Programming Khepera II robot for autonomous navigation and exploration using the hybrid architecture

Abstract

This project investigated the feasibility of programming the Khepera II robot for autonomous navigation and exploration using the hybrid robot architecture. At the deliberative layer of the system, the D* Lite algorithm was implemented to find the shortest path between a starting and a destination state, and to perform efficient re-planning during exploration. At the reactive layer, instructions along the shortest path are executed one instruction at a time. Each instruction is executed by following a behavior until a terminator state is reached. Robot exploration is activated when an unexpected world situation is detected along the navigation path. This information is fed to the deliberative layer where the map is updated, and the shortest path was recomputed. A separate visualization module was built to monitor the progress of the navigation and exploration progress. The tool provides a real time feed for the state of robot navigation progress.