Nicolas Verstaevel

Nicolas Verstaevel
Toulouse 1 Capitole University | UT1 · Research Institute in Information Technology

PhD in Artificial Intelligence
Associate Professor @Université Toulouse 1 Capitole, member of the IRIT laboratory, Toulouse, France

About

29
Publications
8,917
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
250
Citations
Introduction
I am an associate professor at University Toulouse 1 Capitole Some keywords: multi-agent systems, robotics, machine learning, problem solving and complex systems
Additional affiliations
September 2019 - present
Toulouse 1 Capitole University
Position
  • Professor (Associate)
September 2019 - present
Institut de Recherche en Informatique de Toulouse
Position
  • Professor (Associate)
March 2018 - July 2019
University of Wollongong
Position
  • Research Fellow
Education
July 2013 - June 2016
Paul Sabatier University - Toulouse III
Field of study
  • Artificial Intelligence
September 2010 - June 2012
Paul Sabatier University - Toulouse III
Field of study
  • Artificial Intelligence, Collective Intelligence, Interaction
September 2007 - June 2010
Université d'Orléans
Field of study
  • Informatics

Publications

Publications (29)
Article
Full-text available
Ambient systems are populated by many heterogeneous devices to provide adequate services to its users. The adaptation of an ambient system to the specific needs of its users is a challenging task. Because human-system interaction has to be as natural as possible, we propose an approach based on Learning from Demonstration (LfD). However, using LfD...
Conference Paper
Full-text available
Over the years, our research group has designed and developed many self-adaptive multi-agent systems to tackle real-world complex problems, such as robot control and heat engine optimization. A recurrent key feature of these systems is the ability to learn how to handle the context they are plunged in, in other words to map the current state of the...
Thesis
Full-text available
The AMAS (Adaptive Multi-Agent Systems) theory proposes to solve complex problems for which there is no known algorithmic solution by self-organization. The self-organizing behaviour of the cooperative agents enables the system to self-adapt to a dynamical environment to maintain the system in a functionality adequate state. In this thesis, we appl...
Article
Full-text available
The increasing development of urban centers brings serious challenges for traffic management. In this paper, we introduce a smart visual sensor, developed for a pilot project taking place in the Australian city of Liverpool (NSW). The project's aim was to design and evaluate an edge-computing device using computer vision and deep neural networks to...
Article
Full-text available
With the drastic increase of their urban population, cities face huge challenges to maintain and update their infrastructures. Assessing in real time the effect of urban policies will be a key tool in the future of urban planning. In this paper, we discuss of mobility and its impact on air quality. We introduce a pilot project in which low cost IoT...
Preprint
Adaptive Multi-Agent Systems (AMAS) transform dynamic problems into problems of local cooperation between agents. We present smapy, an ensemble based AMAS implementation for mobility prediction, whose agents are provided with machine learning models in addition to their cooperation rules. With a detailed methodology, we propose a framework to trans...
Preprint
Self-Adaptive Multi-Agent Systems (AMAS) transform machine learning problems into problems of local cooperation between agents. We present smapy, an ensemble based AMAS implementation for mobility prediction, whose agents are provided with machine learning models in addition to their cooperation rules. With a detailed methodology, we show that it i...
Chapter
Traffic simulation is a tool used by urban planners to assess the impact of new urban designs and public policies on mobility. Over the years, numerous traffic models have been proposed, each model offering different levels of details and performances. Multi-level model coupling is an interesting approach to combine the advantages of complementary...
Article
Full-text available
In the standard definition of the classical gambler's ruin game, a persistent player enters in a stochastic process with an initial budget b0, which is, round after round, either increased by 1 with probability p, or decreased by 1 with probability 1−p. The player wins the game if the budget reaches a given objective value g, and loses the game if...
Article
Full-text available
This paper introduces a simulation framework to model and study mobility changes. Novelty comes from the possibility to combine different agent-based models into the GAMA platform, and to interact with the simulation through pre-designed scenarios and a serious game.The objective is to explore the impact of different urban policies on future mobili...
Conference Paper
Full-text available
In this paper we introduce a dataset of environmental information obtained via indoor and outdoor sensors deployed in the SMART Infrastructure Facility of the University of Wollongong (Australia). The acquired dataset is also made open-sourced along with this paper. We also propose a novel approach based on an evolutionary algorithm to determine pa...
Chapter
Full-text available
Helping users to find pertinent documents within a big corpus through the use of simple queries on a search engine is a major concern in the information retrieval field. The work presented in this article combines the use of standard natural language processing methods to estimate the relevance of a document to a query with an online preference lea...
Conference Paper
Full-text available
Helping users to find pertinent documents within a big corpus through the use of simple queries on a search engine is a major concern in the information retrieval field. The work presented in this article combines the use of standard natural language processing methods to estimate the relevance of a document to a query with an online preference lea...
Article
Full-text available
This paper contributes in several ways. It analyses how the term, disaster informatics has been used over time in the literature in order to establish if there are any patterns of usage or shared meanings across countries/regions or disciplines. Based on insights from the articles reviewed, the study further contributes by providing a more unified...
Article
Full-text available
Air pollution with PM2.5 (particulate matter smaller than 2.5 micro-metres in diameter) is a major health hazard in many cities worldwide, but since measuring instruments have traditionally been expensive, monitoring sites are rare and generally show only background concentrations. With the advent of low-cost, wirelessly connected sensors, air qual...
Article
Full-text available
Floods are amongst the most common and devastating of all natural hazards. The alarming number of flood-related deaths and financial losses suffered annually across the world call for improved response to flood risks. Interestingly, the last decade has presented great opportunities with a series of scholarly activities exploring how camera images a...
Conference Paper
Full-text available
We propose a review of articles dealing with the behavior change of users due to the setting-up of an eco-feedback system on university campuses. The main building types studied are dormitories. Results show that feedback is necessary but it needs to be borne by human actions such as social influence, peer comparison, or competition to induce susta...
Conference Paper
Full-text available
Smart cities involve, in a large scale, a wide array of interconnected components and agents, giving birth to large and heterogeneous data flows. They are inherently cross-disciplinary, provide interesting challenges, and constitute a very promising field for future urban developments, such as smart grids, eco-feedback, intelligent traffic control,...
Conference Paper
Full-text available
With 7/10 of the population which will live in urban center by 2050, Cities face huge challenge inviting to rethink the very concept of a City. The Smart Cities concept proposes to use Information and Communication Technologies to design sustainable solutions for improving socio-ecological aspects of cities. In this paper, we present the challenge...
Conference Paper
Full-text available
Sensors and actuators are progressively invading our everyday life, as well as industrial processes. They form complex and pervasive systems usually called " ambient systems " or " cyber-physical systems ". These systems are supposed to efficiently perform various and dynamic tasks in an ever-changing environment. They need to be able to learn and...
Conference Paper
Full-text available
Designing a controller to supervise an ambient application is a complex task. Any change in the system composition or end-users needs involves re-performing the whole design process. Giving to each device the ability to self-adapt to both end-users and system dynamic is then an interesting challenge. This article contributes to this challenge by pr...
Conference Paper
Full-text available
L’adaptation des systèmes ambiants aux besoins spécifiques des utilisateurs est une tâche complexe. Pour rendre l’interaction humain-système aussi naturelle que possible pendant l’adaptation, nous proposons une approche basée sur l’apprentissage par démonstration. Cet apprentissage requiert des techniques d’apprentissage adaptatifs. Nous présentons...
Conference Paper
Full-text available
Our work focuses on Extreme Sensitive Robotic that is on multi-robot applications that are in strong interaction with humans and their integration in a highly connected world. Because human-robots interactions have to be as natural as possible, we propose an approach where robots Learn from Demonstrations, memorize contexts of learning and self-org...
Article
Our work focuses on Extreme Sensitive Robotic that is on multi-robot applications that are in strong interaction with humans and their integration in a highly connected world. Because human-robots interactions have to be as natural as possible, we propose an approach where robots Learn from Demonstrations, memorize contexts of learning and self-org...
Article
Ambient systems are populated by many heterogeneous devices to provide adequate services to their users. The adaptation of an ambient system to the specific needs of its users is a challenging task. Because human-system interaction has to be as natural as possible, we propose an approach based on Learning from Demonstration (LfD). LfD is an interes...

