A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence

Guoqiang Zhao; Xiangzhou Wang; Shuhua Zheng; Qian Han

doi:10.1109/CCDC55256.2022.10033427

A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence

Guoqiang Zhao^*, Xiangzhou Wang, Shuhua Zheng, Qian Han

^*Corresponding author for this work

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

This paper presents, Anytime Fast-BIT∗ (AFBIT∗), a sampling based, asymptotically optimal manipulation motion planner which quickly finds an initial feasible path and rapidly improves the path quality toward optimality. AFBIT∗ is guided by modified heuristics in task space for faster first solution. A local optimization method is adopted at the end of every round to optimize the current best path and generate the next vertex and edge for the global path while a new round begins to improve the quality of the remaining path. Simulation results suggest AFBIT∗ is more efficient and effective on manipulation problems than BIT∗ and Fast-BIT∗.

Original language	English
Title of host publication	Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	357-363
Number of pages	7
ISBN (Electronic)	9781665478960
DOIs	https://doi.org/10.1109/CCDC55256.2022.10033427
Publication status	Published - 2022
Event	34th Chinese Control and Decision Conference, CCDC 2022 - Hefei, China Duration: 15 Aug 2022 → 17 Aug 2022

Publication series

Name	Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022

Conference

Conference	34th Chinese Control and Decision Conference, CCDC 2022
Country/Territory	China
City	Hefei
Period	15/08/22 → 17/08/22

Keywords

Industrial robots
Manipulation motion planning
Sampling-Based Algorithm

Access to Document

10.1109/CCDC55256.2022.10033427

Cite this

Zhao, G., Wang, X., Zheng, S., & Han, Q. (2022). A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence. In Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022 (pp. 357-363). (Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCDC55256.2022.10033427

Zhao, Guoqiang ; Wang, Xiangzhou ; Zheng, Shuhua et al. / A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence. Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 357-363 (Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022).

@inproceedings{d7eb1afb670b48b9b70c75b5de2ccc36,

title = "A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence",

abstract = "This paper presents, Anytime Fast-BIT∗ (AFBIT∗), a sampling based, asymptotically optimal manipulation motion planner which quickly finds an initial feasible path and rapidly improves the path quality toward optimality. AFBIT∗ is guided by modified heuristics in task space for faster first solution. A local optimization method is adopted at the end of every round to optimize the current best path and generate the next vertex and edge for the global path while a new round begins to improve the quality of the remaining path. Simulation results suggest AFBIT∗ is more efficient and effective on manipulation problems than BIT∗ and Fast-BIT∗.",

keywords = "Industrial robots, Manipulation motion planning, Sampling-Based Algorithm",

author = "Guoqiang Zhao and Xiangzhou Wang and Shuhua Zheng and Qian Han",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 34th Chinese Control and Decision Conference, CCDC 2022 ; Conference date: 15-08-2022 Through 17-08-2022",

year = "2022",

doi = "10.1109/CCDC55256.2022.10033427",

language = "English",

series = "Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "357--363",

booktitle = "Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022",

address = "United States",

}

Zhao, G , Wang, X , Zheng, S & Han, Q 2022, A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence. in Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022. Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022, Institute of Electrical and Electronics Engineers Inc., pp. 357-363, 34th Chinese Control and Decision Conference, CCDC 2022, Hefei, China, 15/08/22. https://doi.org/10.1109/CCDC55256.2022.10033427

A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence. / Zhao, Guoqiang ; Wang, Xiangzhou ; Zheng, Shuhua et al.
Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 357-363 (Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence

AU - Zhao, Guoqiang

AU - Wang, Xiangzhou

AU - Zheng, Shuhua

AU - Han, Qian

PY - 2022

Y1 - 2022

N2 - This paper presents, Anytime Fast-BIT∗ (AFBIT∗), a sampling based, asymptotically optimal manipulation motion planner which quickly finds an initial feasible path and rapidly improves the path quality toward optimality. AFBIT∗ is guided by modified heuristics in task space for faster first solution. A local optimization method is adopted at the end of every round to optimize the current best path and generate the next vertex and edge for the global path while a new round begins to improve the quality of the remaining path. Simulation results suggest AFBIT∗ is more efficient and effective on manipulation problems than BIT∗ and Fast-BIT∗.

AB - This paper presents, Anytime Fast-BIT∗ (AFBIT∗), a sampling based, asymptotically optimal manipulation motion planner which quickly finds an initial feasible path and rapidly improves the path quality toward optimality. AFBIT∗ is guided by modified heuristics in task space for faster first solution. A local optimization method is adopted at the end of every round to optimize the current best path and generate the next vertex and edge for the global path while a new round begins to improve the quality of the remaining path. Simulation results suggest AFBIT∗ is more efficient and effective on manipulation problems than BIT∗ and Fast-BIT∗.

KW - Industrial robots

KW - Manipulation motion planning

KW - Sampling-Based Algorithm

UR - http://www.scopus.com/inward/record.url?scp=85149530852&partnerID=8YFLogxK

U2 - 10.1109/CCDC55256.2022.10033427

DO - 10.1109/CCDC55256.2022.10033427

M3 - Conference contribution

AN - SCOPUS:85149530852

T3 - Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022

SP - 357

EP - 363

BT - Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 34th Chinese Control and Decision Conference, CCDC 2022

Y2 - 15 August 2022 through 17 August 2022

ER -

Zhao G , Wang X , Zheng S, Han Q. A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence. In Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 357-363. (Proceedings of the 34th Chinese Control and Decision Conference, CCDC 2022). doi: 10.1109/CCDC55256.2022.10033427

A Novel Version of Sampling-based Motion Planner for Manipulation with Faster Initial Solution and Convergence

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this