Roman Fedorenko

Geesara Prathap, Roman Fedorenko, Alexandr Klimchik

We propose a novel filter for segmenting the regions of interest from LiDAR 3D point cloud for multirotor aerial vehicles. It is specially targeted for real-time applications and works on sparse LiDAR point clouds without preliminary mapping. We use this filter as a crucial component of fast obstacle avoidance system for agriculture drone operating at low altitude. As the first step, each point cloud is transformed into a depth image and then identify places near to the vehicle (local maxima) by locating areas with high pixel densities. Afterwards, we merge the original depth image with identified locations after maximizing intensities of pixels in which local maxima were obtained. Next step is to calculate the range angle image that represents angles between two consecutive laser beams based on the improved depth image. Once the corresponding range angle image is constructed, smoothing is applied to reduce the noise. Finally, we find out connected components within the improved depth image while incorporating smoothed range angle image. This allows separating the regions of interest. The filter has been tested on various simulated environments as well as an actual drone and provides real-time performance. We make our source code, dataset available at https://github.com/GPrathap/hagen.git and real world experiment result can be found on the following link: https://www.youtube.com/watch?v=iHd_ZkhKPjc available online.

Geesara Kulathunga, Dmitry Devitt, Roman Fedorenko et al.

We explore path planning followed by kinodynamic smoothing while ensuring the vehicle dynamics feasibility for MAVs. We have chosen a geometrically based motion planning technique \textquotedblleft RRT*\textquotedblright\; for this purpose. In the proposed technique, we modified original RRT* introducing an adaptive search space and a steering function which help to increase the consistency of the planner. Moreover, we propose multiple RRT* which generates a set of desired paths, provided that the optimal path is selected among them. Then, apply kinodynamic smoothing, which will result in dynamically feasible as well as obstacle-free path. Thereafter, a b spline-based trajectory is generated to maneuver vehicle autonomously in unknown environments. Finally, we have tested the proposed technique in various simulated environments.

Geesara Kulathunga, Roman Fedorenko, Sergey Kopylov et al.

Real-time long-range local planning is a challenging task, especially in the presence of dynamics obstacles. We propose a complete system which is capable of performing the local replanning in real-time. Desired trajectory is needed in the system initialization phase; system starts initializing sub-components of the system including point cloud processor, trajectory estimator and planner. Afterwards, the multi-rotary aerial vehicle starts moving on the given trajectory. When it detects obstacles, it replans the trajectory from the current pose to pre-defined distance incorporating the desired trajectory. Point cloud processor is employed to identify the closest obstacles around the vehicle. For replanning, Rapidly-exploring Random Trees (RRT*) is used with two modifications which allow planning the trajectory in milliseconds scales. Once we replanned the desired path, velocity components(x,y and z) and yaw rate are calculated. Those values are sent to the controller at a constant frequency to maneuver the vehicle autonomously. Finally, we have evaluated each of the components separately and tested the complete system in the simulated and real environments.

Adelya Sabirova, Maksim Rassabin, Roman Fedorenko et al.

The paper presents the study and implementation of the ground detection methodology with filtration and removal of forest points from LiDAR-based 3D point cloud using the Cloth Simulation Filtering (CSF) algorithm. The methodology allows to recover a terrestrial relief and create a landscape map of a forestry region. As the proof-of-concept, we provided the outdoor flight experiment, launching a hexacopter under a mixed forestry region with sharp ground changes nearby Innopolis city (Russia), which demonstrated the encouraging results for both ground detection and methodology robustness.