Home // INTELLI 2019, The Eighth International Conference on Intelligent Systems and Applications // View article

Path Planning for an Industrial Robotic Arm

Authors:
Zahid Iqbal
João Reis
Gil Gonçalves

Keywords: sampling-based planning, configuration space, grid-based search, kd trees, PRMs

Abstract:
Enabling humans and robots to work together in modern industrial environments can increase production volumes and reduce costs. However, a robot must be equipped to perceive humans and redirect its actions under hazardous events or for cooperative tasks. Thus, dealing with dynamic obstacles appears as an essential exercise. This work presents a motion planning algorithm for robots based on Probabilistic Road Maps (PRM). For efficient nearest neighbour search, we use kd-trees in learning and query phases of the algorithm. We construct the roadmap as an undirected graph in the free space. We implement the method for a simple configuration space in R2 and a point robot is considered to navigate between given initial and goal configurations added to the roadmap, all specified in two dimensions. We use Euclidean distance when finding the closest neighbours. The shortest path between the start and goal configurations is found using Dijkstra’s algorithm. The method is easy to implement. After the learning phase, the method can answer multiple queries. We propose to use this method in combination with a labelled voxel-based grid for solving multiple path planning queries efficiently.

Pages: 30 to 36

Copyright: Copyright (c) IARIA, 2019

Publication date: June 30, 2019

Published in: conference

ISSN: 2308-4065

ISBN: 978-1-61208-723-8

Location: Rome, Italy

Dates: from June 30, 2019 to July 4, 2019