Cookies Policy
We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out More
Close
  • Menu
About

About

I'm a fast learner software engineer, always looking to expand my knowledge in new technologies and with great interest in science (computer science and engineering, robotics, biotechnology, space exploration, among others).

My main research areas are augmented reality, 3D perception, computer vision, safety critical systems, assembly automation, localization and mapping of autonomous vehicles among many others within the industrial and mobile robotics fields.

Interest
Topics
Details

Details

001
Publications

2018

Automatic generation of disassembly sequences and exploded views from solidworks symbolic geometric relationships

Authors
Costa, CM; Veiga, G; Sousa, A; Rocha, LF; Oliveira, EC; Cardoso, HL; Thomas, U;

Publication
2018 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2018, Torres Vedras, Portugal, April 25-27, 2018

Abstract

2017

Evaluation of Stanford NER for extraction of assembly information from instruction manuals

Authors
Costa, CM; Veiga, G; Sousa, A; Nunes, S;

Publication
2017 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2017, Coimbra, Portugal, April 26-28, 2017

Abstract

2017

Beam for the steel fabrication industry robotic systems

Authors
Rocha, LF; Tavares, P; Malaca, P; Costa, C; Silva, J; Veiga, G;

Publication
ISARC 2017 - Proceedings of the 34th International Symposium on Automation and Robotics in Construction

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.

2017

Pose Invariant Object Recognition Using a Bag of Words Approach

Authors
Costa, CM; Sousa, A; Veiga, G;

Publication
ROBOT 2017: Third Iberian Robotics Conference - Advances in Intelligent Systems and Computing

Abstract

2016

2D Cloud Template Matching - A comparison between Iterative Closest Point and Perfect Match

Authors
Sobreira, H; Rocha, L; Costa, C; Lima, J; Costa, P; Paulo Moreira, AP;

Publication
2016 IEEE INTERNATIONAL CONFERENCE ON AUTONOMOUS ROBOT SYSTEMS AND COMPETITIONS (ICARSC 2016)

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.