Extended Dijkstra Algorithm in Path Planning for Vision Based Patrol Robot

In the recent years, Global positioning system (GPS) has worked with Global Navigation Satellite System (GNSS) to provide higher accuracy quality of locating a device. However, this localization service doesn't reach indoor facility. For an indoor type vision based patrol robot, the problem would encounter in path planning that allows the patrol robot to find the optimum path to reach the destination and return to home position. In this paper, an extended Dijkstra algorithm is proposed for path planning to the vision based patrol robot for surveillance purposes. This design used visual type sensor, range sensor and IMU system to instantaneously update the map data according to the current path of the vision robot and apply the path planning feature to perform obstacle avoidance and re-routing process based on the obstacle type faced by the robot. The result shown by this approach indeed capable to complete multiple cycles of testing with positive result.