Two-Stage Robotic Bin Picking of Small Metallic Objects

Author:

Herbert MeikeORCID,Bach Paul,Lieret MarkusORCID,Fürst Jens,Franke JörgORCID

Abstract

AbstractRobotic grasping of small metallic objects such as bolts is a challenging task due to the small dimensions and textureless reflective surfaces. Depth images acquired of such objects are often noisy and error-prone. In addition, overlapping of parts occur as they are provided randomly oriented in a box such as a small load carrier. To overcome the limitations of existing solutions for bolt separation, a flexible and cost-effective system is developed using an industrial robot and a magnetic gripper. In a two-stage procedure, the bolts are first grasped blindly from a box and placed on a flat surface. In the second step, object detection and pose estimation is performed and the individual bolts are grasped and inserted into a fixture, so that finally the bolts are in a defined position. Industrial use cases for this system are the automated preparation of bolts for robotic screwing processes or automated commissioning of small objects for assembly tasks. The methodology, implementation and evaluation of the proposed solution is presented in this paper.

Publisher

Springer International Publishing

Reference13 articles.

1. Du, G., Wang, K., Lian, S., Zhao, K.: Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review. Artif. Intell. Rev. 54(3), 1677–1734 (2021)

2. Bochkovskiy, A., Wang, C., Liao, H.M.: YOLOv4: optimal speed and accuracy of object detection. ArXiv abs/2004.10934, pp. 1–17 (2020)

3. Wang, R.J., Li, X., Ling, C.X.: Pelee: a real-time object detection system on mobile devices. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS’18), pp. 1967–1976. Curran Associates Inc., Red Hook (2018)

4. Liu, H., Rivera Soto, R.A., Xiao, F., Jae Lee, Y.: YolactEdge: real-time instance segmentation on the edge. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 9579–9585. IEEE, Xi’an (2021)

5. Sun, Y., Zuo, W., Liu, M.: RTFNet: RGB-thermal fusion network for semantic segmentation of urban scenes. IEEE Robot. Autom. Lett 4(3), 2576–2583 (2019)

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