Flavien Balbo

Mines Saint-Etienne | ENSM-SE · Département ISI

Over the past few decades, intelligent transportation systems (ITS) have emerged as an effective way to improve the performance of transportation systems. ITS provide innovative services, enhance travel safety, provide travellers with more choices, and make transportation systems more efficient. Multi-agent systems (MAS), which define autonomous in...

Le développement de véhicules autonomes, capables de communiquer de pair à pair, ainsi que l’intérêt pour les solutions à la demande (par exemple, Uber, Lyft, Heetch), sont les principales motivations de cette étude. Le problème d’allocation des véhicules aux clients est d’une importance majeure dans la gestion des systèmes de transport à la demand...

One of the main challenges in Industry 4.0 is the supervision and coordination of heterogeneous robots at runtime, especially when they have a certain level of autonomy, as seen in Autonomous Mobile Robots. In addition, autonomous robots and their digital twins are designed by private manufacturers, and their code is often inaccessible. In this stu...

Deploying fleets of Connected Autonomous Vehicles (CAVs), with limited peer-to-peer communication ranges, in order to provide On-demand Transport (ODT) services, requires a careful choice and evaluation of solution methods for resource allocation problems. We adopt in this paper a multiagent approach consists of: 1) defining a generic model to ODT'...

Deploying autonomous vehicle fleets, with limited communication ranges, in order to provide ODT service requires a careful choice and evaluation of solution methods for resource allocation problems. Our multiagent approach consists of: 1) Generic Modeling (AV-OLRA)- Autonomous Vehicles Online Localized Resource Allocation: A generic model to ODT's...

Multi-agent systems can be considered a natural paradigm when modeling various transportation systems, whose management involves solving hard, dynamic, and distributed allocation problems. Such problems have been studied for decades, and various solutions have been proposed. However, even the most straightforward resource allocation mechanisms lead...

Les problèmes d'allocation sont d'importance majeure dans la gestion des systèmes de transport à la demande (ODT). Ils ont été étudiés pendant des décennies, et diverses solutions ont été proposées. Les approches de résolution peuvent être classées en deux catégories : centralisées et décentralisées. Dans la pratique, chacune a ses avantages et dés...

Allocation problems are major issues in managing On-Demand Transport (ODT) systems. They have been studied for decades, and a variety of solutions were proposed. The approaches to these problems can be classified as centralized and decentralized. Each has its pros and cons in practice. In this work, we aim to provide a generic model for the proble...

Poster illustration of our extended abstract at AAMAS-21 "A Generic Multi-Agent Model for Resource Allocation Strategies in Online On-Demand Transport with Autonomous Vehicles"

Allocation problems are major issues in managing On-Demand Transport (ODT) systems. They have been studied for decades, and a variety of solutions were proposed. The approaches to these problems can be classified as centralized and decentralized. Each has its pros and cons in practice. In this work, we aim to provide a generic model for the problem...

Emphasizing the need for transparency and explainability of resource allocation decisions in ODT systems to be understandable by humans and move toward a more controllable resource allocation. We propose in this preliminary work a multi-agent architecture and general implementation guidelines towards meeting these requirements.

The introduction of driver-less technologies can improve on-demand transport (ODT) systems and help make passenger transportation and logistics more efficient. Major issues in managing ODT systems are allocation problems, i.e., finding feasible and good allocations of requests to vehicles. Being autonomous, vehicles in large fleets can make decentr...

On-Demand Transport (ODT) systems have attracted increasing attention in recent years. Traditional centralized dispatching can achieve optimal solutions, but NP-Hard complexity makes it unsuitable for online and dynamic problems. Centralized and decentralized heuristics can achieve fast, feasible solution at run-time with no guarantee on the qualit...

On-Demand Transport (ODT) systems have attracted increasing attention in recent years. Traditional centralized dispatching can achieve optimal solutions, but NP-Hard complexity makes it unsuitable for online and dynamic problems. Centralized and decentralized heuristics can achieve fast, feasible solution at run-time with no guarantee on the qualit...

On-Demand Transport (ODT) systems have attracted increasing attention in recent years. Traditional centralized dispatching can achieve optimal solutions with NP-Hard complexity, making it unsuitable for online and dynamic problems. Decentralized approaches can achieve fast feasible solution at run-time with no guarantee on the quality. Starting fro...

Dans le cadre du transport à la demande (TAD), l'appariement centralisé traditionnel permet d'obtenir des solutions optimales, mais reste NP-difficile et donc inadapté aux problèmes en ligne et dynamiques. Les approches décentralisées permettent d'obtenir des solutions réalisables en temps réel, mais sans garantie de qualité. Ici, nous considérons...

