Path planning based on Dijkstra algorithm: an experience with Robotino in ROS

• Grant number: 13/16865-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: September 01, 2013
• End date: December 31, 2014
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Marilza Antunes de Lemos
• Grantee: Carlos Alberto Vilaça Junior
• Host Institution: Universidade Estadual Paulista (UNESP). Campus Experimental de Sorocaba. Sorocaba , SP, Brazil

Abstract

Introducing mobile autonomous agents to navigate and perform tasks in industrial environments is one of the goals to provide flexible manufacturing associated with cost reduction. Particularly, in the industry, these agents are called AGVs (Automatic Guided Vehicle) and are characterized as robust autonomous robots capable of carrying industrial materials and interact with machines. Among the various methods proposed in the literature for path planning is Dijkstra's algorithm. Based on the proposed arena in Festo Logistics Competition/Robocup2013, representing an industrial environment, this project proposes using the Dijkstra algorithm to implement a path planner for this environment. Boost library components related to the Dijkstra algorithm will be adapted according to the application being developed in ROS (Robot Operating System), resulting in the proposed path planner. Thus, the environment of the arena will be modeled as a graph and used in simulated tests for the planner. In sequence, the research will be directed to investigate how to incorporate the planner with other programs ROS in order to run it directly on the Robotino.(AU)