Perception for detection and grasping
Document typePart of book or chapter of book
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder
ProjectAEROARMS - AErial RObotic system integrating multiple ARMS and advanced manipulation capabilities for inspection and maintenance (EC-H2020-644271)
This research presents a methodology for the detection of the crawler used in the project AEROARMS. The approach consisted on using a two-step progressive strategy, going from rough detection and tracking, for approximation maneuvers, to an accurate positioning step based on fiducial markers. Two different methods are explained for the first step, one using efficient image segmentation approach; and the second one using Deep Learning techniques to detect the center of the crawler. The fiducial markers are used for precise localization of the crawler in a similar way as explained in earlier chapters. The methods can run in real-time.
The final publication is available at link.springer.com
CitationGuerra, E. [et al.]. Perception for detection and grasping. A: "Aerial robotic manipulation: research, development and applications". Berlín: Springer, 2019, p. 275-283.