Fernando De la Rosa

Los Andes University (Colombia) | UNIANDES · Department of Systems and Computer Engineering

In Robotics, one of the core problems is motion planning towards a specified goal. Today, there are different solutions; however, most of them require complex models of the environment, not intuitive at all, and force the programmer to understand in detail the operating mode of the robot she/he is working with. Furthermore, most algorithms use inac...

This paper describes the development of a hierarchical control system based on learning from demonstration applications. This system is capable of identifying and handling ambiguous situations that may have happened during the demonstration. An ambiguous situation is defined as a state of the robot in which the demonstrator executed different actio...

Este trabajo presenta una arquitectura de interacción multimodal que se propone como la componente de interacción/control de aplicaciones computacionales existentes o nuevas, en particular para aplicaciones de computación visual 2D/3D. La arquitectura busca favorecer la multimodalidad en la interacción entre el usuario y una aplicación computaciona...

The Multi-Resolution Cooperation Control (MRCC) approach is presented, which proposes a control architecture for intentional cooperation distributing responsibilities on multiple levels by applying the multi-resolution principle. This principle implies a hierarchical decomposition of the MAS cooperative control, where each layer manages the decisio...

This work presents an approach to plan motion strategies for robotics tasks constrained by uncertainty in position, orientation, and control. Our approach operates in a (x, y, θ) configuration space and it combines two local functions: a contact-based attraction function and an exploration function. Compliant motions are used to reduce the position...

Self-driving robots have to fulfill many different operations, as coordinating the motors’ traction, camera movement, or actuator arms mechanics, as well as more high-level operations like driving to different places. Autonomous navigation is of utmost importance for exploration robots, which must drive around exploring areas with unknown terrain c...

This article presents a system architecture that integrates the construction, execution, and monitoring of threedimensional flight paths for drones using virtual reality (VR). In this work, we propose a system that allows the construction and execution of flight paths by people who lack experience in drone piloting. For this purpose, the integrati...

MaruGen (Machinations Ruleset Generator) is a semi-automatic system for the generation of mechanics, rules, spaces, and missions for video games. The objective is to give, to the role of video game designer, an expression mechanism, based on the definition of rules, and the ability to explore the concepts of progression and emergence in videogames...

The Data Structures course is common in Systems Engineering and Computer Science programs, providing a fundamental basis for professional training in these disciplines. This course presents a great pedagogical challenge, due to the high complexity in the algorithms studied and the levels of abstraction that it requires. Considering that the traditi...

This paper presents an implementation of a technique to solve the problem of Multi-Travel Salesman Problem (MTSP) applied on mobile robots in dynamic scenarios. Because MTSP is a NP-Complete problem, we use genetic algorithms in order to resolve it efficiently. Once we got a theoretical solution for MTSP, we required to apply this on simulated and...

El arte del diseño y desarrollo de juegos es por naturaleza un proceso complejo y multidisciplinario, que requiere múltiples roles, procesos y talentos para su realización exitosa. Una de las etapas críticas corresponde al diseño (creación de mecánicas y reglas, y definición de la misión y objetivos del videojuego) y es la etapa en que se tiene men...

One of the major challenges related to teaching programming and algorithmics to amateur students is the time spent to explain a language’s syntax. Also, students who undertake computer programming may find problems that hinder their understanding of concepts and the development of their problem-solving and programming skills. This paper presents th...

Deep Learning is a machine learning technique that seeks to define neural networks based on pattern recognition from the input data, and to achieve results with a high level of confidence and time efficiency. In this paper, this technique is used in two processes that aim to improve the indoor exploration of a mobile robot. The first process enable...

Deep Learning es una técnica de aprendizaje de máquina que busca definir redes neuronales basadas en el reconocimiento de patrones de los datos de entrada y lograr resultados con un nivel de confianza alto y eficiente en tiempo. En este trabajo se aplica en dos procesos que buscan mejorar la exploración de un robot móvil en espacios interiores. El...

Este artículo presenta una propuesta de una arquitectura de un sistema que integra diferentes tecnologías existentes en consultas Web, visualización de información e interacción multimodal humano-computador. La arquitectura propuesta depende de fuentes de información Web heterogéneas que se presentan al usuario en forma de servicios usando un siste...

One of the major challenges related to teaching programming and algorithms to novice students is the time spent on the language’s syntax and how their attention is incorrectly focused on the syntax rather than the acquisition of concepts and the development of problem-solving and programming skills. This study focuses on the design and evaluation o...

