Fernando De la Rosa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fernando De la Rosa has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Pedro Guillermo Feijóo-García
Georgia Institute of Technology, Atlanta, GA, USA
3 shared publications Andrea K. Pérez
Universidad Santo Tomás
2 shared publications- Carlos Quintero
Houston Methodist DeBakey Heart & Vascular Center, Houston Methodist, Houston, Texas, US
2 shared publications - Eyberth Rojas
Universidad Santo Tomás
2 shared publications - Germán Bravo
Universidad de los Andes
2 shared publications - Jose Tiberio Hernandez
Universidad de los Andes
2 shared publications
Latest Publications
- 14 November 2023
- Published by Springer Nature
- p. 128-140
Planning Navigation Routes in Unknown Environments
- 14 November 2023
- Published by Springer Nature
- p. 128-140
Planning Navigation Routes in Unknown Environments
- Open Access
- 27 March 2020
- Published by Universidad de Antioquia in Revista Facultad de Ingeniería Universidad de Antioquia
- No. 99,p. 9-20
Semi-automatic construction of video game design prototypes with MaruGen
Machinations Ruleset Generator (MaruGen) is a semi-automatic system for the generation of mechanics, rules, spaces (environments), and missions for video games. The objective of this system is to offer an expression mechanism for the video game designer role based on the definition of rules, and the ability to explore the concepts of progression and emergence in video games by using a formal, usable, and defined tool to design games with innovative and complex elements, and behaviors defined from combinations of basic elements. Based on the expressed designs and with the participation of programmers and video game artists, MaruGen allows the generation of agile video game prototypes in the Unity game engine. These prototypes can be analyzed by the entire workgroup to look for games with diverse complexities that make them attractive to their users. MaruGen is based on the expression of rules on elements of interest in video games and the rewriting mechanism using L-Systems for the generation of procedural content. MaruGen was evaluated in the construction of the Cubic Explorer video game and tested by gamers and video game developers during the Game Jam Ludum Dare 38.
- 27 March 2020
- Published by Universidad de Antioquia in Revista Facultad de Ingeniería Universidad de Antioquia
- No. 99,p. 9-20
Open AccessSemi-automatic construction of video game design prototypes with MaruGen
Machinations Ruleset Generator (MaruGen) is a semi-automatic system for the generation of mechanics, rules, spaces (environments), and missions for video games. The objective of this system is to offer an expression mechanism for the video game designer role based on the definition of rules, and the ability to explore the concepts of progression and emergence in video games by using a formal, usable, and defined tool to design games with innovative and complex elements, and behaviors defined from combinations of basic elements. Based on the expressed designs and with the participation of programmers and video game artists, MaruGen allows the generation of agile video game prototypes in the Unity game engine. These prototypes can be analyzed by the entire workgroup to look for games with diverse complexities that make them attractive to their users. MaruGen is based on the expression of rules on elements of interest in video games and the rewriting mechanism using L-Systems for the generation of procedural content. MaruGen was evaluated in the construction of the Cubic Explorer video game and tested by gamers and video game developers during the Game Jam Ludum Dare 38.
- Open Access
- 1 January 2019
- Published by International Association of Online Engineering (IAOE) in International Journal of Emerging Technologies in Learning (iJET)
- Vol. 14 (10) , 161-179
Scaffolded Block-based Instructional Tool for Linear Data Structures A Constructivist Design to Ease Data Structures' Understanding
Data structures courses commonly introduce topics involving high levels of abstraction and complexity, requiring significant effort from instructors and students to achieve positive teaching-learning outcomes. Despite the multiple studies that have occurred within the Computer Science Education (CS ED) community to understand the experiences that novice programmers may have when learning how to program, there is still a lack of exploration and research on understanding these experiences in scenarios different from first-year Computer Science (CS) courses. Looking further from CS introductory courses, this paper presents the results of a pilot study that evaluated the interaction of a group of CS Colombian students with DStBlocks, which is a scaffolded block-based instructional technology created to ease linear data structures understanding. The findings and results of this pilot study are favorable, corresponding to tests centered on user experience and learning impact.
- 1 January 2019
- Published by International Association of Online Engineering (IAOE) in International Journal of Emerging Technologies in Learning (iJET)
- Vol. 14 (10) , 161-179
Open AccessScaffolded Block-based Instructional Tool for Linear Data Structures A Constructivist Design to Ease Data Structures' Understanding
Data structures courses commonly introduce topics involving high levels of abstraction and complexity, requiring significant effort from instructors and students to achieve positive teaching-learning outcomes. Despite the multiple studies that have occurred within the Computer Science Education (CS ED) community to understand the experiences that novice programmers may have when learning how to program, there is still a lack of exploration and research on understanding these experiences in scenarios different from first-year Computer Science (CS) courses. Looking further from CS introductory courses, this paper presents the results of a pilot study that evaluated the interaction of a group of CS Colombian students with DStBlocks, which is a scaffolded block-based instructional technology created to ease linear data structures understanding. The findings and results of this pilot study are favorable, corresponding to tests centered on user experience and learning impact.
