Push-to-See: Learning Non-Prehensile Manipulation to Enhance Instance Segmentation via Deep Q-Learning
Author:
Affiliation:
1. School of Computer Science, University of Nottingham,UK
2. Toshiba Research,Cambridge,UK
3. Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology,Germany
Funder
NCNR (National Centre for Nuclear Robotics, EPSRC)
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9811522/9811357/09811645.pdf?arnumber=9811645
Reference28 articles.
1. Linear Push Policies to Increase Grasp Access for Robot Bin Picking
2. Human-level control through deep reinforcement learning;mnih;Nature,2015
3. Weakly Supervised Region Proposal Network and Object Detection
4. Vision-Based Robotic Pushing and Grasping for Stone Sample Collection under Computing Resource Constraints
5. Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data
Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. A Multitask and Kernel Approach for Learning to Push Objects with a Target-Parameterized Deep Q-Network;2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS);2023-10-01
2. TRF-Net: a transformer-based RGB-D fusion network for desktop object instance segmentation;Neural Computing and Applications;2023-08-05
3. Constructing a Sorting Robot for Densely Gathered Mixed Industrial Waste Items;Journal of the Robotics Society of Japan;2023
4. RL-Studio: A Tool for Reinforcement Learning Methods in Robotics;ROBOT2022: Fifth Iberian Robotics Conference;2022-11-19
5. Review of Learning-Based Robotic Manipulation in Cluttered Environments;Sensors;2022-10-18
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3