Road Traffic Rules Synthesis Using Grammatical Evolution

Conference paper

DOI: 10.1007/978-3-319-55792-2_12

Part of the Lecture Notes in Computer Science book series (LNCS, volume 10200)
Cite this paper as:
Medvet E., Bartoli A., Talamini J. (2017) Road Traffic Rules Synthesis Using Grammatical Evolution. In: Squillero G., Sim K. (eds) Applications of Evolutionary Computation. EvoApplications 2017. Lecture Notes in Computer Science, vol 10200. Springer, Cham

Abstract

We consider the problem of the automatic synthesis of road traffic rules, motivated by a future scenario in which human and machine-based drivers will coexist on the roads: in that scenario, current road rules may be either unsuitable or inefficient. We approach the problem using Grammatical Evolution (GE). To this end, we propose a road traffic model which includes concepts amenable to be regulated (e.g., lanes, intersections) and which allows drivers to temporarily evade traffic rules when there are no better alternatives. In our GE framework, each individual is a set of rules and its fitness is a weighted sum of traffic efficiency and safety, as resulting from a number of simulations where all drivers are subjected to the same rules. Experimental results show that our approach indeed generates rules leading to a safer and more efficient traffic than enforcing no rules or rules similar to those currently used.

Keywords

Simulation Road traffic model Stochastic evolution Driverless cars 

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Engineering and ArchitectureUniversity of TriesteTriesteItaly

Personalised recommendations