be viewed in the following video: https://youtu.be/jWbUJOrSacI .
READ FULL TEXT
