Search

According to the characteristics of cooperative motion control of humanoid robot, a cooperative motion model of two humanoid robot in ball handling was deduced and a control method based on second order cone principle was introduced to maintain the stability in movement for multi-robot. By deducing constraints of stability in cooperative movement, an equation of SOCP was constructed, and the stability control problem was converted for solving equations of second order cone. Finally, the effectiveness of the proposed method is verified by simulation and experiment.

As the traffic situation of the road network in urban areas is becoming increasingly congested, the classical algorithm of rapidly exploring random tree (RRT) is introduced into the scene of the road network with scheduled tracks in this paper. And a dynamic path planning method based on the RRT algorithm is designed. The algorithm takes the start road segment of the route as the root node in the random tree to perform random extensions until the leaf node of the random tree covers the target road segment. Finally, the algorithm is simulated on the road network with congested areas in Wuhan. The result shows that the proposed method can not only effectively avoid the congestion areas in the road network, but also better meet the real-time demand for dynamic path planning.

It is an extremely complex process of controlling walking motion for humanoid robot, and its dynamics model has many rich features. The article puts forward a kind of optimization design method on any time humanoid robot walking movement. Firstly, this article makes a stability analysis of walking humanoid robot based on the ZMP criterion, at the same time with the design of using a humanoid robot walking movement by the criterion of the error between the expectations and kinetic energy of the weighted kinetic minimum norm make the problem into a second-order cone programming (SOCP) optimization problem, then use the interior point method to solve the kinetic energy of optimization coefficient of the humanoid robot walking movement, and by compares with the LMS design method and genetic algorithms, finally the algorithm is validated in the simulation and experiment, the numerical results are present for illustration.

Since remote sensing images' features of substantial data and complex landmark, so it needs a higher requirement for edge detection operator. Using Gabor wavelet as the edge detection operator can get over the limitations of grads operator and Canny operator in edge detection. However, the method based on 2-D Gabor wavelet takes more time. In response to this lack of Gabor wavelet, this paper presents an edge detection method based on parallel processing of FFTW and Gabor wavelet and the experimental analysis shows this method can improve the processing speed of the algorithm greatly.

In order to solve the complex problems in path planning of humanoid robot, an algorithm model based on ant colony algorithm is proposed. The robot simulation modeling environment is formed by the grid. The idea of the algorithm is simulating the process of ants foraging, and many ants complete optimal path search by collaborate with each other to pass the pheromone to find food. Through simulation experiments, we achieved better results. Satisfactory results are achieved by made experiments on the humanoid robot NAO, and the algorithm are verified finally.

For the characteristics of humanoid robot in stability control, a method called second-order cone planning is proposed for controlling the stability of robot walking. The stability control of humanoid robot is configured to convert the second order cone to be suitable for solving the problem by derivating a variety of stability constraints of robot during the walking movement. The effectiveness of the proposed method is validated through simulation and experiments

In this paper, online gait control system is designed for walking-up-stairs movement according to the features of humanoid robot, the hybrid evolutionary approach based on neural network optimized by particle swarm is employed for the offline training of the movement process, and the optimal gait of the stability is generated. Additionally, through embedded monocular vision, on-site environmental information is collected as neural network input, so necessary joint trajectory is output for the movement. Simulations and experiment testify the efficiency of the method.

Vision system is the critical component for soccer robot. During the football competition, most information perceived by robot is from vision system. Because of the variable illumination conditions, traditional image segmentation method based on color information is not satisfactory. An object recognition algorithm, which combined color image segmentation with edge detection is presented in this paper based on the color information and shape information of the object. This algorithm implement image segmentation using color information in the HSV color space obtain the pixel of the object, and use this pixel implement edge detection to recognize the object. Experiments show that this algorithm can recognize the object exactly in the different illumination conditions, satisfy the requirement of the competition.

To meet the demands of game and entertainment, autonomous humanoid robot HIT-2 is designed. Firstly, system structure of the robot is introduced. Then methods of image processing and algorithms for localization based on embedded vision system are presented. Finally, motion planning for penalty kick is carried out by the method of motion control combined with selective joints control.