Topological Autonomous Navigation for Mobile Robots in Indoor Environments using ANN and FSM

Daniel Oliveira SalesFernando Santos OsórioDenis Fernando Wolf

In this paper, we present an autonomous navigation system based on a finite state machine (FSM) combined with an artificial neural network (ANN) in an indoor patrolling robot. In the first step, the ANN is trained to recognize the different specific environment configurations, identifying the different robot situations (states) based on laser detections. Then, a program generates the expected sequence of states and actions for a specific route defined by the user, configuring a path in a topological like map. So, the robot becomes able to autonomously navigate through this environment, reaching the destination after going through a sequence of specific environment places, each place being identified by its local properties, as for example, straight path, path turning to left, path turning to right, bifurcations and path intersections. The experiments were performed with a Pioneer P3-AT robot equipped with a 180o Sick Lidar and a in a Patrolling task in order to validate and evaluate this approach. The proposed method demonstrated to be a promising approach to autonomous mobile robots navigation.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: