Experimental Results of an Indoor Navigation Method Based on Bionic Behaviors

The present proposal is inspired by bionics; in this way, local path planning is developed by using the perception system under a deliberative strategy. Indoor global navigation is attained by solving local goals within an occupancy grid framework. Path-planning is computed at each perception step by using the on-robot monocular perception system and considering the detected obstacles. In this context, artificial potential fields are used for attracting the robot towards the desired coordinates. Trajectory tracking is based on reactive behaviors that are performed by using local model predictive control techniques. Global navigation is done by considering a set of local points that have to be reached using reactive behaviors. Dead reckoning problems are set to zero by selecting natural structured landmarks as local passage points that act as local attraction fields towards the goal. The research work is completed with a set of local experiments developed on a wheeled mobile robot.