Search

Considering path optimization problem on mobile robot, an experimental platform based on NAO robot is set up to build navigation map and get optimal path under unknown environment. Based on simultaneous localization and mapping (SLAM) theory, the sonar sensor of the NAO robot is adopted to detect distances between robot and obstacles and between robot and end landmark. K-means algorithm is used to classify the obstacle and calculate the accurate distances, and a sonar sensor and a camera are used to distinguish the obstacle and the landmark. Then, Q-learning algorithm is adopted to build navigation map for the robot. After that, bi-directional parallel search strategy and simulate annealing algorithm are proposed to improve traditional artificial bee colony algorithm, and the improved artificial bee colony algorithm is introduced to find optimal path in the navigation map. Finally, the experimental results show that the built navigation map based the robot can find an optimal path from the origin to the landmark avoiding the obstacles and a faster convergence speed can be obtained by the improved artificial bee colony algorithm.

Laser marking is an important branch of the laser information processing technology. The existing laser marking machine based on PC and WINDOWS operating system, are large and inconvenient to move. Still, it cannot work outdoors or in other harsh environments. In order to compensate for the above mentioned disadvantages, this paper proposed an embedded laser marking controller based on ARM and FPGA processors. Based on the principle of laser galvanometer scanning marking, the hardware and software were designed for the application. Experiments showed that this new embedded laser marking controller controls the galvanometers synchronously and could achieve precise marking.

At present, the technology of the traditional relay controller and honeywell digital controller are adopted in many combustion machine control systems. But the two technologies show some shortcomings in practice. A new combustion machine control system based on PLC was presented in which the intelligent PID control algorithm was adopted. In the new proposed system, the temperature is controlled by the analog outputs. The practical application results show that the proposed system with properties of high accuracy, good stability and high reliability. The design of software and hardware of the new system is introduced in this paper.

This paper presents an improved method of fabric defects inspection based on local entropy. The adaptive threshold was used for judging the defects of different pictures. It is good for reducing the error due to the change of the background and the subjective factor. The Tyler expand is also used to simplify the formula of the local entropy to accelerate the speed of calculation. In addition, noise in pictures is filtered out and the shape of the defects remains the same after the filtering by opening function of mathematical morphology. Final experiment results shows that this method has the advantage of high identification and good anti-noise ability.

A method of character recognition based on Hough transform and RBF neural network is proposed through research on weight accumulation algorithm of Hough transform. According to the feature of characters’ structure by using the duality of point-line Hough transform was done. In this method, the number of the points on the same line in parameter space and the position coordinates of the elements in image mapping space were taken to RBF neural network recognition system as characteristic input vector. It reduced the dimension of character feature vector and reflected the overall distribution of character lattice and the essential feature of character shape. The simulation results indicated there were some merits in this improved method: capability of recognition is strong, the quantity of calculation is small, and the speed of calculation is quick.