Navigational analysis of multiple humanoids using a hybrid regression-fuzzy logic control approach in complex terrains

Abstract

In the current work, a hybrid navigational control architecture combining regression analysis with fuzzy logic control has been proposed for smooth and hassle-free motion planning of humanoids. In the proposed hybrid scheme, sensory information regarding obstacle distances are initially supplied to the regression controller, and an interim turning angle is obtained as the preliminary output based on the preloaded training pattern of the regression model. In the next phase, interim turning angle is again supplied to the fuzzy controller to generate the ultimate turning angle which eventually guides the humanoid to take a safe direction of turn while avoiding any obstacle present in the work environment. The working of the developed hybrid model is validated through simulation and real-time environments, and satisfactory results have been obtained from comparisons of selected navigational parameters along with a minimal percentage of deviations. To avoid possible chances of inter-collision for navigation of multiple humanoids in a common platform, a Petri-Net model has been integrated with the developed hybrid control scheme. Finally, the developed motion planning model is also assessed against another existing navigational controller, and significant performance enhancement is obtained.