Learning to Singulate Objects using a Push Proposal Network

By Andreas Eitel, Nico Hauff, Wolfram Burgard. 2017

86 citations recorded by the source corpus.

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 this http URL

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Yuke Zhu
2. Kuan Fang
3. Silvio Savarese
4. Animesh Garg
5. Li Fei-Fei

In Computer Vision and Pattern Recognition

1. Li Fei-Fei
2. Silvio Savarese
3. Yuke Zhu
4. Kristen Grauman
5. Luc Van Gool
6. Trevor Darrell
7. Jitendra Malik
8. Xiaogang Wang

In Control and Systems Engineering

1. Yuke Zhu
2. Silvio Savarese
3. Li Fei-Fei
4. Animesh Garg
5. Kuan Fang
6. Ajay Mandlekar
7. Roberto Mart'in-Mart'in
8. Abhinav Kumar Gupta

Citations in the corpus

• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, neutral): “A recent work from Eitel et al. (2017) introduces a model that is able to propose push actions based on over-segmented RGB-D images, in order to separate unknown objects in cluttered environments.”
• Learning task-oriented grasping for tool manipulation from simulated self-supervision (2018, methodology): “Sweeping with tools has been studied in the context of singulation and part retrieval (Eitel et al., 2017; Laskey et al., 2017).”