Robotic tasks such as navigation and path planning can be greatly enhanced by a vision system capable of providing depth perception from fast and accurate 3D surface reconstruction. Focused on robotic welding tasks we present a comparative analysis of a novel mathematical formulation for 3D surface reconstruction and discuss image processing requirements for reliable detection of patterns in the image. Models are presented for a parallel and angled configurations of light source and image sensor. It is shown that the parallel arrangement requires 35% fewer arithmetic operations to compute a point cloud in 3D being thus more appropriate for real-time applications. Experiments show that the technique is appropriate to scan a variety of surfaces and, in particular, the intended metallic parts for robotic welding tasks.
Abstract-MARWIN is an intelligent system for automatic robotic welding tasks. It extracts welding parameters and calculates robot trajectories directly from CAD models which are then verified by real-time 3D scanning and registration. The focus of this paper is on describing a novel mathematical formulation for structured light scanning together with the design and testing of the 3D vision system and show how such technology can be exploited within an anthropomatic context. The expected end result is a 3D assisted user-centred robot environment in which a task is specified by the user by simply confirming (and/or adjusting) MARWIN's suggested parameters and welding sequences. I. INTRODUCTIONWelding by robots has experienced a vigorous upsurge in recent years with an estimated 25% of all industrial robots being used in connection to welding tasks [1]. The challenge is to develop flexible automation systems that can be set up quickly and can be switched over to another product line while maintaining quality and profitability. Small and medium enterprises (SMEs) normally do not have the resources to invest in technology requiring extensive human training. The MARWIN project offers a solution to humanrobot interaction by developing a cognitive welding robot where welding tasks and parameters are intuitively selected by the end-user directly from a library of CAD models. Robot trajectories are then automatically calculated from the CAD models and validated through fast 3D scanning of the welding scene. The role of the user is limited to high level specification of the welding task and to the confirmation and/or changing of welding parameters and sequences as suggested by MARWIN. This paper focuses on describing the MARWIN 3D vision system and a novel mathematical formulation for fast 3D scanning using structured light, and on methods to register scanned surfaces to CAD models and estimation of registration errors. The main idea behind the 3D vision system is that, if the scanned model matches the description of their CAD counterparts, then welding can proceed as calculated
Abstract. This paper proposes a new methodology for robotic offline programming (OLP) addressing the issue of automatic program generation directly from 3D CAD models and verification through online 3D reconstruction. Limitations of current OLP include manufacturing tolerances between CAD and workpieces and inaccuracies in workpiece placement and modelled work cell. These issues are addressed and demonstrated through surface scanning, registration, and global and local error estimation. The method allows the robot to adjust the welding path designed from the CAD model to the actual workpiece. Alternatively, for non-repetitive tasks and where a CAD model is not available, it is possible to interactively define the path online over the scanned surface.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.