Path pre-planning generate the feasible conference path between start and destination for UAVs, it relates to restrictions from UAVs itself and environment information. Generally, the path is produced by searching in configuration space with some intelligent searching algorithms, the space is always so huge that it is difficult to obtain high efficiency, even lead to NP hard. We proposed a fast 3D path pre-planning method which plan 2D path firstly and then process height planning based on obtained 2D path, considering typical constraints such as turning angle, climbing/diving angle and static threat avoidance. Fast Marching Method (FMM) and Sparse A-Star (SAS) searching method are used in the course of 2D path planning and height planning respectively, Experiments showed that the proposed method generates path quickly, the obtained path follows terrain and avoids obstacles well.

This paper presents a multi-mode intelligent controller based on the schema theory by analyzing AGV steering control strategy, and selects the corresponding control algorithm through the characteristic identification results. The steering control model of V-AGV is built by Human-simulated Intelligent Control based on the sensory-motor schema. The simulation and experiment results show that the AGV runs well in the structure environment, and the model is open and universal application in the unstructured environment.

Distance metric is important for image transform, it reflects the similarity of manifold between pre and post transformation. Tangent distance method is usually used to approximate nonlinear manifolds by its tangent hyperplane in digit recognition; however, it sometimes neglects the high-order statistic information of the image. A new image distance metric is proposed in this paper which is based on Gabor transformation to obtain the Gabor feature vector, then the feature manifold can be approximated by curve surfaces based on second-order Taylor expansion with respect to intrinsic variables, and the distance metric by Gabor transformation is defined as the minimum distance between the approximated curved surfaces in feature observation space. Experiments show that the distance metric based on Gabor transformation and manifold works well on digit recognition, it excelled tangent distance method.