DESIGN OF INTELLIGENT CRUISE CONTROLLER OF MOTOR VEHICLES
International Journal of Mechatronics and Applied Mechanics, cilt.2023, sa.13, ss.193-197, 2023 (Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 2023 Sayı: 13
- Basım Tarihi: 2023
- Doi Numarası: 10.17683/ijomam/issue13.23
- Dergi Adı: International Journal of Mechatronics and Applied Mechanics
- Derginin Tarandığı İndeksler: Scopus
- Sayfa Sayıları: ss.193-197
- Anahtar Kelimeler: Adaptive Cruise Control, DDPG, Reinforcement Learning
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Erciyes Üniversitesi Adresli: Evet
Özet
Nowadays, due to traffic jam and many cars on traffic, it is very necessary to control the distance between cars and obstacle. Many car producers have been designed and manufacture Cruise Control Systems for cars. Reinforcement learning, one of the popular artificial intelligence techniques, is a method used to train autonomous systems in many different fields. In this simulation study, the adaptive cruise control (ACC) of a ring bus serving in the campus area is controlled with Deep Deterministic Policy Gradient, which is one of the reinforcement learning methods. This simulation study is carried out considering the speed limit in the campus area and the acceleration values required for a comfortable journey of the passengers. Acceleration, velocity and distance values are given with graphs. Consequently; the proposal neural predictor has superior performance to adapt and predict the distance, velocity and acceleration of ego vehicle (bus).