摘要：Many mobile robotics applications, especially in industrial environments, require the robot to perform safe navigation and then reach the goal with a high precision. In this research work, the objective is to analyze the appropriateness of autonomous natural navigation strategies for mobile manipulation tasks. The system must position itself in a realistic map, follow a path closely and then achieve an accurate positioning in the destination point in order to be able to perform the manipulation, inspection or pick task efficiently. Autonomous navigation is not able to fulfill the accuracy required by some of the jobs so that a second positioning system using vision is proposed in this paper. The experiments show that localization systems have, on average, an error greater than a decimetre and how an additional positioning system can reduce it to a few millimetres.
