Inertial-Aided Vision-Based Localization and Mapping in a Riverine Environment with Reflection Measurements
نویسندگان
چکیده
This paper presents an inertial-aided vision-based localization and mapping algorithm for an unmanned aerial vehicle (UAV) that can operate in a GPS-denied riverine environment. We take vision measurements from the features surrounding the river and their corresponding points reflected in the river. We apply a robot-centric mapping framework to let the uncertainty of the features be referenced to the UAV body frame and estimate the 3D positions of point features while estimating the location of the UAV. We demonstrate the localization and mapping results with sensors on our quadcopter UAV platform in the University of Illinois at Urbana Champaign Boneyard Creek. The UAV is equipped with a light weight monocular camera, an inertial measurement unit (IMU) which contains a magnetometer, an ultrasound altimeter, and an on-board computer. To our knowledge, we report the first result of performing localization and mapping by exploiting multiple views with reflections of features in a river-like environment.
منابع مشابه
Vision Based Estimation, Localization, and Mapping for Autonomous Vehicles
In this dissertation, we focus on developing simultaneous localization and mapping (SLAM) algorithms with a robot-centric estimation framework primarily using monocular vision sensors. A primary contribution of this work is to use a robot-centric mapping framework concurrently with a world-centric localization method. We exploit the differential equation of motion of the normalized pixel coordi...
متن کاملA Monocular Vision-aided Inertial Navigation System with Improved Numerical Stability
This paper develops a monocular vision-aided inertial navigation system based on the factored extended Kalman filter (EKF) proposed by Bierman and Thornton. The simultaneous localization and mapping (SLAM) algorithm measurement update and propagation steps are formulated in terms of the factored covariance matrix P = UDU, and a novel method for efficiently adding and removing features from the ...
متن کاملIndoor Localization Techniques based on Wireless Sensor Networks
Indoor localization is one of the most important problems in intelligent service robots, and home and office automation. For mobile robot navigation usually vision-based image processing techniques and dead-reckoning techniques based on inertial navigation systems have been used. These traditional technologies however have revealed many problems in actual applications. Vision-based image proces...
متن کاملMonocular Vision based Navigation in GPS-Denied Riverine Environments
This paper presents a new method to estimate the range and bearing of landmarks and solve the simultaneous localization and mapping (SLAM) problem. The proposed ranging and SLAM algorithms have application to a micro aerial vehicle (MAV) flying through riverine environments which occasionally involve heavy foliage and forest canopy. Monocular vision navigation has merits in MAV applications sin...
متن کاملEffects of Moving Landmark’s Speed on Multi-Robot Simultaneous Localization and Mapping in Dynamic Environments
Even when simultaneous localization and mapping (SLAM) solutions have been broadly developed, the vast majority of them relate to a single robot performing measurements in static environments. Researches show that the performance of SLAM algorithms deteriorates under dynamic environments. In this paper, a multi-robot simultaneous localization and mapping (MR-SLAM) system is implemented within a...
متن کامل