Optimal path planning in cluttered environment using RRT*-AB

Iram Noreen, Amna Khan, Hyejeong Ryu, Nakju Doh, Zulfiqar Habib

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Rapidly exploring Random Tree Star (RRT*) has gained popularity due to its support for complex and high-dimensional problems. Its numerous applications in path planning have made it an active area of research. Although it ensures probabilistic completeness and asymptotic optimality, its slow convergence rate and large dense sampling space are proven problems. In this paper, an off-line planning algorithm based on RRT* named RRT*-adjustable bounds (RRT*-AB) is proposed to resolve these issues. The proposed approach rapidly targets the goal region with improved computational efficiency. Desired objectives are achieved through three novel strategies, i.e., connectivity region, goal-biased bounded sampling, and path optimization. Goal-biased bounded sampling is performed within boundary of connectivity region to find the initial path. Connectivity region is flexible enough to grow for complex environment. Once path is found, it is optimized gradually using node rejection and concentrated bounded sampling. Final path is further improved using global pruning to erode extra nodes. Robustness and efficiency of proposed algorithm is tested through experiments in different structured and unstructured environments cluttered with obstacles including narrow and complex maze cases. The proposed approach converges to shorter path with reduced time and memory requirements than conventional RRT* methods.

Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalIntelligent Service Robotics
DOIs
Publication statusAccepted/In press - 2017 Aug 3

Fingerprint

Motion planning
Sampling
Computational efficiency
Stars
Data storage equipment
Planning
Experiments

Keywords

  • Cluttered environment
  • Intelligent sampling
  • Optimal path
  • Robot path planning
  • RRT*
  • RRT*-AB

ASJC Scopus subject areas

  • Computational Mechanics
  • Engineering (miscellaneous)
  • Mechanical Engineering
  • Artificial Intelligence

Cite this

Optimal path planning in cluttered environment using RRT*-AB. / Noreen, Iram; Khan, Amna; Ryu, Hyejeong; Doh, Nakju; Habib, Zulfiqar.

In: Intelligent Service Robotics, 03.08.2017, p. 1-12.

Research output: Contribution to journalArticle

Noreen, Iram ; Khan, Amna ; Ryu, Hyejeong ; Doh, Nakju ; Habib, Zulfiqar. / Optimal path planning in cluttered environment using RRT*-AB. In: Intelligent Service Robotics. 2017 ; pp. 1-12.
@article{ffbdc472e0254d38bfb3c42d3f91f82e,
title = "Optimal path planning in cluttered environment using RRT*-AB",
abstract = "Rapidly exploring Random Tree Star (RRT*) has gained popularity due to its support for complex and high-dimensional problems. Its numerous applications in path planning have made it an active area of research. Although it ensures probabilistic completeness and asymptotic optimality, its slow convergence rate and large dense sampling space are proven problems. In this paper, an off-line planning algorithm based on RRT* named RRT*-adjustable bounds (RRT*-AB) is proposed to resolve these issues. The proposed approach rapidly targets the goal region with improved computational efficiency. Desired objectives are achieved through three novel strategies, i.e., connectivity region, goal-biased bounded sampling, and path optimization. Goal-biased bounded sampling is performed within boundary of connectivity region to find the initial path. Connectivity region is flexible enough to grow for complex environment. Once path is found, it is optimized gradually using node rejection and concentrated bounded sampling. Final path is further improved using global pruning to erode extra nodes. Robustness and efficiency of proposed algorithm is tested through experiments in different structured and unstructured environments cluttered with obstacles including narrow and complex maze cases. The proposed approach converges to shorter path with reduced time and memory requirements than conventional RRT* methods.",
keywords = "Cluttered environment, Intelligent sampling, Optimal path, Robot path planning, RRT*, RRT*-AB",
author = "Iram Noreen and Amna Khan and Hyejeong Ryu and Nakju Doh and Zulfiqar Habib",
year = "2017",
month = "8",
day = "3",
doi = "10.1007/s11370-017-0236-7",
language = "English",
pages = "1--12",
journal = "Intelligent Service Robotics",
issn = "1861-2776",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - Optimal path planning in cluttered environment using RRT*-AB

AU - Noreen, Iram

AU - Khan, Amna

AU - Ryu, Hyejeong

AU - Doh, Nakju

AU - Habib, Zulfiqar

PY - 2017/8/3

Y1 - 2017/8/3

N2 - Rapidly exploring Random Tree Star (RRT*) has gained popularity due to its support for complex and high-dimensional problems. Its numerous applications in path planning have made it an active area of research. Although it ensures probabilistic completeness and asymptotic optimality, its slow convergence rate and large dense sampling space are proven problems. In this paper, an off-line planning algorithm based on RRT* named RRT*-adjustable bounds (RRT*-AB) is proposed to resolve these issues. The proposed approach rapidly targets the goal region with improved computational efficiency. Desired objectives are achieved through three novel strategies, i.e., connectivity region, goal-biased bounded sampling, and path optimization. Goal-biased bounded sampling is performed within boundary of connectivity region to find the initial path. Connectivity region is flexible enough to grow for complex environment. Once path is found, it is optimized gradually using node rejection and concentrated bounded sampling. Final path is further improved using global pruning to erode extra nodes. Robustness and efficiency of proposed algorithm is tested through experiments in different structured and unstructured environments cluttered with obstacles including narrow and complex maze cases. The proposed approach converges to shorter path with reduced time and memory requirements than conventional RRT* methods.

AB - Rapidly exploring Random Tree Star (RRT*) has gained popularity due to its support for complex and high-dimensional problems. Its numerous applications in path planning have made it an active area of research. Although it ensures probabilistic completeness and asymptotic optimality, its slow convergence rate and large dense sampling space are proven problems. In this paper, an off-line planning algorithm based on RRT* named RRT*-adjustable bounds (RRT*-AB) is proposed to resolve these issues. The proposed approach rapidly targets the goal region with improved computational efficiency. Desired objectives are achieved through three novel strategies, i.e., connectivity region, goal-biased bounded sampling, and path optimization. Goal-biased bounded sampling is performed within boundary of connectivity region to find the initial path. Connectivity region is flexible enough to grow for complex environment. Once path is found, it is optimized gradually using node rejection and concentrated bounded sampling. Final path is further improved using global pruning to erode extra nodes. Robustness and efficiency of proposed algorithm is tested through experiments in different structured and unstructured environments cluttered with obstacles including narrow and complex maze cases. The proposed approach converges to shorter path with reduced time and memory requirements than conventional RRT* methods.

KW - Cluttered environment

KW - Intelligent sampling

KW - Optimal path

KW - Robot path planning

KW - RRT

KW - RRT-AB

UR - http://www.scopus.com/inward/record.url?scp=85026806995&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026806995&partnerID=8YFLogxK

U2 - 10.1007/s11370-017-0236-7

DO - 10.1007/s11370-017-0236-7

M3 - Article

SP - 1

EP - 12

JO - Intelligent Service Robotics

JF - Intelligent Service Robotics

SN - 1861-2776

ER -