Continuous Path Planning of Kinematically Redundant Manipulator using Particle Swarm Optimization

Abstract: This paper addresses a problem of a continuous path planning of a redundant manipulator where an end-effector needs to follow a desired path. Based on a geometrical analysis, feasible postures of a self-motion are mapped into an interval so that there will be an angle domain boundary and a redundancy resolution to track the desired path lies within this boundary. To choose a best solution among many possible solutions, meta-heuristic optimizations, namely, a Genetic Algorithm (GA), a Particle Swarm Optimization (PSO), and a Grey Wolf Optimizer (GWO) will be employed with an optimization objective to minimize a joint angle travelling distance. To achieve n-connectivity of sampling points, the angle domain trajectories are modelled using a sinusoidal function generated inside the angle domain boundary. A complex geometrical path obtained from Bezier and algebraic curves are used as the traced path that should be followed by a 3-Degree of Freedom (DOF) arm robot manipulator and a hyper-redundant manipulator. The path from the PSO yields better results than that of the GA and GWO.

Affiani Machmudah, Setyamartana Parman and M.B. Baharom. “Continuous Path Planning of Kinematically Redundant Manipulator using Particle Swarm Optimization”. International Journal of Advanced Computer Science and Applications (IJACSA) 9.3 (2018). http://dx.doi.org/10.14569/IJACSA.2018.090330

@article{Machmudah2018,
title = {Continuous Path Planning of Kinematically Redundant Manipulator using Particle Swarm Optimization},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2018.090330},
url = {http://dx.doi.org/10.14569/IJACSA.2018.090330},
year = {2018},
publisher = {The Science and Information Organization},
volume = {9},
number = {3},
author = {Affiani Machmudah and Setyamartana Parman and M.B. Baharom}
}