Vision Based Mapless Navigation System for Mobile Robots Using Scale Invariant Features and Optical Flow

Autonomous robots operating in an unknown and uncertain environment must be able to cope with dynamic changes to that environment. For a mobile robot to navigate successfully to a goal whilst avoiding obstacles is a challenging problem. The mapless navigation technique resembles human behaviours more than other approaches This paper presents a new mapless navigation strategy, based on a multi-scale variational approach and Scale Invariant Feature Transformation (SIFT) parameters, for mobile robot navigation using a single Internet based camera as a primary sensor. Real experiments to guide a Pioneer 3-DX mobile robot in a cluttered environment are presented, and the analysis of the results allows us to validate the proposed behavior based navigation strategy.