Camera calibration is the first step of positioning using binocular vision. Owning to the approximation capability of the neural network, a complex mathematical model needed by traditional calibration methods can be avoided. However the general neural network methods have their drawbacks to reduce its accuracy. This paper presents searching algorithm for the best structure and parameters of a neural network using an improved genetic algorithm (GA). The experiments show that this method can be used to establish a mapping between 2D coordinates and 3D coordinates directly and accurately, which is better than traditional calibration and general BP network methods.

National University of Defense Technology has begun a research program to investigate and test ducted-fan propeller architecture for UAV designing. Development of a prototype continues to support ongoing research in the area of autonomous systems. In this paper, we build a nonlinear dynamic model of Ducted-Fan UAV for verifying appropriate controller behavior, and design a hierarchical controller for hovering flight of the UAV.

General pseudospectral method is extended to Lie group by virtue of equivariant map for solving rigid dynamics on Lie group. In particular, for the problem of structural characteristics of the dynamics system can not be conserved by using general pseudospectral method directly on Lie group, the differential equation evolving on the Lie group is transformed to an equivalent differential equation evolving on a Lie algebra on which general pseudospectral method is used, so that the numerical flow of rigid body dynamics is ensured to stay on Lie group. Furthermore, structural conservativeness and numerical stabilities of this method are validated and analyzed by simulation on a 3D pendulum in comparison with using pseudospectral method directly on Lie group.