002866085 001__ 2866085
002866085 003__ SzGeCERN
002866085 005__ 20240307151914.0
002866085 0247_ $$2DOI$$9MDPI$$a10.3390/s23115344
002866085 0248_ $$aoai:cds.cern.ch:2866085$$pcerncds:FULLTEXT$$pcerncds:CERN:FULLTEXT$$pcerncds:CERN
002866085 035__ $$9https://inspirehep.net/api/oai2d$$aoai:inspirehep.net:2671552$$d2023-07-26T12:18:32Z$$h2023-07-27T05:22:00Z$$mmarcxml
002866085 035__ $$9Inspire$$a2671552
002866085 041__ $$aeng
002866085 100__ $$aAlmagro, Carlos Veiga$$uCERN$$uJaume I U., Castellon$$vInteractive Robotic Systems Lab, Jaume I University of Castellón, 12006 Castellón de la Plana, Spain
002866085 245__ $$9MDPI$$a(MARGOT) Monocular Camera-Based Robot Grasping Strategy for Metallic Objects
002866085 260__ $$c2023
002866085 300__ $$a27 p
002866085 520__ $$9MDPI$$aRobotic handling of objects is not always a trivial assignment, even in teleoperation where, in most cases, this might lead to stressful labor for operators. To reduce the task difficulty, supervised motions could be performed in safe scenarios to reduce the workload in these non-critical steps by using machine learning and computer vision techniques. This paper describes a novel grasping strategy based on a groundbreaking geometrical analysis which extracts diametrically opposite points taking into account surface smoothing (even those target objects that might conform highly complex shapes) to guarantee the uniformity of the grasping. It uses a monocular camera, as we are often facing space restrictions that generate the need to use laparoscopic cameras integrated in the tools, to recognize and isolate targets from the background, estimating their spatial coordinates and providing the best possible stable grasping points for both feature and featureless objects. It copes with reflections and shadows produced by light sources (which require extra effort to extract their geometrical properties) in unstructured facilities such as nuclear power plants or particle accelerators on scientific equipment. Based on the experimental results, utilizing a specialized dataset improved the detection of metallic objects in low-contrast environments, resulting in the successful application of the algorithm with error rates in the scale of millimeters in the majority of repeatability and accuracy tests.
002866085 540__ $$3publication$$aCC-BY-4.0$$bMDPI$$fOther$$uhttps://creativecommons.org/licenses/by/4.0/
002866085 542__ $$dthe authors$$g2023
002866085 65017 $$2SzGeCERN$$aDetectors and Experimental Techniques
002866085 6531_ $$9author$$acomputer vision
002866085 6531_ $$9author$$atelerobotics
002866085 6531_ $$9author$$agrasping determination
002866085 690C_ $$aARTICLE
002866085 690C_ $$aCERN
002866085 700__ $$aOrrego, Renato Andrés Muñoz$$uCERN$$uMadrid U.$$vCentro de Automatica y Robotica (CAR) UPM-CSIC, Universidad Politecnica de Madrid, 28006 Madrid, Spain
002866085 700__ $$aGonzález, Álvaro García$$uCERN
002866085 700__ $$aMatheson, Eloise$$uCERN
002866085 700__ $$aPrades, Raúl Marín$$uJaume I U., Castellon
002866085 700__ $$aDi Castro, Mario$$uCERN
002866085 700__ $$aPérez, Manuel Ferre$$uMadrid U.
002866085 773__ $$c5344$$n11$$pSensors$$v23$$y2023
002866085 8564_ $$82466004$$s5263427$$uhttp://cds.cern.ch/record/2866085/files/document.pdf$$yFulltext
002866085 960__ $$a13
002866085 980__ $$aARTICLE