A multi-objective approach to evolving platooning strategies in intelligent transportation systems

Willigen, Willem van; Haasdijk, Evert; Kester, Leon

doi:10.1145/2463372.2463534

Cited by 18 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of the experiments show that the method still holds when substantially increasing the number of objectives. It performs marginally worse, and the resulting nondominated set of controllers is slightly smaller than the results we found in previous work [3], but this was expected and the results are not significantly worse.…”

Section: Discussionsupporting

confidence: 45%

“…In earlier work [3], we did similar work, but only with 2 objectives. These objectives are the ones that we also analysed in detail above, travel time and lane changes.…”

Section: Results and Analysismentioning

confidence: 99%

“…In earlier work [3], we showed that the NEAT-Pareto Strength (NEAT-PS) approach did indeed yield a useful set of controllers that embodied prioritisations of 2 different objectives. In this paper, we extend the method with 4 additional objectives.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast, comfortable or economical: Evolving platooning strategies with many objectives

Willigen

Haasdijk

Kester

2013

16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013)

Self Cite

View full text Add to dashboard Cite

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 that evolves high-level controllers for such intelligent vehicles. The algorithm yields a set of solutions that each embody their own prioritisation 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.In this article, we test our multi-objective approach on 6 objectives. Our method outperforms a widely used human behavioural model on many of the objectives. Some performance is lost when we introduce additional objectives, but these losses are small and therefore acceptable. 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, although we do see that the more objectives are added to the system, the less intuitive the prioritisation of the different objectives becomes.

show abstract

Section: Discussionsupporting

confidence: 45%

“…In earlier work [3], we did similar work, but only with 2 objectives. These objectives are the ones that we also analysed in detail above, travel time and lane changes.…”

Section: Results and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Fast, comfortable or economical: Evolving platooning strategies with many objectives

Willigen

Haasdijk

Kester

2013

16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013)

Self Cite

View full text Add to dashboard Cite

show abstract

“…A(p,c) is the function which incorporates overall effect in the positive personality profile (16). Negative personality profile S N (17) is computed using the current value of negative personality profile and overall effect in personality profile S C .…”

Section: S B S S B S S B S S B S Smentioning

confidence: 99%

“…The primary reason of extending this simulator was the modularity of the software which allowed extension of the existing simulator to incorporate CDM in it. Movsim has been used in several studies [1,16,17].…”

Section: Simulationmentioning

confidence: 99%