Network

Cited By

Projects

Projects (4)
Project
Simulating the transition of transport Infrastructures Toward smart and sustainable Cities Design a simulator and serious game to support the exploration of scenarios for the town of the future.
Project
The SwITCh project aims at supporting decision-making for urban planning by simulating the gradual introduction of disruptive innovations on technology, usage and behaviour of infrastructure. It requires providing a model that is able to assess the impact of these innovations on several key indicators on mobility, user satisfaction and security, economic costs and air pollution. SwITCh integrates a large variety of urban transport modalities (private car, walk, tramway, etc.) and associated infrastructures (pavement, bicycle path, etc.). Achieving such an objective requires building a model that includes current and future infrastructures and modalities, and considering the transition process between current and future situations. SwITCh uses agent-based modelling (ABM) and participative simulation as a unifying framework that allows coupling different models and taking into account both temporal and spatial scales in order to build a holistic model. It will include a city model based on real geographic data (GIS) and a complex realistic model of population behaviour. The model will be designed as a support tool for helping stakeholders (i.e. decision-makers, managers, technicians and citizens) to enrich their reflection and build a shared project to improve transport infrastructures to meet the challenges of future cities. The SwITCh project will be centred on the design and on the implementation of an ABM that will result in an interactive simulator and a serious game. The interactive simulator will be used by the city planners to explore the potential impact of innovations in various evolutionary contexts. It will thus support the urban planning team in making relevant decisions regarding the evolution of their transport infrastructures, by letting them test and assess different alternatives and situations. The interactive simulator will also allow the researchers to highlight potential futures or unexpected side effects to the urban planners and other stakeholders, based on a participatory simulation approach. The serious game will be used by students and the larger public in order to enrich their understanding of the issues involved in the city of the future and the transport infrastructures. It will be based on the interactive simulator but will be enhanced by specific work on the game design in order to be a real support for learning and raising awareness. The interactive simulator and the serious game will be developed with the GAMA open-source platform and will be used in a real context for two case studies: Bordeaux Metropole and the Urban Community of Dijon. The SwITCh project will deliver several main results. Firstly, it will generate and formalize knowledge on future transport infrastructures. Secondly, the project will result in a simulation tool that could have significant socio-economic impacts: by helping infrastructure managers and urban planners, as a reflection support, to adapt infrastructures to future needs, by accelerating the transition to a more sustainable city which should have positive environmental (e.g. air pollution, global warming), economical (e.g. maintenance cost, commercial appeal) and social (e.g. traffic, living environment) impacts. The model will be flexible, easily adaptable to any city, and able to integrate a wide variety of prospective and disruptive scenarios.