A MULTI-CAMERA SYSTEM FOR MOBILE ROBOT LOCALIZATION

摘要

This paper presents a multi-camera system for mobile robot localization in indoor environment. The system consists of wall-mounted cameras with LED illuminator and a processing unit. The processing unit is a PC-cluster developed in-house. It consists of a two-computer system connected by PCI-to-PCI interface board with fiber-optic cable. The camera system provides robot pose information, position and orientation, in real-time with respect to the global reference frame. Three artificial landmarks, which are spherical reflective markers, are mounted on the robot to reduce complexity in localization and tracking. The Kalman filter tracking algorithm is applied to estimate markers position. With this estimation, the system bandwidth and robustness are improved. The robot is controlled by sending command via wireless Ethernet connection. By using measurements from the camera system, experiments on robot motion control with specified trajectories show the effectiveness of our developed system. In the near future, the system can use information from robot’s onboard sensors such as laser range finder and sonar for development of obstacle detection and autonomous navigation.