Titulo Estágio
COSMO - Using error to optimize the city
Área Tecnológica
Sistemas Móvies e Ubíquos
Local do Estágio
CISUC
Enquadramento
A common criticism to systems such as TomTom is that, while they are locally able to optimize a route, globally, they favour traffic jams instead of help avoiding them. The reason is simple: everyone having the same information leads to the similar decisions. The alternative of IQroutes is an aid to those that are attentive to the real-time evolution of traffic, but it may be too late. The initial plan might have been too bad.
In COSMO, we explore the idea of purposely spreading information with error among drivers. Such error consists mostly of changing the weights of the road network (i.e. distance of links). If done properly, theoretically, it is possible to dissolve the traffic using secondary roads.
In year 1, a prototype for a simulator was developed that enables early experiments such as some simple collaborative routing algorithms. The next step is to improve both the simulator and allow for more complex routing algorithm, leading to credible scientific experiments.
Objetivo
The goal of this project is to improve the simulation environment, an idealized world where we are able to simulate the individuals behaviours. These behaviours are individually very simple (just follow the best path according to their destination and road network data) while the overall results might be complex (e.g. a traffic jam). In practice, we will experiment differente types of algorithms, namely based on swarm intelligence and evolutionary computation.
The student will work on the well-known simulation project, SUMO (http://sumo.sourceforge.net/), particularly on the extension that was developed during year 1. Further more s/he will focus on the "Coimbra" case study:
based on an available Origin-Destination matrix on the map (already adapted to COSMO/SUMO), it will be possible to simulate traffic in the entire city with believable origin and destination flows, obtained from field surveys.
Plano de Trabalhos - Semestre 1
The tentative plan for this project (semester 1) is the following:
- October 15th â State of the art (1.5 months)
- October 31st - Understanding simulation platform + OD matrix (2 months)
- November 30th - Implementation of first collaborative routing algorithm (1 month)
- December 15th â Experimentation. (1 month)
- January 15th - Improvement of first algorithm (2 months)
- February 27th - Intermediate report. Plan for new developments on the system of the following semester. (1 month)
Plano de Trabalhos - Semestre 2
The tentative plan for this project (semester 2) is the following:
- April 30th - Implementation of new developments (2 months)
- May 31th - Experiments report. Paper submission. (1 month)
- June 30th - MSc thesis delivery. (1 month)
Condições
Strong skills in programming.
Will to communicate in English with other researchers is also important.
Other interesting skills include Complex Systems and Artificial Intelligence
Observações
Estágio Remunerado
Orientador
Fernando Penousal Machado e João Oliveirinha
machado@dei.uc.pt 📩