Francisco Martinez-Gil

Francisco Martinez-Gil
University of Valencia | UV · Department of Computer Science

BSc Physics. PhD in Computer Science

About

18
Publications
5,949
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
203
Citations
Citations since 2016
7 Research Items
183 Citations
20162017201820192020202120220102030
20162017201820192020202120220102030
20162017201820192020202120220102030
20162017201820192020202120220102030
Additional affiliations
January 2000 - present
University of Valencia
Position
  • Titular de Escuela Universitaria

Publications

Publications (18)
Article
Full-text available
The combination of machine learning methods together with computational modeling and simulation of the cardiovascular system brings the possibility of obtaining very valuable information about new therapies or clinical devices through in-silico experiments. However, the application of machine learning methods demands access to large cohorts of pati...
Article
Full-text available
Reinforcement learning is one of the most promising machine learning techniques to get intelligent behaviors for embodied agents in simulations. The output of the classic Temporal Difference family of Reinforcement Learning algorithms adopts the form of a value function expressed as a numeric table or a function approximator. The learned behavior i...
Article
Full-text available
Modeling pedestrian dynamics and their implementation in a computer are challenging and important issues in the knowledge areas of transportation and computer simulation. The aim of this article is to provide a bibliographic outlook so that the reader may have quick access to the most relevant works related to this problem. We have used three main...
Article
Full-text available
This paper analyzes the emergent behaviors of pedestrian groups that learn through the multiagent reinforcement learning model developed in our group. Five scenarios studied in the pedestrian model literature, and with different levels of complexity, were simulated in order to analyze the robustness and the scalability of the model. Firstly, a redu...
Conference Paper
Multi-agent systems allow the modelling of complex, heterogeneous, and distributed systems in a realistic way. MARL-Ped is a multi-agent system tool, based on the MPI standard, for the simulation of different scenarios of pedestrians who autonomously learn the best behavior by Reinforcement Learning. MARL-Ped uses one MPI process for each agent by...
Article
Full-text available
A new multi-agent reinforcement learning approach is introduced for the simulation of pedestrian groups. The embodied agents learn by interacting with the environment. They must learn to control their velocity, avoiding obstacles and the other pedestrians to reach a goal (a spatial position) inside the virtual environment. A new methodology is prop...
Article
Full-text available
Pedestrian simulation is complex because there are different levels of behavior modeling. At the lowest level, local interactions between agents occur; at the middle level, strategic and tactical behaviors appear like overtakings or route choices; and at the highest level path-planning is necessary. The agent-based pedestrian simulators either focu...
Conference Paper
Full-text available
In this work, a Multi-agent Reinforcement Learning framework is used to generate simulations of virtual pedestrians groups. The aim is to study the influence of two different learning approaches in the quality of generated simulations. The case of study consists on the simulation of the crossing of two groups of embodied virtual agents inside a nar...
Conference Paper
Full-text available
In this paper, the calibration of a framework based in Multi-agent Reinforcement Learning (RL) for generating motion simulations of pedestrian groups is presented. The framework sets a group of autonomous embodied agents that learn to control individually its instant velocity vector in scenarios with collisions and friction forces. The result of th...
Conference Paper
Full-text available
In this paper we introduce a Multi-agent system that uses Reinforcement Learning (RL) techniques to learn local navigational behaviors to simulate virtual pedestrian groups. The aim of the paper is to study empirically the validity of RL to learn agent-based navigation controllers and their transfer capabilities when they are used in simulation env...
Conference Paper
Full-text available
This paper presents a Q-Learning-based multiagent system oriented to provide navigation skills to simulation agents in virtual environments. We focus on learning local navigation behaviours from the interactions with other agents and the environment. We adopt an environment-independent state space representation to provide the required scalability...
Article
Full-text available
We focus in this paper on the problem of learning an autonomous agent's policy when the state space is very large and the set of actions available is comparatively short. To this end, we use a non-parametric decision rule (concretely, a nearest-neighbour strategy) in order to cluster the state space by means of the action that leads to a successful...
Conference Paper
A VECT (Virtual ENvironment for Ceramic Tile) is a software/hardware new-generation system conceived for displaying and presenting full conllections of ceramic tiles in a realistic computer graphics virtual environment. The system aims at giving both the indoor decorator and the customer a realistc idea about the products and helping him with his d...
Conference Paper
Full-text available
Resumen El crecimiento de los aplicaciones en gráficos 3D sugiere la necesidad de exportar las actuales metáforas empleadas en la interacción 2D, así como la introducción de nuevos conceptos 3D que permitan el manejo y la creación de interfaces eficientes en estos entornos. El sistema 4D-GIFT es una plataforma de propósito general para el desarroll...
Conference Paper
The last version of SIRCA driving simulator, a joint project of Robotics Institute and the Dept. of Computer Science of the University of Valencia, provides the database structure and managment techiniques required to include the simulation of the driving process in urban or motorway scenario as well as the simulation of driving freeely on any type...

Network

Cited By

Projects

Projects (6)
Project
Identify biomarkers to characterize the relationship between aorta geometry and Wall Shear Stress under different pathological conditions.