This work is interested in decentrally solving a taxi allocation problem over a fleet of autonomous taxis. Classically, to solve this problem, requests are centralized into a portal where a dispatcher allocates requests to taxis (ideally, in an optimal manner). This requires taxis have continuous access to the portal. However, getting access to suc...

A wide variety of Intelligent Transportation Systems (ITS) are developed to increase travel safety, improve traffic management and minimize environmental impact. C-ITS (cooperative ITS) are a subclass of ITS based on the communication between the vehicles and/or communication between the vehicles and the infrastructure. C-ITS are promising solution...

A wide variety of Intelligent Transportation Systems (ITS) are developed to increase travel safety, improve traffic management and minimize environmental impact. C-ITS (cooperative ITS) are a subclass of ITS based on the communication between the vehicles and/or communication between the vehicles and the infrastructure. C-ITS are promising solution...

An Advanced Traveler Information System (ATIS) aims at providing travelers with multi-modal trip planning, route guidance services and advisory functions. Most ATIS's provide travel solutions that cover only specific geographic areas, travel modes and/or transport operators, and are insufficiently personalized. Moreover, the solutions are normally...

Multi-goal pathfinding (MGPF) is a problem of searching for a path between a start and a destination that allows a set of goals to be satisfied along the path. In this paper, we address MGPF in the context of ubiquitous environments such as airports, commercial centers and smart campuses that accommodate cyber, physical and social entities from sma...

Multi-goal pathfinding (MGPF) is a problem of searching for a path between a start and a destination allowing a set of goals to be satisfied. We address MGPF in ubiquitous environments that accommodate cyber, physical and social (CPS) entities from smart objects to sensors and to humans. Given a MGPF problem in a pervasive environment, our approach...

Multi-goal pathfinding (MGPF) is a problem of searching for a path between an origin and a destination, which allows a set of goals to be satisfied. We are interested in MGPF in ubiquitous environments that are composed of cyber, physical and social (CPS) entities from connected objects, to sensors and to people. Our approach aims at exploiting dat...

Abstract In this paper, we define the online localized resource allocation problem, especially relevant for modeling transportation applications. The problem modeling takes into account simultaneously the geographical location of consumers and resources together with their online nondeterministic appearance. We use urban parking management as an il...

The use of new information and communication technologies has become a central solution to improve transport systems. What has led to which is called the Intelligent Transport Systems (ITS). Societal challenges for ensuring their effective implementations are crucial both to respond to users needs, and to design sustainable transport systems. In th...

The environment, as a space shared between agents is essential to multi-agents systems (MAS). Depending on the systems, it responds to different points of view. It is described as physical or communicative as that agents interact through situated actions or exchanging messages, or social if a social model governs the interactions. Each of these vie...

The environment, as a space shared between agents is essential to multi-agents systems (MAS). Depending on the systems, it responds to different points of view. It is described as physical or communicative as that agents interact through situated actions or exchanging messages, or social if a social model governs the interactions. Each of these vie...

The development of surface public transportation networks is a major issue in terms of ecology, economy and society. Their quality in terms of punctuality and passengers services (regularity between buses) should be improved in order to improve their attractiveness. To do so, cities often use regulation systems at intersections that grant priority...

The environment, as a space shared between agents, is a key component of multiagent systems (MAS). Depending on systems, this space may integrate physical, communication or social dimensions. Each of them has its own process and rules to support agents' interaction. The dimensions of the environment are generally connected either outside of the age...

The environment, as a space shared between agents, is a key component of multiagent systems (MAS). Depending on systems, this space may integrate physical, communication or communication dimensions. Each of them has its own process and rules to support agents' interaction. The dimensions of the environment are generally connected either outside of...

The environment, as a space shared between agents, is a key component of multiagent systems (MAS). Depending on systems, this space may integrate physical, communication or social dimensions. Each of them has its own process and rules to support agents' interaction. For instance, in the physical dimension, the rules may be based on the agents' loca...

JFSMA'2014 - 22èmes Journées Francophones sur les Systèmes Multi-Agents, LORIOL SUR DROME, FRANCE, 08-/10/2014 - 10/10/2014

L'environnement, en tant qu'espace partagé entre agents, est un élément essentiel des systèmes multiagents. Selon les systèmes, cet espace intègre des dimensions différentes comme une dimension physique support à l'ancrage spatial et à l'activité des agents sur cette dimension, ou une dimension sociale support aux communications entre agents. Ces d...

