Abstract:
La creación de mapas y modelado del entorno es una tarea primordial en la navegación de robots móviles. Obtener un modelo
del entorno ligero y robusto es imperativo cuando los procesos se van a ejecutar en un robot con capacidad de cómputo y memoria
limitada como es el caso de la mayoría de los rob... Ver más
Map building and environment modelling is a main task in mobile robot navigation. Obtaining a lightweight and robust model
of the environment is crucial when processes are going to be run in a robot with low computing power and memory, as in the
case of most climbing robots. This article proposes the use of different neural network architectures to identify from the data
captured with a LiDAR sensor those points contained in planes belonging to reticular structures. Our purpose is to remove
irrelevant information such as trees or soil in order to reduce the computation and memory requirements for mapping or
localization tasks. For training these neural networks, an automatic dataset generation and labelling process has been developed
through simulated environments. The experiments evidence the capacity of neural networks to segment elements of the structure
contained in a plane.