Robotic vehicles working in unknown environments require the ability to determine their location while learning about obstacles located around them. A classic approach to solving this problem is feature-based Simultaneous Localization and Mapping (SLAM) using an Extended Kalman Filter (EKF). In this paper, feature-based EKF SLAM is used to examine the feasibility of using a low cost vision-based sensor for performing SLAM in enclosed underwater environments. Classic acoustic-based range sensors suffer from poor performance in enclosed areas due to reflections, furthermore the relatively high cost of acoustic-based navigation sensors prevents their use on low cost underwater vehicles. To overcome these challenges, a custom vision-based range finder and a downward facing camera for the implementation of a standard feature tracking algorithm are used to perform EKF SLAM.

This content is only available via PDF.
You do not currently have access to this content.