This paper describes the use of particle swarm algorithm and k-nearest neighbor method to optimize the process of radial basis function (RBF) network and we use the Denavit-Hartenberg (DH) method to research PUMA560 robotics, the results of the forward kinematics is derived as the RBF network training samples. We use six identical RBF network of twelve-input, single output, to achieve a PUMA560 inverse kinematics calculation. Simulation results show that the results obtained with this method has high accuracy and fast convergence. Keyword: k-nearest neighbor method, radial basis function network, particle swarm algorithm, PUMA560 robot, Inverse kinematicssI.

To maximize the bandwidth of green wave of trunk road is a main issue in the research of signal control in urban traffic. However, the traditional analytical algorithmcan not be applied in actual traffic widely. A novel dynamic two-direction green wave coordinate control strategy was proposed to overcome the problem. By combining the genetic BP neural network with the traditional analytical algorithm, the urban traffic of two-direction was controlled coordinately online. Finally, an actual example was presented. It shows that not only the green wave bandwidth, the phase difference of each intersection and the critical cycle of trunk road were optimized according to real-time traffic flow, but also our algorithm can be used in different traffic condition by adjusting the parameters of the model.