Project type:

  • Robotics
  • Computational Geometry
  • AI Algorithms
  • PhD Thesis

  • July 2015 - July 2018
Used technologies:


A qt Triangulation and Planning (qTnP) architecture

This project, along with the PhD Thesis in the context of the MarineUAS EU Horizon 2020 project, focuses on a high-level architecture for heterogeneous aerial, fixed wing teams of robots, which operate in complex coastal areas.

Initially deals with complex coastal decomposition in relation with a vehicles' on-board sensor. Then, it proposes a novel algorithmic approach of partitioning any given complex area, for an arbitrary number of Unmanned Aerial Vehicles (UAV). This partitioning schema, respects the relative flight autonomy capabilities of the robots, providing them a corresponding region of interest.

In addition, a set of algorithms is proposed for obtaining coverage waypoint plans and are designed to afford the non-holonomic nature of fixed-wing vehicles and the restrictions their dynamics impose. Finally, a variation of a well-known path tracking algorithm is proposed, in order to further reduce the flight error of waypoint following. This study is conducted in a marine studies test case of buoy information extraction.

The Architecture

The modular architecture permits the individual modules to be added in any realisation and experimental framework. Moreover, it permits its use on a distributed manner for an arbitrary number of UAVs. Local and global information are shared and the workload is divided among the actors.

The Results

The developed algorithms have been deployed on-board each light weight, low-cost fixed wing platform. The results from the conducted experiments and simulations showed that this is a computational inexpensive method for complete coverage of complex areas.
The Thesis can be found in the links section whereas the code of the ROS nodes can be found in my GitHub page.

This portfolio uses XHTML, css and the foundation framework