Autonomous robot retrieval system

摘要

Mobile robots are used for exploration and object manipulation in hazardous environments, but in many cases human presence is still required posing a risk to the health and safety of the human operator. In order to operate fully autonomously in a completely unknown environment a mobile robot is required to both create a map of its environment and localize itself; this is known as simultaneous localization and mapping (SLAM). SLAM is a very active area of robotics research but many robot platforms using this technique are relatively large and more sophisticated than the mobile robot featured in this work. This work proposes a small, low-cost mobile robot platform for the autonomous retrieval of an object in a completely unknown environment using OpenRatSLAM. The main contribution of this project will be the implementation of a SLAM algorithm used in conjunction with vision based object recognition on a Lego NXT mobile robot.