An Evolutionary Path Planner for Multiple Robot Arms

Authors:
Héctor A. Venegas;J. Raymundo Marcial-Romero
Affiliations:
Facultad de Ingeniería, Universidad Autónoma del Estado de México, México;Facultad de Ingeniería, Universidad Autónoma del Estado de México, México
Venue:
EvoWorkshops '09 Proceedings of the EvoWorkshops 2009 on Applications of Evolutionary Computing: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG
Year:
2009

Citing 7
Cited 0

The complexity of robot motion planning

The complexity of robot motion planning
Gross motion planning—a survey

ACM Computing Surveys (CSUR)
Robot Motion Planning

Robot Motion Planning
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
A genetic path planning algorithm for redundant articulated robots

Robotica
Spatial Planning: A Configuration Space Approach

IEEE Transactions on Computers
The Ariadne's clew algorithm

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present preliminary results of a path planner for two robotic arms sharing the same workspace. Unlike many other approaches, our planner finds collision-free paths using the robot's cartesian space as a trade-off between completeness and no workspace preprocessing. Given the high dimensionality of the search space, we use a two phase Genetic Algorithm to find a suitable path in workspaces cluttered with obstacles. Because the length of the path is unknown in advance, the planner manipulates a flexible and well crafted representation which allows the path to grow or shrink during the search process. The performance of our planner was tested on several scenarios where the only moving objects were the two robotic arms. The test scenarios force the manipulators to move through narrow spaces for which suitable and safe paths were found by the planner.