Learning to Singulate Objects using a Push Proposal Network

TL;DR

This paper introduces a neural network that enables robots to effectively separate unknown objects in cluttered environments by selecting optimal push actions, demonstrated through real-world experiments with high success rates.

Contribution

A novel push proposal network trained on autonomous robot interactions that generalizes to various objects and configurations for object singulation in clutter.

Findings

High success rate in singulating up to 8 objects

Effective generalization to novel objects and arrangements

Low number of push actions needed for successful separation

Abstract

Learning to act in unstructured environments, such as cluttered piles of objects, poses a substantial challenge for manipulation robots. 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 autonomous interaction of a PR2 robot with randomly organized tabletop scenes. The model is designed to propose meaningful push actions based on over-segmented RGB-D images. We evaluate our approach by singulating up to 8 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. Videos of our experiments can be viewed at http://robotpush.cs.uni-freiburg.de