Abstract
A novel multi-sensor fusion indoor localization algorithm based on ArUco marker is designed in this paper. The proposed ArUco mapping algorithm can build and correct the map of markers online with Grubbs criterion and K-mean clustering, which avoids the map distortion due to lack of correction. Based on the conception of multi-sensor information fusion, the federated Kalman filter is utilized to synthesize the multi-source information from markers, optical flow, ultrasonic and the inertial sensor, which can obtain a continuous localization result and effectively reduce the position drift due to the long-term loss of markers in pure marker localization. The proposed algorithm can be easily implemented in a hardware of one Raspberry Pi Zero and two STM32 micro controllers produced by STMicroelectronics (Geneva, Switzerland). Thus, a small-size and low-cost marker-based localization system is presented. The experimental results show that the speed estimation result of the proposed system is better than Px4flow, and it has the centimeter accuracy of mapping and positioning. The presented system not only gives satisfying localization precision, but also has the potential to expand other sensors (such as visual odometry, ultra wideband (UWB) beacon and lidar) to further improve the localization performance. The proposed system can be reliably employed in Micro Aerial Vehicle (MAV) visual localization and robotics control.
Highlights
Global position system (GPS) is the main localization system of Micro Aerial Vehicle (MAV) in an outdoor environment, which has the advantages of low-cost and high-precision [1]
In the sensor registration layer, the proposed ArUco Mapping module uses an online mapping algorithm to realize the camera localization, the attitude estimation of MAV is based on the extended Kalman filter (EKF) [22], and the pyramid Lucas-Kanade (PLK) optical flow algorithm is utilized to estimate the translational speed of camera
The proposed system assumes that all the markers are located on the ground, the errors of Pitch and Roll are avoided via the static calibration
Summary
Global position system (GPS) is the main localization system of Micro Aerial Vehicle (MAV) in an outdoor environment, which has the advantages of low-cost and high-precision [1]. Several V-SLAM systems have been proposed in recent years such as Semi-direct visual odometry (SVO) [7] and oriented FAST and rotated brief SLAM (ORB-SLAM) [8] These two strategies have been applied in many MAV systems, which can realize precise localization based on the high-performance image process unit. The high cost of the motion capture system limits it only in adaptive industrial or laboratory environments; 2D markers cooperative localization technology is typically introduced in an environment where localization and navigation are needed for robots using low cost machine vision. It can provide accurate six-degrees-of-freedom information of the camera.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
