Journal
DRONES
Volume 6, Issue 11, Pages -Publisher
MDPI
DOI: 10.3390/drones6110369
Keywords
middleware; aerial robotics; computer vision; deep learning
Categories
Funding
- Programas de Actividades I+D en la Comunidad de Madrid [S2018/NMT-4331]
- Structural Funds of the EU
Ask authors/readers for more resources
Unmanned Aerial Vehicles (UAVs) are an integral part of various fields with numerous applications. This work introduces DroneWrapper, a middleware programming infrastructure built on the Robot Operating System (ROS) and implemented in Python, to simplify the development process of UAV applications for users with limited knowledge of aerial robotics. The infrastructure provides a user programming interface that abstracts complexities associated with the aircraft, allowing for the development of applications. Several drivers have been developed for different aerial platforms, and two applications, follow-color and follow-person, have been created to demonstrate the use of the infrastructure.
Unmanned Aerial Vehicles (UAVs) are part of our daily lives with a number of applications in diverse fields. On many occasions, developing these applications can be an arduous or even impossible task for users with a limited knowledge of aerial robotics. This work seeks to provide a middleware programming infrastructure that facilitates this type of process. The presented infrastructure, named DroneWrapper, offers the user the possibility of developing applications abstracting the user from the complexities associated with the aircraft through a simple user programming interface. DroneWrapper is built upon the de facto standard in robot programming, Robot Operating System (ROS), and it has been implemented in Python, following a modular design that facilitates the coupling of various drivers and allows the extension of the functionalities. Along with the infrastructure, several drivers have been developed for different aerial platforms, real and simulated. Two applications have been developed in order to exemplify the use of the infrastructure created: follow-color and follow-person. Both applications use techniques of computer vision, classic (image filtering) or modern (deep learning), to follow a specific-colored object or to follow a person. These two applications have been tested on different aerial platforms, including real and simulated, to validate the scope of the offered solution.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available