Efficient and adaptive lidar–visual–inertial odometry for agricultural unmanned ground vehicle

The accuracy of agricultural unmanned ground vehicles’ localization directly affects the their navigation. However, due to changeable environment and fewer features in scene, it is challenging for these vehicles localize precisely global positioning system-denied areas with a single sensor. In this article, we present an efficient adaptive sensor-fusion odometry framework based on simultaneous mapping handle problems without assistance system. leverages three kinds sub-odometry (lidar odometry, visual inertial odometry) automatically combines them depending provide accurate pose estimation real time. combination implemented by trading off robustness estimation. efficiency adaptability are mainly reflected novel surfel-based iterative closest point method lidar propose, which utilizes surfel radius range initialization improve different environments. We test our system various working zones some other open data sets, results prove that proposed shows better performance accuracy, robustness, compared state-of-art methods.