SLAM Algorithm Applied to Robotics Assistance for Navigation in Unknown Environments

FERNANDO AUAT CHEEIN; NATALIA LÓPEZ; CARLOS SORIA; EUGENIO OROSCO; FERNANDO LOBO PEREIRA; FERNANDO DI SCIASCIO; RICARDO CARELLI

Paraná Entre Ríos Argentina

Jornada; II Jornadas Argentinas sobre Interfaces Cerebro Computadora; 2009

Laboratorio de Ingeniería en Rehabilitación e Investigaciones Neuromusculares y Sensoriales. FI. UNER

In this paper, a Simultaneous Localization and Mapping (SLAM) algorithm is implemented to allow the environmental learning of a mobile robot while its navigation is governed by -and not restricted to- electromyographic signals. The environmental learning executed by the SLAM and low behaviour based reactions of the mobile robot are robotic autonomous tasks whereas the mobile robot navigation inside an environment is commanded by a Muscle-Computer Interface (MCI), user decision dependent. A sequential Extended Kalman Filter (EKF) feature-based SLAM is implemented. For mobile robot navigation purposes, five commands were obtained from the MCI: turn to the left, turn to the right, stop, start and exit. A kinematics controller to control the mobile robot was implemented. A low level behavior strategy was also implemented to avoid robot?s collisions with the environment and moving agents. The entire system was tested in a population of seven volunteers and the experiments were carried out inside a closed low dynamic environment showing an average time of 35 minutes in completing the navigation of the entire environment while learning to use of MCI. The SLAM results have shown a consistent reconstruction of the environment. The integration of a highly demanding processing stage -the SLAM- with a MCI and the communication between both on real time execution have shown to be successful.