Intelligent control based on wavelet decomposition and neural network for predicting of human trajectories with a novel vision-based robotic

• Published in: Expert systems with applications Vol. 38; no. 11; pp. 13994 - 14000
• Main Author: Soyguder, Servet
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2011
• Subjects: Artificial neural network (ANN); Computer simulation; Decomposition; Human; Human trajectory; Intelligent control; Mathematical models; Mobile robots; Robotics; Target tracking predicting; Tracking systems; Trajectories; Wavelet; Wavelet decomposition (WD); Target tracking predicting; Artificial neural network (ANN); Mobile robots; Human trajectory; Wavelet decomposition (WD); Intelligent control
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2011.04.207

► I modeled an intelligent novel vision-based robotic tracking system which developed to predict the performance of human trajectories. ► I examined to learn trajectory data of information about vision-based robot. ► The learned information to find out road will increase performance of mobile robot. ► Besides, the learned information by sensors on robot will provide the robot’s interaction with the environment. In this paper, an intelligent novel vision-based robotic tracking model is developed to predict the performance of human trajectories with a novel vision-based robotic tracking system. The developed model is based on wavelet packet decomposition, entropy and neural network. We represent an implementation of a novel vision-based robotic tracking system based on wavelet decomposition and artificial neural (WD-ANN) which can track desired human trajectory pattern in real environments. The input–output data set of the novel vision-based robotic tracking system were first stored and than these data sets were used to predict the robotic tracking based on WD-ANN. In simulations, performance measures were obtained to compare the predicted and human–robot trajectories like actual values for model validation. In statistical analysis, the RMS value is 0.0729 and the R 2 value is 99.76% for the WD-ANN model. This study shows that the values predicted with the WD-ANN can be used to predict human trajectory by vision-based robotic tracking system quite accurately. All simulations have shown that the proposed method is more effective and controls the systems quite successful.