Goal Directed, State and Behavior based Navigation Algorithm for Smart “Robosofa” Furniture

  • G. Narvydas Kaunas University of Technology
  • R. Maskeliunas Kaunas University of Technology
  • V. Raudonis Kaunas University of Technology


This article presents a navigation system for the intelligent furniture of the “RoboSofa” project capable of navigation through a known environment and reaching the target in the shortest possible time. The target can be set by human being using various input modalities or remote control devices. The additional environmental scanning and image recognition (location markers) features were implemented in this solution. Our solution works by performing the data fusion gathered from sensors. This information is combined with a-priori knowledge of the environment to estimate “Robosofa” position and send commands to the actuators for movement. The main goals described were to solve one of the most important aspects of mobile robotics - to perform successful locomotion, obstacle avoidance task. The Khepera2 based mobile test platform controlled based on proposed control system effectively avoids obstacles and reliably reaches the target point. Ill. 4, bibl. 17 (in English; abstracts in English and Lithuanian).