Optimal path planning based on a multi-tree T-RRT* approach for robotic task planning in continuous cost spaces

Research output: Contribution to conferencePaper

Abstract

This paper presents an integrated approach to robotic task planning in continuous cost spaces. This consists of a low-level path planning phase and a high-level Planning Domain Definition Language (PDDL)-based task planning phase. The path planner is based on a multi-tree implementation of the optimal Transition-based Rapidly-exploring Random Tree (T-RRT*) that searches the environment for paths between all pairs of configuration waypoints. A method for shortcutting paths based on cost function is also presented. The resulting minimized path costs are then passed to a PDDL planner to solve the high-level task planning problem while optimizing the overall cost of the solution plan. This approach is demonstrated on two scenarios consisting of different cost functions: obstacle clearance in a cluttered environment and elevation in a mountain environment. Preliminary results suggest that significant improvements to path quality can be achieved without significant increase to computation time when compared with a T-RRT-based implementation.

Conference

Conference12th France - Japan Congress, 10th Europe - Asia Congress on Mechatronics
Abbreviated titleMECH2018
CountryJapan
CityTsu, Mie
Period10/09/1812/09/18
Internet address

Fingerprint

Motion planning
Robotics
Planning
Costs
Cost functions

Keywords

  • task planning
  • sampling-based path planning
  • cost space planning
  • autonomy
  • robotics

Cite this

Wong, C., Yang, E., Yan, X-T., & Gu, D. (2018). Optimal path planning based on a multi-tree T-RRT* approach for robotic task planning in continuous cost spaces. 242-247. Paper presented at 12th France - Japan Congress, 10th Europe - Asia Congress on Mechatronics, Tsu, Mie, Japan. https://doi.org/10.1109/MECATRONICS.2018.8495886
Wong, Cuebong ; Yang, Erfu ; Yan, Xiu-Tian ; Gu, Dongbing. / Optimal path planning based on a multi-tree T-RRT* approach for robotic task planning in continuous cost spaces. Paper presented at 12th France - Japan Congress, 10th Europe - Asia Congress on Mechatronics, Tsu, Mie, Japan.6 p.
@conference{9547a1ad7d8d471b99cba14f285b8f98,
title = "Optimal path planning based on a multi-tree T-RRT* approach for robotic task planning in continuous cost spaces",
abstract = "This paper presents an integrated approach to robotic task planning in continuous cost spaces. This consists of a low-level path planning phase and a high-level Planning Domain Definition Language (PDDL)-based task planning phase. The path planner is based on a multi-tree implementation of the optimal Transition-based Rapidly-exploring Random Tree (T-RRT*) that searches the environment for paths between all pairs of configuration waypoints. A method for shortcutting paths based on cost function is also presented. The resulting minimized path costs are then passed to a PDDL planner to solve the high-level task planning problem while optimizing the overall cost of the solution plan. This approach is demonstrated on two scenarios consisting of different cost functions: obstacle clearance in a cluttered environment and elevation in a mountain environment. Preliminary results suggest that significant improvements to path quality can be achieved without significant increase to computation time when compared with a T-RRT-based implementation.",
keywords = "task planning, sampling-based path planning, cost space planning, autonomy, robotics",
author = "Cuebong Wong and Erfu Yang and Xiu-Tian Yan and Dongbing Gu",
note = "{\circledC} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 12th France - Japan Congress, 10th Europe - Asia Congress on Mechatronics, MECH2018 ; Conference date: 10-09-2018 Through 12-09-2018",
year = "2018",
month = "9",
day = "10",
doi = "10.1109/MECATRONICS.2018.8495886",
language = "English",
pages = "242--247",
url = "http://www.tc-iaip.org/mecatronics2018/index.html",

}

Wong, C, Yang, E, Yan, X-T & Gu, D 2018, 'Optimal path planning based on a multi-tree T-RRT* approach for robotic task planning in continuous cost spaces' Paper presented at 12th France - Japan Congress, 10th Europe - Asia Congress on Mechatronics, Tsu, Mie, Japan, 10/09/18 - 12/09/18, pp. 242-247. https://doi.org/10.1109/MECATRONICS.2018.8495886

Optimal path planning based on a multi-tree T-RRT* approach for robotic task planning in continuous cost spaces. / Wong, Cuebong; Yang, Erfu; Yan, Xiu-Tian; Gu, Dongbing.

2018. 242-247 Paper presented at 12th France - Japan Congress, 10th Europe - Asia Congress on Mechatronics, Tsu, Mie, Japan.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Optimal path planning based on a multi-tree T-RRT* approach for robotic task planning in continuous cost spaces

AU - Wong, Cuebong

AU - Yang, Erfu

AU - Yan, Xiu-Tian

AU - Gu, Dongbing

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2018/9/10

Y1 - 2018/9/10

N2 - This paper presents an integrated approach to robotic task planning in continuous cost spaces. This consists of a low-level path planning phase and a high-level Planning Domain Definition Language (PDDL)-based task planning phase. The path planner is based on a multi-tree implementation of the optimal Transition-based Rapidly-exploring Random Tree (T-RRT*) that searches the environment for paths between all pairs of configuration waypoints. A method for shortcutting paths based on cost function is also presented. The resulting minimized path costs are then passed to a PDDL planner to solve the high-level task planning problem while optimizing the overall cost of the solution plan. This approach is demonstrated on two scenarios consisting of different cost functions: obstacle clearance in a cluttered environment and elevation in a mountain environment. Preliminary results suggest that significant improvements to path quality can be achieved without significant increase to computation time when compared with a T-RRT-based implementation.

AB - This paper presents an integrated approach to robotic task planning in continuous cost spaces. This consists of a low-level path planning phase and a high-level Planning Domain Definition Language (PDDL)-based task planning phase. The path planner is based on a multi-tree implementation of the optimal Transition-based Rapidly-exploring Random Tree (T-RRT*) that searches the environment for paths between all pairs of configuration waypoints. A method for shortcutting paths based on cost function is also presented. The resulting minimized path costs are then passed to a PDDL planner to solve the high-level task planning problem while optimizing the overall cost of the solution plan. This approach is demonstrated on two scenarios consisting of different cost functions: obstacle clearance in a cluttered environment and elevation in a mountain environment. Preliminary results suggest that significant improvements to path quality can be achieved without significant increase to computation time when compared with a T-RRT-based implementation.

KW - task planning

KW - sampling-based path planning

KW - cost space planning

KW - autonomy

KW - robotics

UR - http://www.tc-iaip.org/mecatronics2018/

U2 - 10.1109/MECATRONICS.2018.8495886

DO - 10.1109/MECATRONICS.2018.8495886

M3 - Paper

SP - 242

EP - 247

ER -

Wong C, Yang E, Yan X-T, Gu D. Optimal path planning based on a multi-tree T-RRT* approach for robotic task planning in continuous cost spaces. 2018. Paper presented at 12th France - Japan Congress, 10th Europe - Asia Congress on Mechatronics, Tsu, Mie, Japan. https://doi.org/10.1109/MECATRONICS.2018.8495886