Aim to the disadvantage of traditional panoramic image feature extraction and matching algorithm, such as huge data processing and low time efficiency, an improved panoramic image feature extraction and matching algorithm base on SURF and improved KD tree search is proposed. Firstly, SURF is used to extract feature point and generate feature description, secondly, the KD tree search method with high efficiency is used to match feature point, and an improved KD tree search method is proposed to avoid wrong matching. Simulation and experiment results in case of translation and rotation indicate that the proposed algorithm owns better efficiency, accuracy and robust property.

An improved simultaneous localization and mapping(SLAM) method based on extended Kalman filter(EKF) is presented to solve the SLAM problem of mobile robot with omnidirectional vision. The environment feature is extracted from the environment information around the mobile robot got by onmidirectional vision, then the landmark is located, finally, the position and attitude of the mobile robot and the map library are updated synchronously by using the EKF algorithm. Simulation results and real robot experiment results indicate the effectiveness and accuracy of the proposed approach.

Aircraft landing process is the most complicated and most dangerous phases of flight.For highly nonlinear,atmospheric environmental interference,and high real-time requirement,a new optimized CMAC-PID adaptive control is presented which is applied in simulation of 6DOF nonlinear aircraft landing process.Based on traditional CMAC-PID,the adaptive control of the optimized learning rate is implemented,which effectively improved the learning speed.The PID parameters are adjusted by using Genetic Algorithm.Thereby,the whole control system has been further optimized.The simulation of 6DOF nonlinear aircraft landing process based on the proposed control method is implemented.The simulation results show that the optimized CMAC-PID adaptive control has perfect dynamic characteristic and strong ability of rejection.

In order to solve problems with static sensor nodes,the monitoring performance of key points using mobile robots was studied.Mathematical expectations of the number of state cycles of key points in a certain period of time were deduced,in order to obtain an event number that was monitored by a mobile sensor in a key point,and the function of monitoring performance was obtained.Also,monitoring performance was analyzed theoretically along with velocity,path and the number of mobile robots.At the same time the mobile robots sensor motion planning method was proposed,and through a heuristic motion planning method k paths were established,allowing each key point to be monitored by at least one mobile sensor.This enabled the monitoring performance to be as successful as possible.Simulation experiments show that when the speed exceeds a certain value,the monitoring performance of mobile sensors will be greater than of fixed sensors.With the increasing number of mobile sensors the monitoring performance grows.

A k-TSPN(traveling salesman problem with neighborhoods) algorithm was proposed,which can divide k-TSPN problem into two sub-problems to reduce the complexity of the problem.k paths of robots were generated by random recursion algorithm to determine the visited sequence of each path by sensors.Then,the hitting points were searched within communication range of each sensor by GA to optimize the paths,and the points were expressed by angles to reduce a half of optimized variables and the range of the hitting points,reducing the search space of genetic algorithm and the extreme points greatly.By niching,population migration and increasing Hamming distance between different populations,an improved adaptive genetic algorithm was improved;enhances search speed and precision of genetic algorithm.Simulation results show that the proposed algorithm reduces the length of the paths and get a better result.

The quality of coverage achieved by mobile sensors depends on the velocity, mobility pattern, number of mobile sensors deployed and the dynamics of the phenomenon being sensed. The gains attained by mobile sensors over static sensors and the optimal motion strategies for mobile sensors are not well understood. In this paper we consider the following event capture problem: The events of interest arrive at certain points in the sensor field and disappear according to known arrival and departure time distributions. An event is said to be captured if it is sensed by one of the mobile sensors before it fades away. We analyze how the quality of coverage scales with velocity and number of mobile sensors. We present algorithm for the motion planning problem: for sensors with fixed speed, what is the minimum number of sensors required to satisfy a bound on the event loss probability? For the minimum sensor problem, when the robots are restricted to move along a line our algorithm return the number of sensors used is within a factor of two of the optimal solution. Simulation experiments show that the Superiority of the proposed algorithm.

As a generalization of one-dimensional minimum-error threshold segmentation method was widely used in image segmentation.In this paper,two-dimensional minimum-error threshold algorithm and its fast algorithm(here referring to the original method) are improved,and threshold acquirement formula of the original minimum-error threshold segmentation method was deformed.By using look-up table method,acquirement of two-dimensional threshold is transformed into that of two one-dimensional threshold,so the calculation is simplified and time complexity is reduced from O(L2) to O(L).Experimental results show this decomposition algorithm outperforms original algorithm.Without losing the robustness to noise and needing more time and space,it can get the same segmentation threshold as the original method.

The designing method of filtering, fault-tolerating, and fusing PID control is put forward, concerning multisensor time-delay system with colored noise disturbance. First of all, this method detects fault and isolate the data by the weighted square sum of residuals (WSSR) method which is measured by multisensors, then the data which is detected right will be measurement fused, and the fused data will be optimally filtered basing on modern time series analysis method. Finally, the global optimal estimation of measured data will be got, which will be brought back to the input endian in order to improve PID controlling accuracy. A 3-sensor servomotor control example shows the effectiveness of the method.

Mobile robots often need to find a trajectory to another position in their environment, subject to constraints posed by obstacles and the robot's capabilities. Several approaches have been used to address this problem each with some limitations, including state discretizations, planning efficiency, and lack of interleaved execution. Anytime RRTs algorithm is a recently developed algorithm on which fast continuous domain path planners can be based. This paper presents a modification to the anytime RRTs algorithm. Optimization include a more general biased distribution, which was explored in this work in the form of a waypoint cache. Which improve replanning efficiency and the quality of generated paths. We demonstrate the effectiveness of the algorithm on single robot planning domains.

The problem of collision-free path planning for nuclear reactor repairing manipulator with the given end path is considered.A hybrid algorithm of combining the transpose of Jacobian control algorithm with rapidly-exploring random tree method is presented.The nearest configuration point to the workspace with goal point is taken as the expanded node of the tree to avoid the solving of inverse kinematics.The best expanding direction is calculated with the jacobian transpose control algorithm.And the velocity of the end tool of the manipulator is restricted by using the bisection gradient-decent extend algorithm to avoid the occurrence of joint velocity mutation.The simulation results show the rapidity and validity of the proposed hybrid algorithm.