Wardana, Mochammad Revi Fikri (2025) Perancangan Sistem Adaptive Cruise Control (ACC) Pada Autonomous Vehicle Menggunakan Optimasi Genetic Algorithm (GA) Berbasis Robot Operating System (Ros) Dan Car Learning To Act (CARLA). Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5009211090-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5009211090-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy |
Abstract
Perkembangan teknologi kendaraan otonom menuntut sistem kontrol longitudinal yang adaptif terhadap lingkungan dinamis. Penelitian ini merancang dan mengimplementasikan sistem Adaptive Cruise Control (ACC) pada kendaraan otonom berbasis Dynamic Window Approach (DWA) yang dioptimasi menggunakan Genetic Algorithm (GA) dalam lingkungan Robot Operating System (ROS) 2 Foxy dan simulator CARLA 0.9.13. Sistem ACC dirancang untuk mengatur kecepatan kendaraan berdasarkan empat zona jarak aman, yaitu emergency, critical, warning, dan safe distance, berdasarkan jarak kendaraan terhadap obstacle dinamis yang dideteksi sensor LiDAR. Parameter jarak dan kecepatan adaptif ditentukan melalui proses optimasi GA dengan fungsi objektif yang mempertimbangkan safety score. Sistem diuji dalam skenario simulasi dengan 35 objek dinamis di peta Town 01 CARLA. Hasil evaluasi menunjukkan bahwa sistem mampu menjaga jalur dengan rata-rata path error sebesar 1.19 meter, serta mempertahankan beban komputasi rata-rata sebesar 35.83%. Sistem juga merespons kondisi lalu lintas seperti pejalan kaki dan lampu merah dengan penyesuaian kecepatan yang halus. Penelitian ini menunjukkan bahwa pendekatan ACC berbasis zona jarak aman dan optimasi evolusioner dapat menjadi solusi efektif untuk pengendalian longitudinal kendaraan otonom, serta membuka potensi integrasi lebih lanjut dengan sistem kontrol lateral dan persepsi.
=======================================================================================================================================
The advancement of autonomous vehicle technology demands a robust longitudinal control system that can adapt to dynamic environments. This research designs and implements an Adaptive Cruise Control (ACC) system for autonomous vehicles based on the Dynamic Window Approach (DWA), optimized using a Genetic Algorithm (GA) within the Robot Operating System (ROS) 2 Foxy and CARLA 0.9.13 simulator. The ACC system is designed to regulate vehicle speed based on four safe distance zones: emergency, critical, warning, and safe, determined by the distance between the ego vehicle and dynamic obstacles detected via LiDAR sensors. Distance and speed parameters were optimized using GA, with an objective function that considers safety score. Experiments were conducted in a simulated environment with 35 dynamic obstacles in CARLA’s Town 01 map. The results show that the system maintained the vehicle trajectory with an average path error of 1.19 meters, while sustaining a mean computational load of 35.83%. The system also successfully responded to traffic light signals and pedestrian crossings by smoothly adjusting speed. This research demonstrates that a zone-based ACC approach combined with evolutionary optimization can be an effective solution for longitudinal control in autonomous vehicles, and holds promise for future integration with lateral control and perception systems.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Autonomous Vehicle, Adaptive Cruise Control, Genetic Algorithm, ROS |
| Subjects: | Q Science > QA Mathematics > QA402.5 Genetic algorithms. Interior-point methods. T Technology > TJ Mechanical engineering and machinery > TJ217 Adaptive control systems T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL152.8 Vehicles, Remotely piloted. Autonomous vehicles. |
| Divisions: | Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis |
| Depositing User: | Mochammad Revi Fikri Wardana |
| Date Deposited: | 05 Aug 2025 08:21 |
| Last Modified: | 05 Aug 2025 08:21 |
| URI: | http://repository.its.ac.id/id/eprint/127215 |
Actions (login required)
 |
View Item |