Search

In the current investigation, a two-stage hybridization model has been used for the motion planning of humanoids in complex environmental conditions using regression analysis and the firefly algorithm. In the first step, sensory outputs are fed to the regression model, and an initial turning angle (ITA) is obtained. In the second step, the ITA is again fed as input to the firefly model along with other required inputs, and the final turning angle (FTA) is obtained. The FTA serves as the guiding parameter for the humanoids to reach their desired destinations. The developed motion planning scheme has been implemented on NAO humanoid robots in simulation and experimental platforms. A Petri-Net control strategy has been integrated along with the hybrid scheme while negotiating multiple humanoids in a common platform. The results obtained from the motion planning analysis in simulation and experimental arenas are compared against each other in terms of selected navigational parameters and observed satisfactory agreements. Finally, the proposed hybrid controller is also tested against another standard navigational model and substantial enhancement in the performance has been noticed. [ABSTRACT FROM AUTHOR]

The increasing demand for automation and material transportation has shown an incline toward optimal path navigation. The present work implements an intelligent Memory-based gravitational search algorithm (MGSA) with an evolutionary learning strategy to achieve a globally optimal collision-free path. The Evolutionary learning strategy helps improve the diversity among the Gravitational masses/agents, hence improving the overall exploration capability of the model. While the other approaches focus more on an evolutionary strategy based on mutation and cross-overs, the present technique implements the evolutionary strategy based on the position of the fit agents to improve the position of the unfit agents in the population. It ensures a fast-converging path planning result with an improved trajectory. Further, adding a memory-based approach helps the model remember the location of the best agent within the population. The controller is tested with multiple Humanoids on even and uneven terrains and showed a minimal improvement of more than 4% in path length with a minimum 5% deviation in the simulation and experimental results. The proposed approach showed a further improvement of more than 6% compared to the different intelligent path-planning approaches in a similar environment. [ABSTRACT FROM AUTHOR]

Parameters identification on structure subjected to moving load can be predicted by using the accurate and reliable data. The concepts of recurrent neural networks (RNNs) approach have been used in parameters (crack locations and severities) identifications in structure subjected to moving load in the present methodology. This methodology has incorporated the knowledge based Elman's recurrent neural networks (ERNNs) and Jordan's recurrent neural networks (JRNNs) jointly for the identification of parameters. This approach has been addressed as the inverse problem for predicting the locations and quantification of cracks in the structure in a supervised manner. The Levenberg-Marquardt's back propagation algorithm is implemented to train the proposed networks. To check the robustness of the present method, Numerical studies followed by Finite Element Analysis (FEA) and experimental verifications (Forward problems) are presented as a case study by considering a multi-cracked simply supported structure under a moving mass. The estimated crack locations and severities obtained from the proposed RNNs model converge well with those of FEA and experiments. From the demonstration of the case study, it concludes that the proposed analogy can identify and quantify the crack locations and severities effectively.

This paper addresses the performance comparison of Radial Basis Function Neural Network (RBFNN) with novel Wavelet Neural Network (WNN) of designing intelligent controllers for path planning of mobile robot in an unknown environment. In the proposed WNN, different types of activation functions such as Mexican Hat, Gaussian and Morlet wavelet functions are used in the hidden nodes. The neural networks are trained by an intelligent supervised learning technique so that the robot makes a collision-free path in the unknown environment during navigation from different starting points to targets/goals. The efficiency of two algorithms is compared using some MATLAB simulations and experimental setup with Arduino Mega 2560 microcontroller in terms of path length and time taken to reach the target as an indicator for the accuracy of the network models.