Pengaplikasian Kalman Filter sebagai Pengendali dalam Permainan The Open Racing Car Simulator (TORCS)

Abstract

The Open Racing Car Simulator (TORCS) works as both a playable game and a framework to develop artificial intelligence-based controllers. As a platform for researchers, TORCS has become a platform in controller development with various approaches in artificial intelligence using sensors and actuators provided by the SCR Server via the SimpleDriver architecture. In this research, the author develops a controller using the Kalman Filter, an algorithm to predict and measure states based on previous measurements to determine future trajectory with Rapid Application Development (RAD) chosen as the development method. The test took place in 5 different circuits available from the TORCS installation to compare its performance with another controller. The test result showed that KalmanDriver, the developed controller, has an adequate average performance close enough to results in a non-noisy setting and against another controller in noisy setting, both in terms of fastest times and top speeds.