Intelligent navigation of a self-fabricated biped robot using a regression controller

With increasing demand towards use of biped robots in industrial automation and other related applications, navigation and path planning has emerged as one of the most challenging research topic over the last few decades. In this paper, a novel navigational controller is designed and implemented in a self-fabricated biped robot. After fabricating the biped equipped with a large set of sensors, a regression controller is implemented in it for obstacle avoidance and path optimization purpose. The obstacle distances detected by the sensory network of the biped are fed as input parameters to the regression controller and the output obtained from the controller is the necessary heading angle required to avoid the obstacles present randomly in the environment. The biped is tested in a simulation environment for obstacle avoidance and target following behaviour. Along with that, to validate the simulation results, a real-time experimental set up is designed under laboratory conditions. The results obtained from both the environments are compared in terms of navigational parameters and a good agreement between them is observed. Being a relatively new area of research, the navigation of bipeds can serve as a pioneer act towards industrial automation.