Design and Construction of a Cost-Effective Didactic Robotic Arm for Playing Chess, Using an Artificial Vision System

Cristian Del Toro,Omar Rodríguez-Álvarez,Carlos Robles-Algarín

doi:10.3390/electronics8101154

Cristian Del Toro, Omar Rodríguez-Álvarez + Show 1 more

Open Access

https://doi.org/10.3390/electronics8101154

Copy DOI

Journal: Electronics	Publication Date: Oct 12, 2019
Citations: 5	License type: CC BY 4.0

Affiliation: University of Magdalena

Abstract

This paper presents the design and construction of a robotic arm that plays chess against a human opponent, based on an artificial vision system. The mechanical design was an adaptation of the robotic arm proposed by the rapid prototyping laboratory FabLab RUC (Fabrication Laboratory of the University of Roskilde). Using the software Solidworks, a gripper with 4 joints was designed. An artificial vision system was developed for detecting the corners of the squares on a chessboard and performing image segmentation. Then, an image recognition model was trained using convolutional neural networks to detect the movements of pieces on the board. An image-based visual servoing system was designed using the Kanade–Lucas–Tomasi method, in order to locate the manipulator. Additionally, an Arduino development board was programmed to control and receive information from the robotic arm using Gcode commands. Results show that with the Stockfish chess game engine, the system is able to make game decisions and manipulate the pieces on the board. In this way, it was possible to implement a didactic robotic arm as a relevant application in data processing and decision-making for programmable automatons.

Highlights

The first machine to play chess was built in 1769 by Wolfgang von Kempelen and was known as “The Turk” [1]
The integration of the mechanical and artificial vision systems resulted in a fully functional robot capable of autonomously playing chess against a human using Stockfish as a chess engine
A machine learning model for the color classification and movement detection of chess pieces was successfully implemented for the game perception of an autonomous chess-playing robot

Summary

Introduction

The first machine to play chess was built in 1769 by Wolfgang von Kempelen and was known as “The Turk” [1]. Alan Turing and David Champernowne were the first to develop a program capable of playing a full chess game [2], known as “Turing’s paper machine” [3,4]. Because at the time there were no computers capable of executing the instructions, it was Turing himself who performed the processing tasks using paper and pencil. It was not until 1996 that a fully functional computer program, IBM’s Deep Blue, was able to defeat the world champion Gary Kasparov [5]

Methods

Results

Conclusion