|
An adaptive traffic light control system using reinforcement learning |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Kietikul Jearanaitanakij 2. Chanayut Jamkhaw 3. Nattapat Puangpipat 4. Tot Worasrivisal |
| Title | An adaptive traffic light control system using reinforcement learning |
| Publisher | Research and Development Office, Prince of Songkla University |
| Publication Year | 2565 |
| Journal Title | Songklanakarin Journal of Science an Technology (SJST) |
| Journal Vol. | 44 |
| Journal No. | 4 |
| Page no. | 914-922 |
| Keyword | traffic signal control, transportation, reinforcement learning, adaptive green light time, wasteful green light problem |
| URL Website | https://rdo.psu.ac.th/sjst/index.php |
| ISSN | 0125-3395 |
| Abstract | Traffic signal control (TSC) is a challenging issue in managing an urban transportation system. A fixed time TSC iseasy to implement but has drawbacks in such measures as flow rate, waiting time, and traffic density. The situation gets worsewhen the arrival rates of vehicles periodically change over time, which is usual in most urban cities. We propose adaptivereinforcement learning (RL) to manage TSC with varying vehicle arrival rates. Our objectives are to improve the averages offlow rate and waiting time and reduce the wasteful green light problem by considering the vehicle densities of the current laneand the downstream directions. Experiments were conducted by Simulation of Urban MObility (SUMO) under three trafficlayouts and various vehicle arrival rates. The proposed method not only reduced on average traffic density, waiting time, andqueue length, but also increased the average flow rate and average speed, relative to the other algorithms tested. |
