{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/push-net-deep-planar-pushing-for-objects-with","title":"Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties","arxiv_id":null,"date":"2018-06-28","proceeding":"Robotics: Science and Systems 2018 6","authors":["Jue Kun Li","David Hsu","Wee Sun Lee"],"abstract":"This paper introduces Push-Net, a deep recurrent\r\nneural network model, which enables a robot to push objects of unknown physical properties for re-positioning and\r\nre-orientation, using only visual camera images as input. The\r\nunknown physical properties is a major challenge for pushing.\r\nPush-Net overcomes the challenge by tracking a history of push\r\ninteractions with an LSTM module and training an auxiliary\r\nobjective function that estimates an object’s center of mass. We\r\ntrained Push-Net entirely in simulation and tested it extensively\r\non many different objects in both simulation and on two real\r\nrobots, a Fetch arm and a Kinova MICO arm. Experiments\r\nsuggest that Push-Net is robust and efficient. It achieved over\r\n97% success rate in simulation on average and succeeded in all\r\nreal robot experiments with a small number of pushes.","url_abs":"http://www.roboticsproceedings.org/rss14/p24.pdf","url_pdf":"http://www.roboticsproceedings.org/rss14/p24.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"push-net-deep-planar-pushing-for-objects-with","repo_url":"https://github.com/ljklonepiece/PushNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}