In most multiagent-based simulation (MABS) frameworks, a scheduler activates the agents who compute their context and decide the action to execute. This context computation by the agents is executed based on information about themselves, the other agents and the objects of the environment that are accessible to them. The issue here is the identific...

Awareness is a concept that has been frequently studied in the context of Computer Supported Cooperative Work. However, other fields of computer science can benefit from this concept. Recent research in the multi-agent systems field has highlighted the relevance of complex interaction models such as multi-party communication and context awareness f...

Cet article traite des questions de sécurité des systèmes multi-agents dans les langages de coordination orientés données. Ces langages se fondent sur un espace de données partagées par les agents et utilisées pour coordonner leurs activités. Nous étendons ces langages avec un mécanisme de sécurité fondé sur des conditions associées à toute donnée...

In this paper, we define the online localized resource allocation problem, especially relevant for modeling transportation applications. This model takes into account simultaneously the dynamic locations of the resources and the consumers, together with their online nondeterministic appearance. We instantiate the model with the urban parking manage...

In the context of road urban traffic management, the problem of parking spots search is a major issue because of its serious economic and ecological fallout. In this paper, we propose a multi-agent system that aims to decrease, for private vehicles drivers, the parking spots search time. In the system that we propose, a community of drivers shares...

This paper proposes a bimodal urban traffic control strategy based on a multi-agent model. We call bimodal traffic, a traffic which takes into account both private vehicles and public vehicles such as buses. The objective of this research is to improve global traffic, to reduce bus delays and to improve bus regularity in congested areas of the netw...

Agent-based simulation is used to understand complex systems and to experiment several scenarios. In classical simulation frameworks, a pitfall is the fact that the action phase, based on local agent context analysis, is repeated in each agent at each time cycle during the simulation execution. This analysis inside the agents reduces agent flexibil...

The environment is a powerful first-order abstraction in Multi-Agent Systems (MAS), as well as a critical building block. The agents interact in their environment and the effects of their actions are observed and evaluated through this environment. The local complexity of the agents depends on its management of the interaction and action processes....

In the context of road urban traffic management, the problem of parking spots search is a major issue because of its serious economic and ecological fallout. In this paper, we propose a multi-agent system that aims to decrease, for private vehicles drivers, the parking spots search time. In the system that we propose, a community of drivers shares...

In the context of road urban trafic management, the problem of parking spots search is a major issue because of its serious economic and ecological fallout. In this paper, we propose a multiagent system that aims to decrease, for private vehicles drivers, the parking spots search time. In the system that we propose, a drivers community shares infor...

The development of surface public transportation networks is a major issue in terms of ecology, economy and society. Their quality in term of punctuality and passengers services(regularity between buses) should be improved. To do so, cities often use regulation systems at junctions that grant priority to buses. However, most of them hardly take int...

This paper proposes a bimodal urban traffic control strategy based on a multi-agent model. We call bimodal traffic a traffic which takes into account private vehicles and public transport vehicles such as buses. The objective of this research is to improve global traffic and reduce the time spent by buses in traffic jams so that buses cope with the...

The environment has emerged as a powerful first-order abstraction in Multi-Agent Systems (MAS), as well as a critical building block. One benefit is to reduce the complexity of the agents by delegating to the environment a part of the tasks of the system. This delegating process provides a flexible way to exchange information and to coordinate the...

This paper proposes a strategy of urban bimodal traffic regulation based on multi-agent modelization. The objective of this strategy is to work on the duration of the traffic lights to regulate traffic for transport modes that include private and public transport vehicles, principally the bus. The model respects the method of bus regulation with a...

http://www.lamsade.dauphine.fr/scripts/FILES/publi1433.pdf

Multi-party communications taking place within organizations lead to different interaction modes such as (in)direct communication between roles, (in)direct communication restricted to a group, etc. Fully normative organisations need to regulate and control those modes as they do for agents’ behaviors. However, this problem is not well addressed in...

Multi-agent-based simulation (MABS) is used to understand complex real life processes and to experiment several scenarios in order to reproduce, understand and evaluate these processes. A crucial point in the design of a multi-agent-based simulation is the choice of a scheduling policy. In classical multi-agent-based simulation frameworks, a pitfal...

This paper presents an agent-based approach used to design a Transportation Regulation Support System (TRSS), that reports the network activity in real-time and thus assists the bus network regulators. The objective is to combine the functionalities of the existing information system with the functionalities of a decision support system in order to...

The multiagent paradigm is well suited to designing trans-portation applications. However, when implementing such applications in highly dynamic environments, it is very costly to use languages relying on channel-based communication. Data driven coordination languages rely on a shared space in which agents add, read and retrieve data. They are intu...

