A – Título: What Artificial Intelligence has to do with Traffic
B – Área de concentração
c – exatas ( x ) engenharia, matemática, química, outra (ciência da computação)
C – Autor (es): Ana Lúcia Cetertich Bazzan
D – Dr. Ing.
E – Instituição de pesquisa ou de trabalho: UFRGS
F - Summary:
Transportation systems are complex systems that have a huge impact in the economy of the nations. The second half of the last century has seen the beginning of the phenomenon of traffic congestion. This arose due to the fact that the demand for mobility in our society has increased constantly.
Traffic congestion is a phenomenon caused by too many vehicles trying to use the same infrastructure at the same time. The consequences are well-known: delays, air pollution, decrease in speed, driver unsatisfaction which may lead to risk manouvers thus reducing safety for pedestrians as well as for other drivers.
The increase in transportation demand can be met by providing additional capacity. However, this is no longer be economically or socially attainable or feasible. Thus, the emphasis has shifted to improving the existing infrastructure without increasing the overall nominal capacity, by means of an optimal utilization of the available capacity.
Among the measures that can be taken, perhaps the most important is to improve the management of the transportation and traffic systems by use of recent developments in the areas of communication and information technology. Here, Artificial Intelligence can provide a key contribution, especially if we consider the Brazilian scenario within the next years when the country hosts two important events (World Soccer Cup and Olympic Games).
Recent developments such as intelligent traffic information system can provide the user of the transportation system with a variety of informations regarding alternative routes, detours, load of the network, and even expected travel time. However information per se does not guarantee efficiency. It is necessary that a change in paradigm occur in order to fully profit from technological advances that we experience nowadays.
Target technologies for this change in paradigm are: vehicle automation (e.g. cruise control), road automation (e.g. smart highways), embedded components (e.g. GPS and mobile devices), car2car communication, control devices based on images and cameras, information totems, tracking for public transportation systems, podcars, etc.
Techniques from Artificial Intelligence in general and Multiagent Systems in particular fit these concepts very well given the need to reproduce human behavior in pedestrian and vehicular
simulation, facilitate the distributed optimization and control, regulate road pricing mechanisms, as well as manage the integration of diverse kinds of systems at various levels of decision-making.
Four paradigmatic examples are i) the autonomous guided vehicles (see and the recently launched Ultra PRT at Heathrow Airport – ii) distributed control of traffic lights; iii) information for route choice; and iv) microscopic simulation of pedestrian and crowds.
References:
BAZZAN, A. L. C.
Opportunities for multiagent systems and multiagent reinforcement learning in traffic control
In Autonomous Agents and Multiagent Systems, 18(3): 342-375, 2009.
BAZZAN, A. L. C. Traffic as a Complex System: Four Challenges for Computer Science and Engineering. In: XXXIV SEMISH, 2007, Rio de Janeiro. v. 1. p. 2128-2142.
M. Papageorgiou, Traffic control, in: R. W. Hall (Ed.), Handbook of Transportation Science, Kluwer Academic Pub, 2003, Ch. 8, pp. 243- 277.
F.-Y. Wang, Toward a revolution in transportation operations: AI for complex systems, IEEE Intelligent Systems 23 (6) (2008) 8-13.