Title
A multi-objective approach to evolving platooning strategies in intelligent transportation systems
Author
van Illigen, W.
Haasdijk, E.
Kester, L.J.H.M.
Publication year
2013
Abstract
The research in this paper is inspired by a vision of intelligent vehicles that autonomously move along motorways: they join and leave trains of vehicles (platoons), overtake other vehicles, etc. We propose a multi-objective evolutionary algorithm based on NEAT and SPEA2 that evolves highlevel controllers for such intelligent vehicles. The algorithm yields a set of solutions that each embody their own priori-tisation of various user requirements such as speed, comfort or fuel economy. This contrasts with the current practice in researching such controllers, where user preferences are summarised in a single number that the controller development process then optimises. Proof-of-concept experiments show that evolved controllers substantially outperform a widely used human behavioural model. We show that it is possible to evolve a set of vehicle controllers that correspond with different prioritisations of user preferences, giving the driver, on the road, the power to decide which preferences to emphasise. Copyright © 2013 ACM.
Subject
Physics & Electronics
DSS - Distributed Sensor Systems
TS - Technical Sciences
Safe and Clean Mobility
Defence
Mobility
Intelligent transportation systems
Multi-objective optimisation
Neuro-evolution
Platooning
To reference this document use:
http://resolver.tudelft.nl/uuid:82a0ab32-0431-47c2-bda4-5f1df13650d1
DOI
https://doi.org/10.1145/2463372.2463534
TNO identifier
478830
Publisher
ACM, New York, NY
Source
15th Genetic and Evolutionary Computation Conference, GECCO 2013, 6-10 July 2013, Amsterdam, Netherlands, 1397-1404
Document type
conference paper