Eduardo Vendrell

Application of a real time expert system platform for flexible autonomous transport in industrial production

Abstract In a manufacturing environment, material transport plays a key role for the production process efficiency. In Schoeller-Bregenz (SB), a textile manufacturing SME, induction wire guided vehicles performed typical material transports, without the flexibility to adapt transport routes to changes in the production process. To overcome these deficits in the RETRARO project 8 an Autonomous Guided Vehicle (AGV) was designed and tested in the production plant. To adapt to changing production configurations, RETRARO had to provide solutions for the following functionality regarding economical constraints: algorithms for efficient path planning and health monitoring; economic sensor systems to provide navigation and obstacle avoidance functions; Integration of free navigation capabilities with existing wire guidance systems. This paper presents a survey on the AGV system design and details on the implementation of the control system based on: the real time expert system REAKT for path planning and health monitoring; a low cost ultra sonic range detection system using sensor data fusion for navigation and obstacle avoidance.

Reactive planning simulation in dynamic environments with VirtualRobot

One of the difficulties of using Artificial Neural Networks (ANNs) to estimate atmospheric temperature is the large number of potential input variables available. In this study, four different feature extraction methods were used to reduce the input vector to train four networks to estimate temperature at different atmospheric levels. The four techniques used were: genetic algorithms (GA), coefficient of determination (CoD), mutual information (MI) and simple neural analysis (SNA). The results demonstrate that of the four methods used for this data set, mutual information and simple neural analysis can generate networks that have a smaller input parameter set, while still maintaining a high degree of accuracy.

Robot planning and re-planning using decomposition, abstraction, deduction, and prediction

Abstract One of the current topics of research in robotics is activity planning. Most works in this field are related to artificial intelligence (AI) techniques. The main feature of robot planning systems is that they are focused on the particular robot problem or are intended to solve a particular aspect of the planning problem. For this last case, motion planning or task planning are solved in an independent way. This paper covers robot activity planning and re-planning, from the high-level activity description to the final trajectory of the robot. Problem decomposition and abstraction are applied to obtain a robot plan; deduction and prediction are used for on-line trajectory re-planning. Temporal reasoning enables the obtention of velocity tuning for a trajectory.

PATU: A mentoring program for freshmen

In order to avoid the gap between the post-compulsory secondary education and the University, the PATU program has been conducted at the UPV. Every freshman has a teacher as an academic advisor and a sophomore as an “older brother”. Students have evaluated the program as useful and interesting, and in addition, the ones following this action have a better academic performance during their first year.

Architecture Definition for a Flexible Transport System in Industrial Production

Abstract Most of mobile robots in industrial environments are wire guided, following induction wires and artificial reference marks laid down on the factory floor. This kind of approach has the lack of flexibility to adapt the system for different transport requirements. This lack may be overcome using Autonomous Guided Vehicles (AGVs) which must be provided with an intelligent control system. Precisely, the purpose of the RETRARO project was to support intelligent control of an AGV in a specific production process. In this paper, the architecture of the system is explained, making special attention to the different module functions and their interfaces.

Assessment of the learning competence of Mathematics for freshmen of the Computer Science degree

Mathematics is an important core of the syllabus of any Computer Science degree. We have studied the relation between the learning competence of Mathematics for first-years at the Universidad Politécnica de Valencia, and their success in the subjects of mathematics in the degree. Its relevance for their success in the whole first academic year is also reported.

Human Intuitions Based Planning for Mobile Robots Considering Dynamic Environments

Abstract Considering dynamic environments where mobile robots move makes much more difficult planning resolution. The possibility to have non-controlled mobiles in the environment is one of the cases considered in dynamic environments. This paper presents a planner based on human intuitions such as environment watching, problem decomposition and hierarchical structure. In this way, a watcher is in charge to estimate future actions of non-controlled mobiles, from present and historical position data. These estimations are essential inputs for the mission planner of the controlled mobile to obtain optimal solutions. Problem decomposition and hierarchical structure are considered to propose an adequate software architecture.

Robot Programming Based on Commercial CAD Systems

Abstract Cost reduction in commercial CAD systems makes them appropriate to be used as a support tool for robot programming. The use of these systems allows a graphical, intuitive tool to be acquired for supporting robot programmers. The paper describes the development of a robot programming system based on a low cost commercial CAD software. This programming system admit robots to be handled in an interactive way from a personal computer. Programs are made by modifying the robot configuration graphically on the computer screen. The developed tool is for general use, and accept any robot modelled in the CAD system to be programmed. In the paper, an education laboratory for training robot programmers using this software is described

An Augmented Reality Mobile App for Museums: Virtual Restoration of a Plate of Glass

One of the problems for archaeologic museums is having the opportunity to show most of the objects that they preserve. This is an action they can’t afford because of the limitation of exhibition spaces, the high number of artifacts they guard and/or the conditions of the real objects. Nowadays, with the use of cutting-edge 3D technologies, there is the possibility to offer virtual views of objects adding information and enhancing visitor’s experience. In this paper, an Augmented Reality app for visualizing restored ancient artifacts is presented. Based on an algorithm that addresses geometric constraints of fragments to re-build the object from parts, the AR application shows a reconstructed artifact offering the possibility for the user to visualize missing fragments. The app has been demonstrated using a real restored glass plate from the Manises Ceramic Museum, under the context of a research project funded by the Spanish Ministry of Economy, Industry and Competitiveness.

Analysis of the impact of a mentoring program in the computer science degrees at the Universitat Politecnica de Valencia - Impact of the PATU program at the Escuela Tecnica Superior de Ingenieria Informatica of the UPV

In this work we show the impact of a mentoring program for freshmen set for the degrees taught at the Escuela Tecnica Superior de Ingenierlia Informaitica of the Universitat Politecnica de Valencia. We analyze the variables that influence the student participation in the program, and we evaluate the impact that following up it has for an improvement of the academic performance of the students.