A Constructivist Approach for a Self-Adaptive Decision-Making System: Application to Road Traffic Control

Guériau, Maxime; Armetta, Frédéric; Hassas, Salima; Billot, Romain; Faouzi, Nour‐Eddin El

doi:10.1109/ictai.2016.0107

Cited by 15 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intuitively, the cognitive growth of an intelligent system would imply the evolution/extension of both very specific knowledge and overall dynamics coordinating the several learning-related aspects. In the last decade, constructivist approaches have been used for smart environments [12,13] and transport systems [14]. The studies contributing to these aspects provide contributions highly specialized in simplistic and very structured domains [15].…”

Section: Imagination In Humansmentioning

confidence: 99%

Towards Explainable Visionary Agents: License to Dare and Imagine

Ciatto

Najjar

Calbimonte

et al. 2021

Explainable and Transparent AI and Multi-Agent Systems

View full text Add to dashboard Cite

Since their appearance, computer programs have embodied discipline and structured approaches and methodologies. Yet, to this day, equipping machines with imaginative and creative capabilities remains one of the most challenging and fascinating goals we pursue. Intelligent software agents can behave intelligently in well-defined scenarios, relying on Machine Learning (ML), symbolic reasoning, and the ability of their developers for tailoring smart behaviors to specific application domains. However, to forecast the evolution of all possible scenarios is unfeasible. Thus, intelligent agents should autonomously/creatively adapt to the world's mutability. This paper investigates the meaning of imagination in the context of cognitive agents. In particular, it addresses techniques and approaches to let agents autonomously imagine/simulate their course of action and generate explanations supporting it, and formalizes thematic challenges. Accordingly, we investigate research areas including: (i) reasoning and automatic theorem proving to synthesize novel knowledge via inference; (ii) automatic planning and simulation, used to speculate over alternative courses of action; (iii) machine learning and data mining, exploited to induce new knowledge from experience; and (iv) biochemical coordination, which keeps imagination dynamic by continuously reorganizing it.

show abstract

Section: Imagination In Humansmentioning

confidence: 99%

Towards Explainable Visionary Agents: License to Dare and Imagine

Ciatto

Najjar

Calbimonte

et al. 2021

Explainable and Transparent AI and Multi-Agent Systems

View full text Add to dashboard Cite

show abstract

“…For example, in [20], the authors exploit the advantage of using the anticipatory behaviours of agents in multi-agent coordination for the simulation of traffic at intersections. In [21], a constructivist learning control model is proposed to facilitate traffic regulation. For traffic flow optimization, Ksontini et al [22] propose a model based on an egocentric representation of the traffic environment that exploits the heterogeneity of vehicles and the drivers' behaviours.…”

Section: Human-agent Interaction Modelsmentioning

confidence: 99%

Game Theory-based Human-Assistant Agent Interaction Model

Razakatiana

Kolski

Mandiau

et al. 2020

Proceedings of the 8th International Conference on Human-Agent Interaction

View full text Add to dashboard Cite

As road traffic is becoming increasingly dense, new needs in terms of intelligent human-machine interaction are emerging for their control by human operators. One avenue of research consists in assisting them in their control task by an assistant agent. This paper presents a feasibility study in this field, involving interactions between humans and an assistant agent. For this purpose, a game theory-based model is proposed in order to be able to model a context-sensitive system for the cooperative realization of complex tasks. In this case, the participants of the game are human operators and an assisting agent interacting within the framework of the realization of a control task. Thus, each participants can choose an action between two possible ones (to cooperate or not). Then, the proposed utility functions allow to build the context-sensitive payoff matrix at each observation cycle of the human-machine interaction. To validate our model, we have implemented a simulated control situation; it concerns the regulation of traffic through intersections; this involves two human operators and an assistant agent. Thus, the assistant agent uses the game payoff matrix for its decision-making in using Nash equilibrium. This paper describes a feasibility study, focusing on an analysis of the results obtained during the execution of the simulation. Different research perspectives arise from this study in order to improve and generalize the proposed model.

show abstract

“…Further methods were based on Multi-agent systems to control traffic at signalized intersections in a distributed way [24]. Moreover, in [25] an approach enabling to combine a set of traditional learning methods was proposed for self-adaptive decision making. Petri nets have been introduced for traffic modelling and control in [8] then many other works have been proposed for modelling and controlling traffic into road network intersections [9], [10].…”

Section: Literature Reviewmentioning

confidence: 99%

An Adaptive Control Strategy of Urban Signalized Intersection Using Petri Nets

Idrissi

Tajer

Nait-Sidi-Moh

et al. 2018

2018 International Conference on Control, Automation and Diagnosis (ICCAD)

View full text Add to dashboard Cite

The dynamic behavior of traffic signals controlling an isolated intersections can be seen as a discrete event system that can be modeled by Petri nets. The approach used in this paper proposes an adaptive control strategy of urban signalized intersection in real time using T-timed Petri Nets (T-TPNs). This strategy allows to manage the green light time autonomously according to the queue size for each flow in each lane of the intersection. A decentralized approach is proposed for the decision-making, where every phase in the intersections can be considered as a subsystem to be modelled and controlled (by traffic lights) separately, then a global controller allows to manage the conflicts between several phases.

show abstract

A Constructivist Approach for a Self-Adaptive Decision-Making System: Application to Road Traffic Control

Cited by 15 publications

References 16 publications

Towards Explainable Visionary Agents: License to Dare and Imagine

Towards Explainable Visionary Agents: License to Dare and Imagine

Game Theory-based Human-Assistant Agent Interaction Model

An Adaptive Control Strategy of Urban Signalized Intersection Using Petri Nets

Contact Info

Product

Resources

About