Global position determination and vehicle path estimation from a vision sensor for real-time video mosaicking and navigation

Abstract

This paper will describe our continuing advances in a joint research effort, undertaken by the Aerospace Robotics Laboratory (ARL) at Stanford University and the Monterey Bay Aquarium Research Institute (MBARI), to enable autonomous navigation from video for unmanned underwater vehicles. In particular, we have developed a real-time vision system for vehicle position sensing and sea-floor mapping. We will present the theoretical development of this work and associated simulation results. In addition, we will discuss the experimental verification of our techniques in the lab environment.