UDC 621.386.22
MATHEMATICAL SUPPORT FOR TASK DISTRIBUTION IN A HYBRID ENVIRONMENT OF NON-STATIONARY AUTONOMOUS OBJECTS
I. A. Chernoivanenko, post-graduate student, VGTU, Voronezh, Russia;
orcid.org/0009-0007-8510-4683, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
O. Ja. Kravets, Dr. in technical sciences, full professor, VSTU, Voronezh, Russia;
orcid.org/0000-0003-0420-6877, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The fast and efficient delivery of autonomous mobile objects (AMO) is becoming a vital and challenging task. To address this issue, a system for collaborative path planning and task distribution using unmanned aerial vehicles (UAV) and unmanned ground vehicles (UGV) is proposed. The system developed makes use of genetic algorithm (GA) to distribute tasks among multiple UAV and UGV and improved rapid random tree search algorithm (informed RRT*) to create obstacle-free trajectories. To further improve the efficiency of task execution and routing an evolutionary strategy for adapting covariance matrix (CMA-ES) is used. The proposed integration of these algorithms can be used to coordinate heterogeneous groups of AMO which significantly increases speed and efficiency of missions.
Key words: : hybrid environment, task distribution, path planning, coordination, autonomous mobile ob ject, genetic algorithm, covariance matrix adaptation, informed RRT* algorithm.