Descripción
|
|
---|---|
The Cross-Entropy (CE) is an efficient method for the estimation of rare-event probabilities and combinatorial optimization. In this work is presented a novel approach of the CE for optimization of a Soft-Computing controller. A Fuzzy controller was design to command an unmanned aerial system (UAS) for avoiding collision task. The only sensor used to accomplish this task was a forward camera. The CE is used to reach a near-optimal controller by modify the scaling factors of the controller inputs. The optimization was realized using the ROS-Gazebo simulation system. To evaluate the optimization a big amount of tests were done with a real quadcopter. | |
Internacional
|
Si |
Nombre congreso
|
International Conference on Unmanned Aircraft Systems (ICUAS'12) |
Tipo de participación
|
960 |
Lugar del congreso
|
Philadelphia, PA, USA, |
Revisores
|
Si |
ISBN o ISSN
|
CDP08UPM |
DOI
|
|
Fecha inicio congreso
|
12/06/2012 |
Fecha fin congreso
|
15/06/2012 |
Desde la página
|
0 |
Hasta la página
|
0 |
Título de las actas
|
Proceedings on International Conference on Unmanned Aircraft Systems (ICUAS'12) |