Biologically-inspired visual landmark learning for mobile robots

This paper presents a biologically-inspired method for selecting visual landmarks which are suitable for navigating within not pre-engineered environments. A landmark is a region of the goal image which is chosen according to its reliability measured through a phase called Turn Back and Look (TBL). This mimics the learning behavior of some social insects. The TBL phase affects the conservativeness of the vector field thus allowing us to compute the visual potential function which drives the navigation to the goal. Furthermore, the conservativeness of the navigation vector field allows us to assess if the learning phase has produced good landmarks. The presence of a potential function means that classical control theory principles based on the Lyapunov functions can be applied to assess the robustness of the navigation strategy. Results of experiments using a Nomad200 mobile robot and a color camera are presented throughout the paper.