Celso De la Cruz

SLAM-based robotic wheelchair navigation system designed for confined spaces

In the present work, a robotic wheelchair navigation system which is specially designed for confined spaces is proposed. In confined spaces, the movements of wheelchairs are restricted by the environment more than other unicycle type vehicles. For example, if the wheelchair is too close to a wall, it can not rotate freely because the front or back may collide with the wall. The navigation system is composed by a path planning module and a control module; both use the environment and robot information provided by a SLAM algorithm to attain their objectives. The planning strategy uses the Monte Carlo technique to find a minimum path within the confined environment and takes into account the variance propagation in the predicted path for ensuring the safe driving of the robot. The objective of the navigation system is to drive the robotic wheelchair within the confined environment in order to reach a desired orientation or posture.

Navegación Autónoma Asistida Basada en SLAM para una Silla de Ruedas Robotizada en Entornos Restringidos

In this work, an interface specially designed for a robotic wheelchair’s navigation within confined spaces is presented. The interface performance is based on two modus: autonomous and non-autonomous. The non-autonomous execution of the robotic wheelchair interface is performed by means of a joystick. The joystick is adapted to the wheelchair’s patient capabilities and it governs the motion of the vehicle within the environment. The autonomous modus of the robotic wheelchair is executed when the user has to turn a given angle within the environment. The turning strategy is performed by means of both: a maneuverability algorithm which is compatible with the wheelchair’s kinematics and the SLAM (Simultaneous Localization and Mapping) algorithm. In addition, the autonomous modus is composed by two modules: a path planning module and a control module. The path planning module uses the map information provided by the SLAM algorithm to generate a safe path compatible with the robotic wheelchair. Such path will allow the vehicle to reach the orientation -angle of turning- given by the user. The control module governs the motion of the robotic wheelchair by means of a trajectory controller when following the path generated by the path planning algorithm. The controller references are updated by the SLAM estimation of the wheelchair’s pose within the environment. Experimental results using a real robotic wheelchair are also shown in this work.

Autonomous assistance navigation for robotic wheelchairs in confined spaces

In this work, a visual interface for the assistance of a robotic wheelchairs navigation is presented. The visual interface is developed for the navigation in confined spaces such as narrows corridors or corridor-ends. The interface performs two navigation modus: non-autonomous and autonomous. The non-autonomous driving of the robotic wheelchair is made by means of a hand-joystick. The joystick directs the motion of the vehicle within the environment. The autonomous driving is performed when the user of the wheelchair has to turn (90, ™90 or 180 degrees) within the environment. The turning strategy is performed by a maneuverability algorithm compatible with the kinematics of the wheelchair and by the SLAM (Simultaneous Localization and Mapping) algorithm. The SLAM algorithm provides the interface with the information concerning the environment disposition and the pose -position and orientation-of the wheelchair within the environment. Experimental and statistical results of the interface are also shown in this work.

SLAM-based turning strategy in restricted environments for car-like mobile robots

In the present work, a strategy to turn a carlike mobile robot in a restricted environment is presented. The strategy uses a Simultaneous Localization and Map Building (SLAM) algorithm to localize the robot in the environment and uses the map generated by the SLAM in the reverse movement of the turning strategy. The planning strategy takes into account the variance propagation in the predicted path for ensure the safe driving of the robot. In all the cases, the robot is considered as a body in movement, not as a point, to exploit all the navigable space. The vehicle is commanded by a kinematic trajectory controller. Real time experimental results are also shown in this work.

Evolving hardware using a new evolutionary algorithm based on evolution of a species

This work presents the analysis of species evolution properties which are considered to design a new evolutionary algorithm for evolvable hardware. These properties reduce the risk of malfunctions in a physical system when it is evolving. A mathematical model, that characterises the natural evolution phenomena of a species, is proposed. A new evolutionary algorithm based on this model is proposed as well. This algorithm is designed to evolve hardware, e.g., to obtain the optimal control parameters of a real control system, while it is executing a repetitive task. The convergence of the proposed algorithm was proven by means of new theorems. Simulations and experimentation studies were carried out in order to validate the theoretical aspects and to evaluate the performance of the evolutionary algorithm.