Navigation of a Differential Wheeled Robot Based on a Type-2 Fuzzy Inference Tree
Dante Mújica-Vargas,
Viridiana Vela-Rincón,
Antonio Luna-Álvarez,
Arturo Rendón-Castro,
Manuel Matuz-Cruz,
José Rubio
Affiliations
Dante Mújica-Vargas
Department of Computer Science, Tecnológico Nacional de México/CENIDET, Interior Internado Palmira S/N, Palmira, Cuernavaca 62490, Mexico
Viridiana Vela-Rincón
Department of Computer Science, Tecnológico Nacional de México/CENIDET, Interior Internado Palmira S/N, Palmira, Cuernavaca 62490, Mexico
Antonio Luna-Álvarez
Department of Computer Science, Tecnológico Nacional de México/CENIDET, Interior Internado Palmira S/N, Palmira, Cuernavaca 62490, Mexico
Arturo Rendón-Castro
Department of Computer Science, Tecnológico Nacional de México/CENIDET, Interior Internado Palmira S/N, Palmira, Cuernavaca 62490, Mexico
Manuel Matuz-Cruz
Departamento de Sistemas Computacionales, Tecnológico Nacional de México/ITTapachula, Tapachula Chiapas 30700, Mexico
José Rubio
Sección de Estudios de Posgrado e Investigación, ESIME Azcapotzalco, Instituto Politécnico Nacional, Av. de las Granjas No. 682, Col. Santa Catarina, Ciudad de México 02250, Mexico
This paper presents a type-2 fuzzy inference tree designed for a differential wheeled mobile robot that navigates in indoor environments. The proposal consists of a controller designed for obstacle avoidance, a controller for path recovery and goal reaching, and a third controller for the real-time selection of behaviors. The system takes as inputs the information provided for a 2D laser range scanner, i.e., the distance of nearby objects to the robot, as well as the robot position in space, calculated from mechanical odometry. The real performance is evaluated through metrics such as clearance, path smoothness, path length, travel time and success rate. The experimental results allow us to demonstrate an appropriate performance of our proposal for the navigation task, with a higher efficiency than the reference methods taken from the state of the art.
