Flexible Navigation: Finite state machine-based integrated navigation and control for ROS enabled robots

This paper describes the Flexible Navigation system that extends the ROS Navigation stack and compatible libraries to separate computation from decision making, and integrates the system with FlexBE — the Flexible Behavior Engine, which provides intuitive supervision with adjustable autonomy. Although the ROS Navigation plugin model offers some customization, many decisions are internal to move_base. In contrast, the Flexible Navigation system separates global planning from local planning and control, and uses a hierarchical finite state machine to coordinate behaviors. The Flexible Navigation system includes Python-based state implementations and ROS nodes derived from the move_base plugin model to provide compatibility with existing libraries as well as future extensibility. The paper concludes with complete system demonstrations in both simulation and hardware using the iRobot Create and Kobuki-based Turtlebot running under ROS Kinetic. The system supports multiple independent robots.