Computing multiple guiding paths for sampling-based motion
planning

D 2019

Computing multiple guiding paths for sampling-based motion planning

VONÁSEK, Vojtěch, Robert PĚNIČKA and Barbora KOZLÍKOVÁ

Basic information

Original name

Computing multiple guiding paths for sampling-based motion planning

Authors

VONÁSEK, Vojtěch (203 Czech Republic, guarantor), Robert PĚNIČKA (203 Czech Republic) and Barbora KOZLÍKOVÁ (203 Czech Republic, belonging to the institution)

Edition

Belo Horizonte, Brazil, Proceedings of the 19th International Conference on Advanced Robotics, ICAR 2019, p. 374-381, 8 pp. 2019

Publisher

Neuveden

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10200 1.2 Computer and information sciences

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

RIV identification code

RIV/00216224:14330/19:00107686

Organization unit

Faculty of Informatics

ISBN

978-1-7281-2467-4

DOI

http://dx.doi.org/10.1109/ICAR46387.2019.8981589

UT WoS

000542960700060

Keywords in English

path planning;sampling;configuration space;robotics

Abstract

V originále

Path planning of 3D solid objects leads to search in a six-dimensional configuration space, which can be solved by sampling-based motion planning. The well known issue of sampling-based planners is the narrow passage problem which is caused by the presence of small regions of the configuration space, that are difficult to cover by random samples. Guided-based planners cope with this issue by increasing probability of sampling along an estimated solution (a guiding path). In the case of six-dimensional configuration space, a guiding path needs to be computed in the configuration space rather than in the workspace. Fast computation of guiding paths can be achieved by solving similar, yet simpler problem, e.g., by reducing size of the robot. This results in an approximate solution (path) that is assumed to be located near the solution of the original problem. The guided sampling along this approximate solution may however fail if the approximate solution is too far from the desired solution. We cope with this problem by sampling the configuration space along multiple approximate solutions. We propose an iterative method to compute multiple approximate solutions in the configuration space. Exploration of the configuration space around already found paths is inhibited, which boosts the search of alternative paths. The performance of the proposed approach is verified in scenarios with multiple narrow passages and compared with several state-of-the-art planners.

Links

GA17-07690S, research and development project

Name: Metody identifikace a vizualizace tunelů pro flexibilní ligandy v dynamických proteinech (Acronym: FLigComp)

Investor: Czech Science Foundation

Citovat

VONÁSEK, Vojtěch, Robert PĚNIČKA and Barbora KOZLÍKOVÁ. Computing multiple guiding paths for sampling-based motion planning. Online. In ICAR - 19th International Conference on Advanced Robotics. Proceedings of the 19th International Conference on Advanced Robotics, ICAR 2019. Belo Horizonte, Brazil: Neuveden, 2019, p. 374-381. ISBN 978-1-7281-2467-4. Available from: https://dx.doi.org/10.1109/ICAR46387.2019.8981589.

@inproceedings{1563696,
   author = {Vonásek, Vojtěch and Pěnička, Robert and Kozlíková, Barbora},
   address = {Belo Horizonte, Brazil},
   booktitle = {Proceedings of the 19th International Conference on Advanced Robotics, ICAR 2019},
   doi = {http://dx.doi.org/10.1109/ICAR46387.2019.8981589},
   editor = {ICAR - 19th International Conference on Advanced Robotics},
   keywords = {path planning;sampling;configuration space;robotics},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Belo Horizonte, Brazil},
   isbn = {978-1-7281-2467-4},
   pages = {374-381},
   publisher = {Neuveden},
   title = {Computing multiple guiding paths for sampling-based motion planning},
   year = {2019}
}

TY  - JOUR
ID  - 1563696
AU  - Vonásek, Vojtěch - Pěnička, Robert - Kozlíková, Barbora
PY  - 2019
TI  - Computing multiple guiding paths for sampling-based motion planning
PB  - Neuveden
CY  - Belo Horizonte, Brazil
SN  - 9781728124674
KW  - path planning;sampling;configuration space;robotics
N2  - Path planning of 3D solid objects leads to search in a six-dimensional configuration space, which can be solved by sampling-based motion planning. The well known issue of sampling-based planners is the narrow passage problem which is caused by the presence of small regions of the configuration space, that are difficult to cover by random samples. Guided-based planners cope with this issue by increasing probability of sampling along an estimated solution (a guiding path). In the case of six-dimensional configuration space, a guiding path needs to be computed in the configuration space rather than in the workspace. Fast computation of guiding paths can be achieved by solving similar, yet simpler problem, e.g., by reducing size of the robot. This results in an approximate solution (path) that is assumed to be located near the solution of the original problem. The guided sampling along this approximate solution may however fail if the approximate solution is too far from the desired solution. We cope with this problem by sampling the configuration space along multiple approximate solutions. We propose an iterative method to compute multiple approximate solutions in the configuration space. Exploration of the configuration space around already found paths is inhibited, which boosts the search of alternative paths. The performance of the proposed approach is verified in scenarios with multiple narrow passages and compared with several state-of-the-art planners.
ER  -

VONÁSEK, Vojtěch, Robert PĚNIČKA and Barbora KOZLÍKOVÁ. Computing multiple guiding paths for sampling-based motion planning. Online. In ICAR - 19th International Conference on Advanced Robotics. \textit{Proceedings of the 19th International Conference on Advanced Robotics, ICAR 2019}. Belo Horizonte, Brazil: Neuveden, 2019, p.~374-381. ISBN~978-1-7281-2467-4. Available from: https://dx.doi.org/10.1109/ICAR46387.2019.8981589.

Detailed Information on Publication Record