Carlos Angel Iglesias Fernandez

A Machine Learning Approach to Pedestrian Detection for Autonomous Vehicles Using High-Definition 3D Range Data

This article describes an automated sensor-based system to detect pedestrians in an autonomous vehicle application. Although the vehicle is equipped with a broad set of sensors, the article focuses on the processing of the information generated by a Velodyne HDL-64E LIDAR sensor. The cloud of points generated by the sensor (more than 1 million points per revolution) is processed to detect pedestrians, by selecting cubic shapes and applying machine vision and machine learning algorithms to the XY, XZ, and YZ projections of the points contained in the cube. The work relates an exhaustive analysis of the performance of three different machine learning algorithms: k-Nearest Neighbours (kNN), Naïve Bayes classifier (NBC), and Support Vector Machine (SVM). These algorithms have been trained with 1931 samples. The final performance of the method, measured a real traffic scenery, which contained 16 pedestrians and 469 samples of non-pedestrians, shows sensitivity (81.2%), accuracy (96.2%) and specificity (96.8%).

A sensor system for detection of hull surface defects.

This paper presents a sensor system for detecting defects in ship hull surfaces. The sensor was developed to enable a robotic system to perform grit blasting operations on ship hulls. To achieve this, the proposed sensor system captures images with the help of a camera and processes them in real time using a new defect detection method based on thresholding techniques. What makes this method different is its efficiency in the automatic detection of defects from images recorded in variable lighting conditions. The sensor system was tested under real conditions at a Spanish shipyard, with excellent results.

Industrial-Like Vehicle Platforms for Postgraduate Laboratory Courses on Robotics

The interdisciplinary nature of robotics allows mobile robots to be used successfully in a broad range of courses at the postgraduate level and in Ph.D. research. Practical industrial-like mobile robotic demonstrations encourage students and increase their motivation by providing them with learning benefits not achieved with traditional educational robotic platforms. This paper presents VEGO, an industrial-like modular vehicle platform for robotic education with an appropriate infrastructure that has been demonstrated to be very useful at the postgraduate level. Besides learning engineering concepts, in performing industrial-like exercises, students develop valuable skills such as teamwork and the capacity to solve problems similar to those they may encounter in a real industrial environment. The developed infrastructure represents a valuable platform for robotic education that can be used in many different disciplines as a way to demonstrate how to cope with the difficulties and challenges related to the development of industrial infrastructure systems. The platform evaluation proved its ability to inculcate the expected engineering skills. A novel approach is adopted through the use of multidisciplinary and close-to-industrial-reality platforms developed under an incremental approach and using an open and customizable structure.

Software-intensive systems interoperability in Smart Grids: A semantic approach

Smart Grid can be thought as integrating the electrical and information technologies in between any point of generation and any point of consumption of the grid. This is a challenging context for the software-intensive systems of the grid, since interoperability among them become a fundamental issue to communicate and interchange data (syntactic interoperability). More than supporting just communication among systems, the interpretation of the interchanged data (semantic interoperability) is a requirement to identify deviations in the grid in time slots as the strict real-time. This paper approach defines a semantic framework which includes 1) a semantic model defined in a powerful ontology language and 2) the proper processing components as the means for interpreting data and for inferencing implicit knowledge. In addition, these both parts need to be integrated into the grid node design for supporting the systems interoperability in all localization and decision levels of the Smart Grid. A case study has been performed to show the feasibility of this approach in the context of an ambitious Smart Grid project and the Spanish electrical grid.

Towards estimating the value of an idea

Today software industry lives in a very competitive environment and firms need to improve constantly. One way to achieve this goal can be the introduction of innovative ideas into the products, processes or services of the firms, allowing thus to increase the value delivered to the customer. Various sources of innovation are already identified in literature to obtain new ideas. It is hard to identify the most effective idea sources. Moreover, to introduce new ideas without a defined goal could turn out lots of waste for the company. In this research work it is pointed out why the estimation of the value of an idea is difficult, more when the item to evaluate is a new unimplemented idea. As a solution to this a framework that facilitates and supports the idea value estimation is proposed. Based on a the available literature, the authors outline a framework for innovation that will facilitate organizations to identify new ideas and to estimate their potential value. This framework will facilitate the introduction of innovation in software intensive systems industry.

TELEOPERATED SERVICE ROBOT FOR HIGH QUALITY SHIPS' MAINTENANCE

Abstract Most shipyard repair operations are not currently automated. A huge number of constraints make maintenance operations such as hull blasting very difficult to automate. There are partial solutions like blasting turbines and ultrahigh pressure water blasting units for vertical walls. This paper details a proposal of incremental development using a robotic teleoperation platform for hull blasting operations funded by a European Consortium of shipyards, equipment manufacturers and research centres. Such system offers an integral solution for hull preparation complying with requirements of efficiency, worker safety and environmental care.

COST EFFECTIVE HIGH-SPEED MACHINE VISION WITHIN THE INDUSTRY OF PRESERVED VEGETABLES

Abstract The paper describes a sophisticated and low cost Automated Visual Inspection System (AVIS) for quality control of preserved orange segments, widely applicable to production processes of preserved fruits and vegetables. Main constraints concerning these kind of inspection applications are addressed: the need of on-line operation together with an strong requirement of economic profitability. The strong commitment of above circumstances have forced the development of a flexible and low cost AVIS architecture. An special effort has been put in the design of the defect detection algorithms to reach two main objectives: accurate feature extraction and on-line capabilities, both considering robustness and low processing time. An on-line implementation to inspect up to ten orange segments by second is reported.

Automated Visual Inspection of Non-Smooth Surfaces. Application to Cast Aluminum

Abstract In this paper a general, low cost, arquitecture is described along with a methodologie for on-line defect detection and analysis in flat surfaces continously produced. On-line inspection of 100% production, along with the proper characteristics of inspection when texture is present force up the development of optimized algorithms for both detection and classification. Also hardware platforms that permit pipelined processing along with high modularity and are needed with a cost that make them competitive in every kind of surface visual inspection applications. An industrial application is described for quality assessment and process driving in cast aluminum obtention.