Robot manipulator self-identification for surrounding obstacle detection

Xinyu Wang; Chenguang Yang; Zhaojie Ju; Hongbin Ma; Mengyin Fu

doi:10.1007/s11042-016-3275-8

Robot manipulator self-identification for surrounding obstacle detection

Xinyu Wang
, Chenguang Yang^*
, Zhaojie Ju
, Hongbin Ma
, Mengyin Fu

^*Corresponding author for this work

School of Automation

Research output: Contribution to journal › Article › peer-review

46 Citations (Scopus)

Abstract

Obstacle detection plays an important role for robot collision avoidance and motion planning. This paper focuses on the study of the collision prediction of a dual-arm robot based on a 3D point cloud. Firstly, a self-identification method is presented based on the over-segmentation approach and the forward kinematic model of the robot. Secondly, a simplified 3D model of the robot is generated using the segmented point cloud. Finally, a collision prediction algorithm is proposed to estimate the collision parameters in real-time. Experimental studies using the Kinect_Ⓡ sensor and the Baxter_Ⓡ robot have been performed to demonstrate the performance of the proposed algorithms.

Original language	English
Pages (from-to)	6495-6520
Number of pages	26
Journal	Multimedia Tools and Applications
Volume	76
Issue number	5
DOIs	https://doi.org/10.1007/s11042-016-3275-8
Publication status	Published - 1 Mar 2017

Keywords

Collision prediction
Manipulator self-identification
Point cloud
Superpixel

Access to Document

10.1007/s11042-016-3275-8

Cite this

@article{ff0c241b6df54b10a8d4c85083a46288,

title = "Robot manipulator self-identification for surrounding obstacle detection",

abstract = "Obstacle detection plays an important role for robot collision avoidance and motion planning. This paper focuses on the study of the collision prediction of a dual-arm robot based on a 3D point cloud. Firstly, a self-identification method is presented based on the over-segmentation approach and the forward kinematic model of the robot. Secondly, a simplified 3D model of the robot is generated using the segmented point cloud. Finally, a collision prediction algorithm is proposed to estimate the collision parameters in real-time. Experimental studies using the KinectⓇ sensor and the BaxterⓇ robot have been performed to demonstrate the performance of the proposed algorithms.",

keywords = "Collision prediction, Manipulator self-identification, Point cloud, Superpixel",

author = "Xinyu Wang and Chenguang Yang and Zhaojie Ju and Hongbin Ma and Mengyin Fu",

note = "Publisher Copyright: {\textcopyright} 2016, The Author(s).",

year = "2017",

month = mar,

day = "1",

doi = "10.1007/s11042-016-3275-8",

language = "English",

volume = "76",

pages = "6495--6520",

journal = "Multimedia Tools and Applications",

issn = "1380-7501",

publisher = "Springer",

number = "5",

}

TY - JOUR

T1 - Robot manipulator self-identification for surrounding obstacle detection

AU - Wang, Xinyu

AU - Yang, Chenguang

AU - Ju, Zhaojie

AU - Ma, Hongbin

AU - Fu, Mengyin

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Obstacle detection plays an important role for robot collision avoidance and motion planning. This paper focuses on the study of the collision prediction of a dual-arm robot based on a 3D point cloud. Firstly, a self-identification method is presented based on the over-segmentation approach and the forward kinematic model of the robot. Secondly, a simplified 3D model of the robot is generated using the segmented point cloud. Finally, a collision prediction algorithm is proposed to estimate the collision parameters in real-time. Experimental studies using the KinectⓇ sensor and the BaxterⓇ robot have been performed to demonstrate the performance of the proposed algorithms.

AB - Obstacle detection plays an important role for robot collision avoidance and motion planning. This paper focuses on the study of the collision prediction of a dual-arm robot based on a 3D point cloud. Firstly, a self-identification method is presented based on the over-segmentation approach and the forward kinematic model of the robot. Secondly, a simplified 3D model of the robot is generated using the segmented point cloud. Finally, a collision prediction algorithm is proposed to estimate the collision parameters in real-time. Experimental studies using the KinectⓇ sensor and the BaxterⓇ robot have been performed to demonstrate the performance of the proposed algorithms.

KW - Collision prediction

KW - Manipulator self-identification

KW - Point cloud

KW - Superpixel

UR - https://www.scopus.com/pages/publications/84957935211

U2 - 10.1007/s11042-016-3275-8

DO - 10.1007/s11042-016-3275-8

M3 - Article

AN - SCOPUS:84957935211

SN - 1380-7501

VL - 76

SP - 6495

EP - 6520

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

IS - 5

ER -

Robot manipulator self-identification for surrounding obstacle detection

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this