Skeleton-Based Visual Servoing in Unknown Environments

Abstract

The generalized Voronoi diagram (GVD) is a powerful environment representation that defines a set of paths at maximal distance from the obstacles. Many works implicitly use this property to define safe navigation strategies for a mobile robot, but, in practice, only a few explicitly extracts in real time the GVD from the robot perception. In this paper, a real-time skeleton-based visual servoing approach is proposed for safe autonomous navigation of mobile robots in unknown structured environments. The control is based on an approximation of the local GVD using the delta medial axis, a fast and robust skeletonization algorithm. The latter produces a filtered skeleton of the freespace surrounding the robot using a pruning parameter that takes into account the robot size. A unified virtual perception frame is also introduced to project the navigable freespace obtained by possibly multiple sensors and observations. After freespace skeletonization and GVD approximation, a visual servoing control is designed and studied to ensure autonomous robot navigation along the extracted GVD branches. The approach is first tested using a simulated environment. Then, an experimental validation is carried out on a real differential wheelchair allowing the system to navigate safely and autonomously without any human intervention. Static and dynamic environment scenarios are studied. The method is immediately generalizable to any differential drive wheeled robot.