Visual odometry on the Mars exploration rovers - a tool to ensure accurate driving and science imaging

作者：Cheng Yang, Mark Maimone, Larry Matthies · 发表于：IEEE Robotics & Automation Magazine · 年份：2006 · DOI：10.1109/mra.2006.1638016 · 被引用次数：145 · 研究领域：Robotics and Sensor-Based Localization、Robotic Path Planning Algorithms、Advanced Vision and Imaging

In this paper, visual odometry is presented as an approach to position estimation to find features in a stereo image pair and track them from one frame to the next. Visual odometry has been a highly effective tool for maintaining vehicle safety while driving near obstacles on slopes, achieving difficult drive approaches in fewer sols, and ensuring accurate science imaging. Although it requires active pointing by human drivers in feature-poor terrain, the improved position knowledge enables more autonomous capability and better science return during planetary operations.