Rosaldo J. F. Rossetti

Using BDI agents to improve driver modelling in a commuter scenario

The use of multi-agent systems to model and to simulate real systems consisting of intelligent entities capable of autonomously co-operating with each other has emerged as an important field of research. This has been applied to a variety of areas, such as social sciences, engineering, and mathematical and physical theories. In this work, we address the complex task of modelling drivers’ behaviour through the use of agent-based techniques. Contemporary traffic systems have experienced considerable changes in the last few years, and the rapid growth of urban areas has challenged scientific and technical communities. Influencing drivers’ behaviour appears as an alternative to traditional approaches to cope with the potential problem of traffic congestion, such as the physical modification of road infrastructures and the improvement of control systems. It arises as one of the underlying ideas of intelligent transportation systems. In order to offer a good means to evaluate the impact that exogenous information may exert on drivers’ decision making, we propose an extension to an existing microscopic simulation model called Dynamic Route Assignment Combining User Learning and microsimulAtion (DRACULA). In this extension, the traffic domain is viewed as a multi-agent world and drivers are endowed with mental attitudes, which allow rational decisions about route choice and departure time. This work is divided into two main parts. The first part describes the original DRACULA framework and the extension proposed to support our agent-based traffic model. The second part is concerned with the reasoning mechanism of drivers modelled by means of a Beliefs, Desires, and Intentions (BDI) architecture. In this part, we use AgentSpeak(L) to specify commuter scenarios and special emphasis is given to departure time and route choices. This paper contributes in that respect by showing a practical way of representing and assessing drivers’ behaviour and the adequacy of using AgentSpeak(L) as a modelling language, as it provides clear and elegant specifications of BDI agents.

Playing Transportation Seriously: Applications of Serious Games to Artificial Transportation Systems

A discussion of the potential integration of serious games into the conceptual framework of artificial transportation systems focuses on behavior elicitation through peer-designed agents to model and simulate artificial societies on a participative basis.

An approach to simulate autonomous vehicles in urban traffic scenarios

The most common cause of traffic accidents is arguably the driver error due to lack of attention. And it is very unlikely this is going to change soon thanks to increasingly cell-phone usage, in-car entertainment systems, and naturally the more frequent traffic jams in highly populated areas. Autonomous vehicles, such as driverless cars, are a promising approach to decrease traffic accidents, as well as congestions. To test this approach, simulations are a safer, more efficient, and cheaper way than live testing. This paper presents an approach to implement a simulator to test such vehicles. It includes a study of the state of the art in driverless car simulation and discusses on the specific objectives that this particular simulator aims to achieve in order to aid testing the interactions of multiple driverless cars in urban networks.

An integrated architecture for autonomous vehicles simulation

Modeling and simulation tools are being increasingly acclaimed in the research field of autonomous vehicles systems, as they provide suitable test beds for the development and evaluation of such complex systems. However, these tools still do not account for some integration capabilities amongst several state-of-the-art Intelligent Transportation Systems, e.g. to study autonomous driving behaviors in human-steered urban traffic scenarios, which are crucial to the Future Urban Transport paradigm. In this paper we describe the modeling and implementation of an integration architecture of two types of simulators, namely a robotics and a traffic simulator. This integration should enable autonomous vehicles to be deployed in a rather realistic traffic flow as an agent entity (on the traffic simulator), at the same time it simulates all its sensors and actuators (on the robotics counterpart). Also, the statistical tools available in the traffic simulator will allow practitioners to infer what kind of advantages such a novel technology will bring to our everydays lives. Furthermore, an architecture for the integration of the aforementioned simulators is proposed and implemented in the light of the most desired features of such software environments. To assess the usefulness of the platform architecture towards the expected realistic simulation facility, a comprehensive system evaluation is performed and critically reviewed, leveraging the feasibility of the integration. Further developments and future perspectives are also suggested.

