Mojtaba Karimi, M.Sc.
Chair of Media Technology (Prof. Steinbach)
- Phone: +49 (89) 289 - 23509
- Room: 0509.02.916
Mojtaba Karimi (Leox) studied Computer Engineering and Information Technology and received his Bachelor of Science (B.Sc.) degree in 2012. In 2014, he graduated with the degree "Master of Science (M.Sc.)" in Robotics Engineering from Amirkabir University of Technology (Tehran Polytechnic), Tehran (Iran). After graduation, Leox worked as a robotics engineer in industry and, later in 2016, he worked in the Center for Advanced Systems & Technologies (CAST) at Tehran University, as a research assistant. In January 2017, he joined the Chair of Media Technology (LMT) at the Technical University of Munich (Germany), as a member of the research staff. He received the STARTUP WORLD – cutting-edge product award at AUTOMATICA 2016 for designing the "Olive Smart Suitcase". His research interests comprise sensor fusion, lidar-inertial localization, and telepresence systems as well as the extensive field of motion control systems.
2016 - 2017: Telepresence and Teleoperation Systems (MAVI):
One of the goals in telepresence systems is to be able to perform daily tasks remotely. A key requirement for this is a robust and reliable mobile robotic platform. Ideally, such a platform should support 360◦ stereoscopic vision and semiautonomous telemanipulation ability. In this research, we designed a telepresence mobile robot platform called MAVI. MAVI is a low-cost and robust but extendable platform for research and educational purpose, especially for machine vision and human interaction in telepresence setups. MAVI platform offers a balance between modularity, capabilities, accessibility, cost and an open source software framework. With a range of different sensors such as Inertial Measurement Unit (IMU), 360◦ laser rangefinder, and force sensors along with smart actuation in omnidirectional holonomic locomotion, high load cylindrical manipulator, and actuated stereoscopic Pan-Tilt-Roll Unit (PTRU), not only MAVI can provide the basic feedbacks from its surroundings, but also can interact within the remote environment in multiple ways. The software architecture of MAVI is based on the Robot Operating System (ROS) which allows for the easy integration of the state-of-the-art software packages. In this research, we used state-of-the-art methods for low-delay sensory data transmission over VBR networks and remote visual-inertial localization systems as well as virtual force feedback for remote mobile manipulation.
 M. Karimi, T. Aykut, and E. Steinbach, “Mavi: A research platform for telepresence and teleoperation,” Robotics, vol. abs/1805.09447, 2018.
 T. Aykut, M. Karimi, C. Burgmair, A. Finkenzeller, C. Bachhuber, E. Steinbach, "Delay Compensation for a Telepresence System with 3D 360° Vision based on Deep Head Motion Prediction and Dynamic FoV Adaptation", IEEE Robotics and Automation Letters (with IROS presentation option), July 2018
Skewed-redundant Hall-effect Magnetic Sensor Fusion for Perturbation-free Indoor Heading Estimation
Robust attitude and heading estimation with respect to a known reference is an essential component for indoor localization in robotic applications. Affordable Attitude and Heading Reference Systems (AHRS) are typically using 9-axis solid-state MEMS-based sensors. The accuracy of heading estimation on such a system depends on the Earth's magnetic field measurement accuracy. The measurement of the Earth's magnetic field using MEMS-based magnetometer sensors in an indoor environment, however, is strongly affected by external magnetic perturbations. We investigate a novel approach for robust indoor heading estimation based on skewed-redundant magnetometer fusion. A tetrahedron platform based on Hall-effect magnetic sensors is designed to determine the Earth's magnetic field with the ability to compensate for external magnetic field anomalies. Additionally, a correlation-based fusion technique is introduced for perturbation mitigation using the proposed skewed-redundant configuration. Our fusion technique uses a correlation coefficient analysis for determining the distorted axis and extracts the perturbation-free Earth's magnetic field vector from the redundant magnetic measurement. Our experimental results show that the proposed scheme can successfully mitigate the anomalies in the magnetic field measurement and estimates the Earth's true magnetic field.
 M. Karimi, E. Babaians, M. Oelsch, T. Aykut, and E. Steinbach. "Skewed-redundant Hall-effect Magnetic Sensor Fusion for Perturbation-free Indoor Heading Estimation." IEEE- IRC (2020).
2018 - Current: Attentive Lidar-Inertial Localization and Mapping for Drone-based Indoor Inspection
Since January 2018 Leox works in the project "KI-Inspektionsdrohne". The goal of this project is to design and develop an autonomous drone for airplane inspection inside a hangar. One of the challenges in this project is the indoor precise localization of the inspection drone for autonomous navigation. The UAV is equipped with a Lidar, high-resolution camera, and 9-DoF AHRS which can be utilized for the 6D position estimation. However, the processing unit and the payload of the drone is limited.
The multidimensional sensory data is computationally expensive for localization algorithms in autonomous navigation for drones. Research shows that not all sensory data are equivalently important during the entire process of SLAM to perform a reliable output. The attention control scheme is one of the effective ways to filter out the highly valuable sensory data for such a system. The predictive attention model, for instance, can help us to improve the result of the sensor fusion algorithms by concentrating on the most valuable sensory data based on the dynamic of the vehicle motion or the semantic understanding of the environment. The aim of this research is to investigate the state-of-the-art attention control models that can be adapted for the multidimensional sensory data acquisition system and compare them from different modalities. In addition, we investigate the different approaches for Lidar-Inertial SLAM for maximizing the latency of the pose estimation for real-time navigation applications.