- 17 February 2018
- Published by Springer Nature
- p. 41-55
Methodology for Learning Multimodal Instructions in the Context of Human-Robot Interaction Using Machine Learning
- 17 February 2018
- Published by Springer Nature
- p. 41-55
Methodology for Learning Multimodal Instructions in the Context of Human-Robot Interaction Using Machine Learning
- 17 February 2018
- Published by Springer Nature
- p. 67-80
Identification of Multimodal Signals for Emotion Recognition in the Context of Human-Robot Interaction
- 17 February 2018
- Published by Springer Nature
- p. 67-80
Identification of Multimodal Signals for Emotion Recognition in the Context of Human-Robot Interaction
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 204-209
Path planning and following using genetic algorithms to solve the multi-travel salesman problem in dynamic scenarios
This paper presents an implementation of a technique to solve the Multi-Travel Salesman Problem (MTSP) when applied to mobile robots in dynamic scenarios. Given that the MTSP is an NP-Complete problem, we used genetic algorithms to solve it efficiently. Once we obtained a theoretical solution for the MTSP, we applied it in simulated and experimental scenarios. In addition, we implemented path planning algorithms to generate the path for each of the robots, and evasion algorithms to manage dynamic scenarios. With those main challenges clear, we tested these implementations in simulation and laboratory environments in order to measure the quality of the proposed solution.
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 204-209
Path planning and following using genetic algorithms to solve the multi-travel salesman problem in dynamic scenarios
This paper presents an implementation of a technique to solve the Multi-Travel Salesman Problem (MTSP) when applied to mobile robots in dynamic scenarios. Given that the MTSP is an NP-Complete problem, we used genetic algorithms to solve it efficiently. Once we obtained a theoretical solution for the MTSP, we applied it in simulated and experimental scenarios. In addition, we implemented path planning algorithms to generate the path for each of the robots, and evasion algorithms to manage dynamic scenarios. With those main challenges clear, we tested these implementations in simulation and laboratory environments in order to measure the quality of the proposed solution.
- Open Access
- 8 December 2016
- Published by International Association of Online Engineering (IAOE) in International Journal of Emerging Technologies in Learning (iJET)
- Vol. 11 (12) , 45-53
RoBlock – Web App for Programming Learning
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 the results of an experimental approach that evaluated the interaction of a group of Colombian students with a Web solution within the context of Mobile Robotics to learn programming and algorithmics. The designed Web App is oriented towards autodidactic learning by using Visual Blocks Programming through five interactive modules that include concepts to be learned by students such as the following: variables, sensors, conditionals, cycles, and functions. The solution is designed to present virtual scenarios for Mobile Robotics. This proposal was evaluated with middle school students from the Colombian education system and was compared to the results obtained using Scratch as a reference tool.
- 8 December 2016
- Published by International Association of Online Engineering (IAOE) in International Journal of Emerging Technologies in Learning (iJET)
- Vol. 11 (12) , 45-53
Open AccessRoBlock – Web App for Programming Learning
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 the results of an experimental approach that evaluated the interaction of a group of Colombian students with a Web solution within the context of Mobile Robotics to learn programming and algorithmics. The designed Web App is oriented towards autodidactic learning by using Visual Blocks Programming through five interactive modules that include concepts to be learned by students such as the following: variables, sensors, conditionals, cycles, and functions. The solution is designed to present virtual scenarios for Mobile Robotics. This proposal was evaluated with middle school students from the Colombian education system and was compared to the results obtained using Scratch as a reference tool.
- 24 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Sistema interactivo multimodal para visualización de información heterogénea
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 sistema de proyección en un espacio público. El usuario interactúa bajo dos modalidades: gestos de las manos sobre la superficie de proyección (entrada táctil) y comandos de voz (entrada audio). Como caso de estudio se desarrolló un sistema de servicios de interés para viajeros en salas de espera en un aeropuerto. Este sistema fue objeto de pruebas por un conjunto de usuarios que permiten obtener resultados sobre el interés de este tipo de sistemas.
- 24 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Sistema interactivo multimodal para visualización de información heterogénea
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 sistema de proyección en un espacio público. El usuario interactúa bajo dos modalidades: gestos de las manos sobre la superficie de proyección (entrada táctil) y comandos de voz (entrada audio). Como caso de estudio se desarrolló un sistema de servicios de interés para viajeros en salas de espera en un aeropuerto. Este sistema fue objeto de pruebas por un conjunto de usuarios que permiten obtener resultados sobre el interés de este tipo de sistemas.
- 1 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Using Deep Learning for Exploration and Recognition of Objects Based on Images
Deep Learning is a machine learning technique that seeks to define neural networks based on pattern recognition from 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 task of a mobile robot. The first process enables the recognition of physical structures such as stairs, elevators and corridors, based on images obtained from an on-board camera. The second process identifies the proximity to obstacles (based on the information from an on-board laser sensor) in order to determine the direction and moving speed of the robot for navigating an indoor space. This work stands out because it uses Deep Learning in both processes, through the implementation of a parametrizable generic neural network system, to create multiple network instances that are customizable according to the type of information, and to integrate them with a mobile robot that navigates in simulated and experimental environments.
- 1 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Using Deep Learning for Exploration and Recognition of Objects Based on Images
Deep Learning is a machine learning technique that seeks to define neural networks based on pattern recognition from 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 task of a mobile robot. The first process enables the recognition of physical structures such as stairs, elevators and corridors, based on images obtained from an on-board camera. The second process identifies the proximity to obstacles (based on the information from an on-board laser sensor) in order to determine the direction and moving speed of the robot for navigating an indoor space. This work stands out because it uses Deep Learning in both processes, through the implementation of a parametrizable generic neural network system, to create multiple network instances that are customizable according to the type of information, and to integrate them with a mobile robot that navigates in simulated and experimental environments.