La version Working paper s'intitule "Agents Secure Interaction in Data driven Languages". Parution dans la seérie LNCS n°6039, http://dx.doi.org/10.1007/978-3-642-13338-1_5 This paper discusses the security issues in data driven coordination languages. These languages rely on a data space shared by the agents and used to coordinate their activities...

In this paper, our objective is to minimize passengers waiting times at the bus stops by making buses wait at a stop. We compare a simple rule based approach to a Monte-Carlo method to reach this objective. When allocated enough time, the Monte-Carlo method gives better results. If the passengers arrivals and the bus travel times are known, the bes...

Data-oriented coordination languages rely on a shared space in which agents add, read and retrieve data. They are intuitively well suited for distributed transportation applications, where different actors evolve in a highly dynamic and very constrained environment. However, existing coordination languages can hardly be used for transportation appl...

Series: Lecture Notes in Computer Science. Subseries: Lecture Notes in Artificial Intelligence , Vol. 5559 Data-oriented coordination languages rely on a shared space in which agents add, read and retrieve data. They are intuitively well suited for distributed transportation applications, where di erent actors evolve in a highly dynamic and very co...

Recent research in the multi-agent systems field has highlighted the relevance of complex interaction models such as multi-party communication and context awareness. Nevertheless, there are no generic interaction model and infrastructure that enable to apply them in a standardized way. Emerging as a first-order abstraction, the environment, in the...

Revue des Nouvelles Technologies de l'Information RNTI-E-15 oui

Abstract—This paper,discusses,the,security,issues in data driven,coordination,languages. These languages,rely on a data space shared by the agents and used to coordinate their activities. We extend these languages with a main distinguishing feature, which is the possibility to define fine-grained security conditions, associated with every datum,in...

Many companies aim to use Web services to integrate heterogeneous and/or remote applications in SOA (Service Oriented Architecture) contexts. We noticed the code of the Web service is monolithic, mixing concerns, and difficult to maintain. On top of all, any change requires to re deploy the modified Web service. Business rules are very often spread...

In this paper we want to minimize passengers waiting times at the bus stops by making buses wait at a stop. We compare a simple rule based approach to a Monte- Carlo method for this problem. When allocated enough time, the Monte-Carlo method gives better results. If the passengers arrivals and the bus travel times are known, the best algorithm is n...

This paper presents an environment-centered approach to design multi-agent solutions to transportation problems. Based on the property-based coordination principle (PbC), the objective of our approach is to solve three recurrent issues in the design of these solutions: the knowledge problem, the space-time dimension and the dynamics of the real env...

Recent research on multi-party communications shows how multi-agent communications can take advantage of the complexity of the human communication process. The salient point is the very nature of the communication channels which enable humans to focus their attention on ambient communications, as well as to direct their own communications. For mult...

Cet article présente une approche reposant sur la modélisation d'un environnement multi-agent pour la conception d'applications dédiées au domaine du transport. Fondée sur le principe PbC (Property-based Coordination), cette approche a pour objectif la résolution de trois difficultés récurrentes dans la conception de ces applications : le problème...

In this paper, we propose a multi-agent approach to solve a hard combinatorial problem: the vehicle routing problem with time win-dows. A multi-agent approach is most relevant when dealing with the dynamic version of the problem, where all the customers are not known before the start of the solving process. We focus on both the interac-tion process...

Atelier Systèmes d'Information en Transport oui

Le titre de la conférence annoncé sur le site du Lamsade est "Vers un Modèle d'Interaction Générique et Opérationnel pour les Systèmes Multi-Agents". Bien que les dialogues bi-parties soient les plus étudiés dans la communauté des Systèmes Multi- Agents (SMA), certains nouveaux modèles tels que l'écoute flottante et les communications multiparties...

This paper presents a Transportation Decision Support System (TDSS) called SATIR that reports the network activity in real-time and thus assists the bus network regulators in their various tasks. We propose a global approach to help regulators to manage the bus network under normal conditions (network monitoring, dynamic schedule management), with...

LNCS n°4696, http://dx.doi.org/10.1007/978-3-540-75254-7_6 Two-party communication is the most-studied model to support interaction between two cognitive agents, whereas that is only one case of what an agent should be able to do. Multi-party communications enhance this model, by taking into account all the roles an agent can have in a communicatio...

When designing agent-based simulation, the choice of a coordination model is a key issue, since one of the difficulties is to link the activation of the agents with their context efficiently. Current solutions separate the activation phase from the action phase of the agents, and each action phase is based on local agent context analysis which is t...