This paper presents a control architecture that enables the execution of cooperative tasks with a set of mobile robots. In this architecture, a cooperative task is defined by known subtasks specified for mono-robot tasks and/or group subtasks. The representation of a cooperative task uses the formalism of a Petri net, which allows the definition of...

The study of the ways in which humans interact with robots is a multidisciplinary field with multiple contributions from electronics, robotics, human-computer interaction, ergonomics and even social sciences. The robotics industry is mainly focused on the development of conventional technologies that improve efficiency and reduce the amount of repe...

La recopilación de información a través de la teledetección inició desde principios del siglo XX, y ha permitido su uso para la toma de decisiones en diversos ámbitos del manejo de desastres. La integración de información de imágenes satelitales e información real de las estaciones de hidrología permite conocer el comportamiento de la inundación en...

The lack of a standard in the area of Automation has led to all manufacturers and researchers to work in parallel on new technologies which have increased the heterogeneity of devices and drivers on the market. As a result, each manufacturer must provide the tools needed for installation, configuration and implementation of its technology. As a con...

Este trabajo presenta una propuesta del componente de interacción de usuario multimodal para ser integrado principalmente con aplicaciones de computación visual 2D/3D. El componente considera múltiples canales de entrada de información funcionando simultáneamente. Sobre cada canal de entrada se define un proceso de tratamiento de información que co...

The motion planning task for a mobile robot aims to generate a free-collision path from an initial point to a target point. This task may be highly complex because it requires a complete knowledge of the robot’s environment. In this paper an option-based hierarchical learning approach is proposed to this problem in which basic behaviors are applied...

This paper presents a multimodal interaction architecture that is proposed as the interaction/control component of new or existing computer applications, particularly for 2D/3D visual computing applications. The architecture aims to encourage multimodality in interaction between the user and the computer application in order to achieve a more natur...

This work presents the Web enabled remote laboratory TeleMobileRobot-Lab developed as a project for supporting the execution of remote labs in Mobile Robotics courses. This laboratory is designed under a client-server architecture where the access to users is enabled through Web clients connecting to a server to perform tele-operation tasks. Each r...

One of the most important challenges in mobile robotics is the estimation of the robot’s position while it explores the environment. The SLAM (Simultaneous Localization and Mapping) technique solves this challenge while it builds an approximate map of the environment. This paper proposes a mono-robot SLAM solution applied by a group of mobile robot...

The execution of actions in interactive applications depends on the user's intention. This intention should be able to be expressed in a natural language for the user. The gestures can be exploited as an intuitive language for the user. Using a gesture-based language, an interactive application must be able to express its possible actions independe...

In order to create a cooperative architecture for multi- agent systems in robotic soccer, it is necessary to model and understand the human soccer concepts to use and express them computationally. This work presents the main features for a multi-agent cooperative architecture based on human soccer concepts. The architecture can be applied to differ...

In Robotics, one of the core problems is motion planning towards a specified goal. Today, there are different solutions; however, most of them require complex models of the environment, which are not intuitive at all, and force the programmer to understand the operating mode in detail of the robot she/he is working with. Furthermore, most algorithm...

We present a scalable application for machine-tool manipulation in Virtual Reality (VR) environments, which aims to support a progressive learning environment. Our application allows interacting with a machine-tool at three different levels, focusing on increasing the manipulation skills acquired by students in each level. We represent the machine-...

El proyecto se desarrolla con la participación interinstitucional de la Universidad Nacional de Colombia a cargo del profesor Ernesto Córdoba, la Universidad de los Andes de Colombia - profesor Pablo Figueroa y Fernando de la Rosa, la Universidad Autónoma de Occidente - profesor Jesús David Cardona y el Instituto Tecnológico y de Estudios Superiore...

Soccer is a complex game, characterized by a dynamic environment with a variety of situations, some of them, considered as non-repetitive, where a team should act cooperatively and respond to the dynamics of the game. This paper proposes and evaluates a set of motions (basic plays) that define an initial level of skills for the individual players o...

In order to build a software architecture suitable to robotic soccer, it is necessary to model the base concepts of human soccer. In human soccer, the coach plays an important role in planning the moves, tactics and strategies to prepare its team to a match, while in robotic soccer the coach usually does not exist. The architecture must be concerne...

We present a scalable application for machine-tool manipulation in VR environments, which aims to support a progressive learning environment. The application allows interacting with a machine-tool in three different levels, focusing on increasing the manipulation skills acquired by the student/user in each level. Our application represents the mach...

