Abstract

Abstract
In this paper, we present a comparison between the older DSTV file format and the newer version of the IFC standard, dedicating special attention of its impact in the robotization of welding and cutting processes in the steel structure fabrication industry. In the last decade, we have seen in this industry a significant increase in the request for automation. These new requirements are imposed by a market focused on the productivity enhancement through automation. Because of this paradigm change, the information structure and workflow provided by the DSTV format needed to be revised, namely the one related with the plan and management of steel fabrication processes. Therefore, with this work we enhance the importance of the increased digitalization of information that the newer version of the IFC standard provide, by showing how this information can be used to develop advanced robotic cells. More in detail, we will focus on the automatic generation of robot welding and cutting trajectories, and in the automatic part assembly planning during components fabrications. Besides these advantages, as this information is normally described having as base a perfect CAD model of the metallic structure, the resultant robot trajectories will have some dimensional error when fitted with the real physical component. Hence, we also present some automatic approaches based on a laser scanner and simple heuristics to overcome this limitations.

Abstract

Abstract
Self-localization of mobile robots in the environment is one of the most fundamental problems in the robotics field. It is a complex and challenging problem due to the high requirements of autonomous mobile vehicles, particularly with regard to algorithms accuracy, robustness and computational efficiency. In this paper we present the comparison of two of the most used map-matching algorithm, which are the Iterative Closest Point and the Perfect Match. This category of algorithms are normally applied in localization based on natural landmarks. They were compared using an extensive collection of metrics, such as accuracy, computational efficiency, convergence speed, maximum admissible initialization error and robustness to outliers in the robots sensors data. The test results were performed in both simulated and real world environments.

Abstract
This letter presents a novel architecture for evaluating the success of picking operations that are executed by industrial robots. It is formed by a cascade of machine learning algorithms (kNN and SVM) and uses information obtained by a 6 axis force/torque sensor and, if available, information from the built-in sensors of the robotic gripper. Beyond measuring the success or failure of the entire operation, this architecture makes it possible to detect in real-time when an object is slipping during the picking. Therefore, force and torque signatures are collected during the picking movement of the robot, which is decomposed into five different stages that allows to characterize distinct levels of success over time. Several trials were performed using an industrial robot with two different grippers for picking a long and flexible object. The experiments demonstrate the reliability of the proposed approach under different picking scenarios since, it obtained a testing performance (in terms of accuracy) up to 99.5% of successful identification of the result of the picking operations, considering an universe of 400 attempts. © 2016 IEEE.