JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/17023

Title: A 2-Stage Framework for Learning to Push Unknown Objects
Authors: Gao, Ziyan
Elibol, Armagan
Chong, Nak Young
Keywords: Robot Planar Pushing
Probabilistic Model
Data-Driven Approach
Issue Date: 2020-10
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: 2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)
DOI: 10.1109/ICDL-EpiRob48136.2020.9278075
Abstract: Robotic manipulation has been generally applied to particular settings and a limited number of known objects. In order to manipulate novel objects, robots need to be capable of discovering the physical properties of objects, such as the center of mass, and reorienting objects to the desired pose required for subsequent actions. In this work, we proposed a computationally efficient 2-stage framework for planar pushing, allowing a robot to push novel objects to a specified pose with a small amount of pushing steps. We developed three modules: Coarse Action Predictor (CAP), Forward Dynamic Estimator (FDE), and Physical Property Estimator (PPE). The CAP module predicts a mixture of Gaussian distribution of actions. FDE learns the causality between action and successive object state. PPE based on Recurrent Neural Network predicts the physical center of mass (PCOM) from the robot-object interaction. Our preliminary experiments show promising results to meet the practical application requirements of manipulating novel objects.
Rights: This is the author's version of the work. Copyright (C) 2020 IEEE. 2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 2020, DOI:10.1109/ICDL-EpiRob48136.2020.9278075. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
URI: http://hdl.handle.net/10119/17023
Material Type: author
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
3396.pdf1301KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, Japan Advanced Institute of Science and Technology