IC-DEEP: A serious games based application to assess the ergonomics of in-vehicle information systems

With the number of in-vehicle information systems and the complexity of their tasks growing at a very high rate in near future, we need a clear understanding of their related distraction or mental workload and its impact on driver performance. Thus, in this paper we introduce these concepts already in the development phase of a product that will be used in an in-vehicle environment. We present the IC-DEEP (In-Car Ergonomics Evaluation Platform), which is an implementation approach in form of a Serious Game (SG) to autonomously assess, under low-time and low-cost conditions, the factors that can jeopardize the driving performance when manipulating or receiving information from in-vehicle information systems (IVISs). We evaluate the feasibility of the proposed approach and draw conclusions on its effects on behavioral changes and IVIS assessment.

A Dynamic Network Simulation Model Based on Multi-Agent Systems

This paper reports on how the abstraction approach of multi-agent systems can be used to represent the complexity inherent in the urban traffic domain, accounting for the importance of modelling travellers’ behaviour and their interaction with intelligent transportation technologies. A key premise in the approach proposed is the identification of what we have coined autonomous decision entity, which is defined as an agent shell to structure the way agents can be implemented and inserted into the environment. Such a structure is very flexible in the sense it is only defined in meta-level, comprising sensors, effectors and a reasoning kernel. The conceptual multi-agent model is presented and implemented within the DRACULA simulation suite, which is used for simulation experiments on the analysis of drivers’ route and departure time choice.

A HLA-based multi-resolution approach to simulating electric vehicles in simulink and SUMO

Traffic congestion affects not only the economic activity of cities but is also responsible for air quality and global warming problems. The employment of electric buses in metropolitan transportation as an alternative to internal combustion engine buses appears to be a promising eco-sustainable solution. However, an important aspect in evaluating the performance and adequateness of such vehicles is the fact they are immersed in an urban context. This work follows a HLA-based distributed architecture for electric bus powertrain simulation within a realistic urban mobility environment. In that sense, it discusses on coupling the SUMO (Simulation of Urban MObility) microscopic traffic simulator with a model of an electric bus powertrain subsystem designed in the MatLab/Simulink environment. Both the electric bus traction subsystems and the integration have been validated using field test experimental data. The proposed simulation framework is multi-faceted. As a matter of fact it can be used, not only as electric vehicle evaluation tool under different dynamics of traffic conditions and driving behavior, but also as a planner for charging strategies and optimizations.

Guest Editorial Special Issue on Artificial Transportation Systems and Simulation

The seven regular papers and one short paper in this special issue focus on artificial transportation systems and simulation.

TraSMAPI: An API oriented towards Multi-Agent Systems real-time interaction with multiple Traffic Simulators

TraSMAPI (Traffic Simulation Manager Application Programming Interface) is designed to provide real-time interaction with Traffic Simulators, collect relevant metrics and statistics, and offer an integrated framework to develop Multi-Agent Systems. It is presented as a tool for the simulation of dynamic control systems in road networks with special focus on Multi-Agent Systems. The abstraction over the simulator opens up the possibility of running different traffic simulators using the same API (application programming interface) allowing the comparison of results of the same application in different simulators. The proposed approach is, therefore, expected to be a key asset in supporting and enhancing engineers and practitioners to make more effective control decisions and implement more efficient management policies while analyzing and addressing traffic related problems in urban areas.

A Cooperative Simulation Framework for Traffic and Transportation Engineering

As contemporary intelligent transportation systems are becoming a reality in our everydays life and future urban transportation brings about concerns of a wide range of new performance measures, multidisciplinary teams are more and more faced with the need to work collaboratively so as to meet those demands. This paper reports on the specification of the MAS-T2er Lab framework, emphasising on its ability to support collaborative simulation and different perspective analyses of the complex and dynamic application domain of traffic and transportation in major urban areas. The architecture underlying all subsystems within the framework is discussed on the basis of the multi-agent systems metaphor, and a practical overview of its use is presented.