Reconfigurable Grasp Planning Pipeline with Grasp Synthesis and Selection Applied to Picking Operations in Aerospace Factories

• Type: Article in International Scientific Journal
• Date: 2021

Authors

João Pedro de Souza (Author) FEUP; Carlos M. Costa (Author) Other; Luís F. Rocha (Author) FEUP; Rafael Arrais (Author) Other; António Paulo Moreira (Author) FEUP; E. J. Solteiro Pires (Author) Other; José Boaventura Cunha (Author) Other

Journal

Title: Robotics and Computer-Integrated Manufacturing

Vol. 67

Pages: 1-9

ISSN: 0736-5845

Publisher: Elsevier

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 2 Citations

Other information

Authenticus ID: P-00S-ECJ

DOI: 10.1016/j.rcim.2020.102032

Abstract (EN): Several approaches with interesting results have been proposed over the years for robot grasp planning. However, the industry suffers from the lack of an intuitive and reliable system able to automatically estimate grasp poses while also allowing the integration of grasp information from the accumulated knowledge of the end user. In the presented paper it is proposed a non-object-agnostic grasping pipeline motivated by picking use cases from the aerospace industry. The planning system extends the functionality of the simulated annealing optimization algorithm for allowing its application within an industrial use case. Therefore, this paper addresses the first step of the design of a reconfigurable and modular grasping pipeline. The key idea is the creation of an intuitive and functional grasping framework for being used by factory floor operators according to the task demands. This software pipeline is capable of generating grasp solutions in an offline phase, and later on, in the robot operation phase, can choose the best grasp pose by taking into consideration a set of heuristics that try to achieve a successful grasp while also requiring the least effort for the robotic arm. The results are presented in a simulated and a real factory environment, relying on a mobile platform developed for intralogistic tasks. With this architecture, new state-of-art methodologies can be integrated in the future for growing the grasping pipeline and make it more robust and applicable to a wider range of use cases.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 9