Javier J. Sánchez Medina

Stochastic vs deterministic traffic simulator. comparative study for its use within a traffic light cycles optimization architecture

Last year we presented at the CEC2004 conference a novel architecture for traffic light cycles optimization. The heart of this architecture is a Traffic Simulator used as the evaluation tool (fitness function) within the Genetic Algorithm. Initially we allowed the simulator to have a random behavior. Although the results from this sort of simulation were consistent, it was necessary to run a huge amount of simulations before we could get a significant value for the fitness of each individual of the population . So we assumed some simplifications to be able to use a deterministic simulator instead of the stochastic one. In this paper we will confirm that it was the right decision; we will show that there is a strong linear correlation between the results of both simulators. Hence we show that the fitness ranking obtained by the deterministic simulator is as good as the obtained with the stochastic one.

Evolutionary Computation Applied to Urban Traffic Optimization

At the present time, many sings seem to indicate that we live a global energy and environmental crisis. The scientific community argues that the global warming process is, at least in some degree, a consequence of modern societies unsustainable development. A key area in that situation is the citizens mobility. World economies seem to require fast and efficient transportation infrastructures for a significant fraction of the population. The non-stopping overload process that traffic networks are suffering calls for new solutions. In the vast majority of cases it is not viable to extend that infrastructures due to costs, lack of available space, and environmental impacts. Thus, traffic departments all around the world are very interested in optimizing the existing infrastructures to obtain the very best service they can provide. In the last decade many initiatives have been developed to give the traffic network new management facilities for its better exploitation. They are grouped in the so called Intelligent Transportation Systems. Examples of these approaches are the Advanced Traveler Information Systems (ATIS) and Advanced Traffic Management Systems (ATMS). Most of them provide drivers or traffic engineers the current traffic real/simulated situation or traffic forecasts. They may even suggest actions to improve the traffic flow. To do so, researchers have done a lot of work improving traffic simulations, specially through the development of accurate microscopic simulators. In the last decades the application of that family of simulators was restricted to small test cases due to its high computing requirements. Currently, the availability of cheap faster computers has changed this situation. Some famous microsimulators are MITSIM(Yang, Q., 1997), INTEGRATION (Rakha, H., et al., 1998), AIMSUN2 (Barcelo, J., et al., 1996), TRANSIMS (Nagel, K. & Barrett, C., 1997), etc. They will be briefly explained in the following section. Although traffic research is mainly targeted at obtaining accurate simulations there are few groups focused at the optimization or improvement of traffic in an automatic manner — not dependent on traffic engineers experience and “art”. O pe n A cc es s D at ab as e w w w .ite ch on lin e. co m

Study of correlation among several traffic parameters using evolutionary algorithms: traffic flow, greenhouse emissions and network occupancy

During the last two years we have been working on the optimisation of traffic lights cycles. We designed an evolutionary, distributed architecture to do this. This architecture includes a Genetic Algorithm for the optimisation. So far we have performed a single criterion optimisation - the total volume of vehicles that left the network once the simulation finishes. Our aim is to extend our architecture towards a multicriteria optimisation. We are considering Network Occupancy and Greenhouse Emissions as suitable candidates for our purpose. Throughout this work we will share a statistical based study about the two new criteria that will help us to decide whether to include them or not in the fitness function of our system. To do so we have used data from two real world traffic networks.

A General Purpose Approach for Global and Local Path Planning Combination

Path planning is a key and complex element for every unmanned ground vehicle development. Once the 3D reconstruction of the environment is completed and the objective configuration (desired position and pose) is defined, there has to be a careful path planning algorithm. That path is subject to many restrictions: it has to be time optimal, we have limited degrees of freedom to work with since the vehicle is a non-holonomic robot, we have limited computational power and real-time constraints regarding on-board equipments, and finally the vehicles mechanical limitations, like the maximum curvature. In this paper we present a new methodology for the path planning calculation. It was meant to be a one for all methodology, useful for different scenarios (automotive, industrial applications, mining, etc.) and different platforms (car-like vehicles, forklift trucks, etc.). This paper splits the problem in two stages. The first one faces the problem of reaching the goal with an a priori knowledge of the position affected by noise. The second approach develops a system capable of reaching the goal, enhancing the precision using a detection system, mainly based on computer vision. Particular focus is given to the interaction between the two methods proposed.

Traffic Signals in Traffic Circles: Simulation and Optimization Based Efficiency Study

Traffic Circles are frequently used in cities, to control vehicular traffic at intersections. As said in [1], their main advantages can be the provision of an adequate throughput and the improvement of user safety, by slower vehicle speeds and reducing traffic conflicts.

A Simple Classification Approach to Traffic Flow State Estimation

One of the most important elements in the mobility of the developed cities is the road traffic management. The mobility determines the quality of citizens’ living conditions because of many reasons, security, efficiency, and the environmental impact. Focusing on security, according to World Health Organization (WHO), every year two millions of people die as a result of traffic accidents. Moreover between twenty and fifty millions of people suffer non-fatal injuries and a proportion of these people suffer from a disability. These injuries affect both the family economy and the country. For this reason, amongst others, it is required to equip the mobility managers with the proper tools to get a precise idea about the current situation and estimate future state. These tools facilitate the decision-making and the development of mobility.