แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Jirayu Petchhan. Better learning to drive autonomously with proximal-policy reinforcement learning and visual perception representations. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2025.
Better learning to drive autonomously with proximal-policy reinforcement learning and visual perception representations
Name: Jirasak Sittigorn
Organization :
King Mongkut's Institute of Technology Ladkrabang. School of Engineering
Email :
jirasak.si@kmitl.ac.th
Name: Racha Tungtrakool
Organization :
King Mongkut's Institute of Technology Ladkrabang. School of Engineering
Email :
65010902@kmitl.ac.th
Name: Jirayu Petchhan
Organization :
King Mongkut's Institute of Technology Ladkrabang. School of Engineering
Email :
jirayu.pe@kmitl.ac.th
LCSH:
Autonomous vehicle
LCSH:
Artificial intelligence
LCSH:
Machine learning
LCSH:
Reinforcement learning
Abstract:
This study presents an approach based on a deep reinforcement learning framework for vision-based autonomous driving in the CARLA environment, focusing on urban driving tasks. The proposed system implements a sub-policy Proximal Policy Optimization (PPO) algorithm and demonstrates its effectiveness in navigating complex scenarios, including lane following, straight driving, and left/right turns. The sub-policy strategy outperforms a single-policy approach in handling intersection maneuvers.
To enhance learning efficiency, the model employs representation learning using a deep mobile network for state representation, significantly reducing image feature complexity. In addition, the integration of a single-shot multi-box detector enables the agent to perform realistic driving behaviors, such as responding to traffic lights and maintaining safe distances from leading vehicles, without compromising training speed.
Although the system demonstrates stable driving performance in various scenarios, limitations remain in handling highly complex decision-making situations and adapting to diverse speed limits due to environmental constraints. Future work will focus on expanding training environments and exploring more advanced network architectures to improve real-world applicability and learning efficiency.
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2025
Modified:
2026-02-24
Issued:
2026-02-24
บทความ/Article
application/pdf
BibliograpyCitation :
In Prince of Songkla University, Phuket Campus. College of Computing. The 9th International Conference on Information Technology (InCIT 2025) (pp.195-200). Phuket : Prince of Songkla University
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.041446 วินาที
Jirasak Sittigorn
| Title | Contributor | Type |
|---|---|---|
| Better learning to drive autonomously with proximal-policy reinforcement learning and visual perception representations
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Jirasak Sittigorn;Racha Tungtrakool;Jirayu Petchhan | บทความ/Article |
Racha Tungtrakool
| Title | Contributor | Type |
|---|---|---|
| Better learning to drive autonomously with proximal-policy reinforcement learning and visual perception representations
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Jirasak Sittigorn;Racha Tungtrakool;Jirayu Petchhan | บทความ/Article |
Jirayu Petchhan
| Title | Contributor | Type |
|---|---|---|
| Better learning to drive autonomously with proximal-policy reinforcement learning and visual perception representations
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Jirasak Sittigorn;Racha Tungtrakool;Jirayu Petchhan | บทความ/Article | |
| Enhancing X-resolution integration through federated learning-based building learning ecosystems
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Thana Hongsuwan;Chaksawat Rueangaram;Thanith Kongsmoot;Jirayu Petchhan | บทความ/Article | |
| Better aware of anticipating customer attrition in telecommunications via enhanced tabular learning networks
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Jirayu Petchhan;Alhakim, Muhammad Firdaus | บทความ/Article |