The use of unmanned aerial systems for industrial applications has evolved considerably in recent years. This paper presents an aerial system capable of perching autonomously on pipes for inspection and maintenance in industrial environments. The target pipe to perch on is detected using a visual algorithm based on a semantic convolutional neuronal network. The information from a color camera is used to segment the image. Then, the segmentation information is fused with a depth image to estimate the pipe's pose, so that the pose of the robot can be controlled relative to it. The aerial robot is equipped with a soft landing system that robustly attaches it to the pipe. The article presents the complete development of the system. Experimental results performed in outdoor environments are shown.

No abstract

Trying to optimize the design of aerial robotics systems, this work presents an optimized low-weight landing system for flapping-wing aerial robots. The design, based on the use of low-sized neodymium magnets, intends to provide that these aerial robots have the capability of landing in restricted areas by using the presented solution. This capacity will increase the application range of these robots. A study of this situation has been done to analyze the perching maneuver forces and evaluate the system. The solution presented is low-weight, lowsized, and also relatively inexpensive. Therefore, this solution may apply to most ornithopter robots. Design, analysis of the implied forces, development and experimental validation of the idea are presented in this work, demonstrating that the developed solution can overcome the ornithopter's payload limitation providing an efficient and reliable solution.

No abstract