Driving as a human: A track learning based adaptable architecture for a car racing controller

Quadflieg J., Preuss M., Rudolph G.


Abstract
We present the evolution and current state of the Mr. Racer car racing controller that excelled at the corresponding TORCS competitions of the last years. Although several heuristics and black-box optimization methods are employed, the basic idea of the controller architecture has been to take over many of the mechanisms human racing drivers apply. They learn the track geometry, plan ahead, and wherever necessary, adapt their plans to the current circumstances quickly. Mr. Racer consists of several modules that have partly been adapted and optimized separately, where the final tuning is usually done with respect to a certain racing track during the warmup phase of the TORCS competitions. We also undertake an experimental evaluation that investigates how the controller profits from adding some of the modules to a basic configuration and which modules are most important for reaching the best possible performance. © 2014 Springer Science+Business Media New York.

Keywords
Car racing; Evolutionary computation; Planning controller; TORCS



Publication type
Research article (journal)

Peer reviewed
Yes

Publication status
Published

Year
2014

Journal
Genetic Programming and Evolvable Machines

Volume
15

Issue
4

Start page
433

End page
476

Publisher
Springer New York LLC

Language
English

ISSN
1389-2576

DOI

Full text