Ahura: A heuristic-based racer for the open racing car simulator

Bonyadi, Mohammad Reza, Michalewicz, Zbigniew, Nallaperuma, Samadhi and Neumann, Frank (2016) Ahura: A heuristic-based racer for the open racing car simulator. IEEE Transactions on Computational Intelligence and AI in Games, . doi:10.1109/TCIAIG.2016.2565661


Author Bonyadi, Mohammad Reza
Michalewicz, Zbigniew
Nallaperuma, Samadhi
Neumann, Frank
Title Ahura: A heuristic-based racer for the open racing car simulator
Journal name IEEE Transactions on Computational Intelligence and AI in Games   Check publisher's open access policy
ISSN 1943-068X
1943-0698
Publication date 2016-05-10
Year available 2016
Sub-type Article (original research)
DOI 10.1109/TCIAIG.2016.2565661
Open Access Status Not Open Access
Total pages 37
Place of publication Piscataway, United States
Publisher Institute of Electrical and Electronics Engineers
Collection year 2017
Language eng
Formatted abstract
Designing automatic drivers for car racing is an active field of research in the area of robotics and artificial intelligence. A controller called Ahura (A HeUristic-based RAcer) for The Open Racing Car Simulator (TORCS) is proposed in this paper. Ahura includes five modules, namely steer controller, speed controller, opponent manager, dynamic adjuster, and stuck handler. These modules have 23 parameters all together that are tuned using an evolutionary strategy for a particular car to ensure fast and safe drive on different tracks. These tuned parameters are further modified by the dynamic adjuster module during the run according to the width, friction, and dangerous zones of the track. The dynamic adjustment enables Ahura to decide on-the-fly based on the current situation, hence, it eliminates the need for prior knowledge about the characteristics of the track. The driving performance of Ahura is compared with other state-of-the-art controllers on 40 tracks when they drive identical cars. Our experiments indicate that Ahura performs significantly better than other controllers in terms of damage and completion time especially on complex tracks (road tracks). Also, experiments show that the overtaking strategy of Ahura is safer and more effective comparing to other controllers. 
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: HERDC Pre-Audit
Centre for Advanced Imaging Publications
 
Versions
Version Filter Type
Citation counts: Google Scholar Search Google Scholar
Created: Wed, 13 Jul 2016, 15:00:39 EST by Ms Kate Rowe on behalf of Learning and Research Services (UQ Library)