Este artículo presenta el diseño e implementación de un sistema de trabajo colaborativo para grupos de investigación. El sistema se apoya en la plataforma Access Grid que permite la gestión y administración de salas de trabajo y políticas de acceso, al mismo tiempo que ofrece servicios de teleconferencia (transmisión de audio/video). Bajo esta plat...

This paper presents an implementation and comparison between odometry and probabilistic algorithms for the mobile robot localization problem in indoor environments.The hardware and software tools used for the experiments are briefly described. Also, a software architecture is proposed to make easier the development of computer applications includin...

This paper presents the design and test processes of a multi-robot architecture based on behaviors. This architecture is the result of simulation tests modifying the levels of knowledge, coordination and organization of multiple robots. The tests have been developed by a team of robots doing a task with a common objective. The behaviors are heurist...

Collaborative environments are designed in order to provide facilities for participants who share a common interest. In research groups, this kind of platforms must include additional requirements in terms of networking and data processing capabilities, requirements that can be satisfied by the use of a suitable infrastructure. This paper presents...

Resumen. Este artículo presenta el proceso de diseño y validación de una arquitectura que controla un grupo de robots trabajando cooperativamente. La arquitectura propuesta está basada en comportamientos y es el resultado de pruebas en simulación modificando los niveles de conocimiento, coordinación y organización de múltiples robots. Las pruebas s...

This work presents a computational tool that leads the interactive creation of 3D geometrical models based on the Scene Graph concept. Into an active learning environment, the purpose is that the student uses the tool for an incremental construction of a 3D object Scene Graph and verifies the results incrementally with a graphical feedback. The obt...

Este trabajo presenta una herramienta computacional que permite la creación interactiva de modelos geométricos compuestos 3D basados en el concepto de Grafo de Escena. En un espacio de aprendizaje, el propósito es que el estudiante utilice la herramienta para construir incrementalmente un grafo de escena de un objeto geométrico compuesto 3D de inte...

Este artículo muestra las posibilidades del uso y desarrollo de aplicaciones colaborativas sobre la red académica de alta conectividad (RENATA), que conecta a Colombia con la red latinoamericana CLARA y a través de ésta con Europa (GEANT) y con Estados Unidos (Internet2). Los prototipos presentados se desarrollaron sobre la plataforma Access Grid y...

This article shows the potential of collaborative applications over the RENATA network, the academic, high-bandwidth, Colombian communication infrastructure with access to other high-bandwidth initiatives in Latin America (CLARA network), Europe (GEANT), and USA (Internet2). Several prototypes on top of Access Grid show the added value for telecoll...

. This paper presents an approach to plan robust motion strategies of a robot navigating through an environment composed of polygonal obstacles subject to geometric uncertainty constraints. The contacts of the robot against the obstacles are used to reduce its position and orientation uncertainties and to guide the robot to its goal configuration....

. This paper presents an approach to plan robust motion strategies of a robot navigating through an environment composed of polygonal obstacles subject to geometric uncertainty constraints. The contacts of the robot against the obstacles are used to reduce its position uncertainty and to guide the robot to its goal configuration. We describe a moti...

A new motion planning approach is proposed for a holonomic robot (with 2 degrees of freedom in translation and 1 in rotation) under geometric uncertainty constraints. The constraints take into account the position, orientation and motion of the robot. The original contribution of the approach is the resolution method and the modelling of uncertaint...

Une nouvelle approche de planification automatique de mouvements est proposée pour un robot holonome (ayant 2 dégrés de liberté en translation et 1 degré de liberté en rotation) sous des contraintes d'incertitudes géométriques. Les incertitudes considérées portent sur le positionnement (position/orientation) et sur le déplacement du robot. L'origin...

This paper presents an approach to plan robust motion strategies of a robot navigating through an environment composed of polygonal obstacles subject to geometric uncertainty constraints. The contacts of the robot against the obstacles are used to reduce its position and orientation uncertainties and to guide the robot to its goal configuration. Th...

This work presents an approach to plan robot motions in the presence of geometric uncertainty. The contacts of the robot against the obstacles are used to reduce the position/orientation uncertainty and to guide the robot towards its goal when it is possible. Consequently, two types of motions are used to construct a motion planner: free space moti...

Resumen— En este documento se propone una plataforma de hardware y software para el desarrollo juegos con robots móviles que pueda ser utilizada como herramienta de apoyo en investigación y ens nanza en eí area de robótica móvil. La plataforma está compuesta por dispositivos de hardware (sistema de visión sobre el campo de juego, estaciones de trab...