AUTHOR=Yang Xinrui , Kahouadji Mouad , Lakhal  Othman , Merzouki  Rochdi TITLE=Integrated design of an aerial soft-continuum manipulator for predictive maintenance JOURNAL=Frontiers in Robotics and AI VOLUME=Volume 9 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2022.980800 DOI=10.3389/frobt.2022.980800 ISSN=2296-9144 ABSTRACT=This article presents an aerial robot used for predictive maintenance in the construction sector. The aerial robot is remotely controlled, allowing the localisation of cracks on wall surfaces and the adaptive deposit of the material for in-situ repairs. This aerial robot describes a fast intervention, allowing time and cost minimising of overhead repairs without the need of scaffolding. It is composed of a flying mobile platform and a soft continuum arm that allows to reach areas with difficult accessibility. Indeed, some constructions have complex geometries that present problems for an access using rigid mechanical arms. The aerial robot uses visual sensors, to automatically identify and localise cracks in walls, based on deep learning convolutional neural networks. A centerline representing the structural feature of the crack is computed. A kinematic controller is designed for a soft continuum arm, allowing it to make an accurate tracking and deposit of material along the crack, when the flying robot is kept stable in stationary position. A set of experiments was carried out on cracks located on flat and oblique surfaces, in order to evaluate the actual performances of the predictive maintenance mechatronic robot.