Neural Network-Based Pose Estimation Approaches for Mobile Manipulation

Author:

Chowdhury Arindam B.1,Li Juncheng1,Cappelleri David J.1

Affiliation:

1. Purdue University School of Mechanical Engineering, , West Lafayette, IN 47907

Abstract

Abstract This paper illustrates two approaches for the mobile manipulation of factory robots using deep neural networks. The networks are trained using synthetic datasets unique to the factory environment. Approach I uses depth and red-green-blue (RGB) images of objects for its convolutional neural network (CNN) and Approach II uses computer-aided design models of the objects with RGB images for a deep object pose estimation (DOPE) network and perspective-n-point (PnP) algorithm. Both the approaches are compared based on their complexity, required resources for training, robustness, pose estimation accuracy, and run-time characteristics. Recommendations of which approach is suitable under what circumstances are provided. Finally, the most suitable approach is implemented on a real mobile factory robot in order to execute a series of manipulation tasks and validate the approach.

Funder

Johnson Space Center

Publisher

ASME International

Subject

Mechanical Engineering

Cited by 4 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. Sparse Convolution-Based 6D Pose Estimation for Robotic Bin-Picking With Point Clouds;Journal of Mechanisms and Robotics;2024-09-03

2. Sim-Grasp: Learning 6-DOF Grasp Policies for Cluttered Environments Using a Synthetic Benchmark;IEEE Robotics and Automation Letters;2024-09

3. GAMMA: Graspability-Aware Mobile MAnipulation Policy Learning based on Online Grasping Pose Fusion;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13

4. Research on Model-Free 6D Object Pose Estimation Based on Vision 3D Matching;Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition;2024-04-26

同舟云学术

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