Robert Milijaš

• Master of Science
• University of Zagreb

This paper addresses the issues of unmanned aerial vehicle (UAV) indoor navigation, specifically in areas where GPS and magnetometer sensor measurements are unavailable or unreliable. The proposed solution is to use an error state extended Kalman filter (ES -EKF) in the context of multi-sensor fusion. Its implementation is adapted to fuse measureme...

This paper addresses the issues of unmannedaerial vehicle (UAV) indoor navigation, specifically in areaswhere GPS and magnetometer sensor measurements are una-vailable or unreliable. The proposed solution is to use anerror state extended Kalman filter (ES -EKF) in the contextof multi-sensor fusion. Its implementation is adapted to fusemeasurements...

This paper describes an application of the Cartographer graph SLAM stack as a pose sensor in a UAV feedback control loop, with certain application-specific changes in the SLAM stack such as smoothing of the optimized pose. Pose estimation is performed by fusing 3D LiDAR/IMU-based proprioception with GPS position measurements by means of pose graph...

This paper investigates the use of LiDAR SLAM as a pose feedback for autonomous flight. Cartographer, LOAM and hdl graph SLAM are tested for this role. They are first compared offline on a series of datasets to see if they are capable of producing high-quality pose estimations in agile and long-range flight scenarios. The second stage of testing co...

In this paper we use the underlying pose graph structure of graph SLAM to allow the user to inspect and intervene into the Simultaneous Localization and Mapping (SLAM) process. With post-processing the map by inserting custom constraints into the optimization problem, the user can improve the quality of the map obtained as the final SLAM result. We...