On-Line Navigational Problem of a Mobile Robot Using Genetic Algorithm

Abstract

  Manufacturing systems of the future foresee the use of intelligent vehicles, optimizing and navigating. The navigational problem is an important and challenging problem in the field of robotics. The robots often find themselves in a situation where they must find a trajectory to another position in their environment, subject to constraints posed by obstacles and the capabilities of the robot itself. On-line navigation is a set of algorithms that plans and executes a trajectory at the same time.         The system adopted in this research searches for a robot collision-free trajectory in a dynamic environment in which obstacles can move while the robot was moving toward the target. So, the robot must operate in real-time such that the system reacts to unexpected obstacles.       Genetic algorithms that have been used successfully in many search problems are used to solve the on-line navigation problem with less computational cost. The system uses genetic algorithm as a search method for an optimal trajectory.