DIMOS TZOUMANIKAS
For a complete publication list have a look on the Publications page as well as my Google Scholar profile.
Aerial Manipulation Using Hybrid Force and Position NMPC Applied to Aerial Writing
Tzoumanikas D., Graule F., Yan Q., Shah D., Popovic M., and Leutenegger S. (2020).
Robotics: Science and Systems (RSS). [PDF]
Aerial manipulation aims at combining the maneuverability of aerial vehicles with the manipulation capabilities of robotic arms. This however, comes at the cost of increased control complexity due to the coupling of the dynamics of the two systems. In order to address this, we propose a Nonlinear Model Predictive Controller (NMPC) which relies on a hybrid control model for the combined system which incorporates interaction forces acting on the end effector. We showcase the performance of our method in "aerial writing" tasks as an example application requiring precision.
Nonlinear MPC with Motor Failure Identification and Recovery for Safe and Aggressive Multicopter Flight
Tzoumanikas D., Yan Q., and Leutenegger S. (2020).
International Conference on Robotics and Automation (ICRA). [PDF]
Safe and precise reference tracking is a crucial characteristic of Micro Aerial Vehicles that have to operate under the influence of external disturbances in cluttered environments. In this paper, we present a NMPC that exploits the fully physics based nonlinear dynamics of the system. We furthermore show how the moment and thrust control inputs can be transformed into feasible actuator commands. In order to guarantee safe operation despite potential loss of a motor under which we show our system keeps operating safely, we developed an EKF based motor failure identification algorithm. We verify the effectiveness of the developed pipeline in flight experiments with and without motor failures.
InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset
Li W., Saeedi S., McCormac J., Clark R., Tzoumanikas D., Ye Q., Huang Y., Tang R., and Leutenegger S. (2018).
British Machine Vision Conference (BMVC). [PDF]
In this work we present a dataset with the aim of providing a higher degree of photo-realism, larger scale, more variability as well as serving a wider range of purposes compared to existing datasets. Our dataset leverages the availability of millions of professional interior designs and millions of production-level furniture and object assets – all coming with fine geometric details and high-resolution texture. We render high-resolution and high frame-rate video sequences following realistic trajectories while supporting various camera types as well as providing inertial measurements. To showcase the usability and uniqueness of our dataset, we show benchmarking results of both sparse and dense SLAM algorithms. Access to the full dataset is available here.
MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM
Xu B., Li W., Tzoumanikas D., Bloesch M., Davison A., and Leutenegger S. (2019).
International Conference on Robotics and Automation (ICRA). [PDF]
In this work we propose a new multi-instance dynamic RGBD SLAM system using an object-level octree-based volumetric representation. It can provide robust camera tracking in dynamic environments and at the same time, estimate geometric, semantic, and motion properties for arbitrary objects in the scene. For each incoming frame, we perform instance segmentation to detect objects and refine mask boundaries using geometric and motion information. Meanwhile, we estimate the pose of each existing moving object using an object-oriented tracking method and robustly track the camera pose against the static scene. Based on the estimated camera pose and object poses, we associate segmented masks with existing models and incrementally fuse corresponding colour, depth, semantic, and foreground object probabilities into each object model. In contrast to existing approaches, our system is able to generate an object-level dynamic volumetric map from a single RGB-D camera, which can be used directly for robotic tasks.
Fully autonomous MAV flight and landing on a moving target using visual-inertial estimation and model-predictive control
Tzoumanikas D., Li W., Grimm M., Zhang K., Kovac M., and Leutenegger S. (2019).
Journal of Field Robotics. [PDF]
In this work, we present the hardware components of the Micro Air Vehicle (MAV) we built with off the self components alongside the designed algorithms that were developed for the purposes of the MBZIRC competition. We tackle the challenge of landing on a moving target by adopting a generic approach, rather than following one that is tailored to the MBZIRC Challenge One setup, enabling easy adaptation to a wider range of applications and targets, even indoors, since we do not rely on availability of GPS. We evaluate our system in an uncontrolled outdoor environment where our MAV successfully and consistently lands on a target moving at a speed of up to 5.0 m/s.