KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Subject: search.filters.subject.Autonomous vehicle

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Better Learning to Drive Autonomously with Proximal-Policy Reinforcement Learning and Visual Perception Representations
    (2025-01-01)
    Sittigorn, Jirasak
    ;
    Tungtrakool, Racha
    ;
    Petchhan, Jirayu
    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. Our study implements a sub-policy Proximal Policy Optimization (PPO) algorithm, demonstrating its effectiveness in navigating complex scenarios including lane following, straight driving, and left/right turns, and outperforming a single-policy approach for intersection maneuvers. To enhance learning efficiency, our representation learning leverages a deep mobile network for state representation, which significantly reduces image feature complexity. Furthermore, the integration of a single-shot multi-box detector enables the agent to perform realistic tasks such as responding to traffic lights and maintaining safe distances from leading vehicles, without compromising training speed. While the system demonstrates stable driving in various scenarios, current limitations include handling highly complex decisions 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.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Driving Dilemmas: A Qualitative Exploration of Autonomous Vehicle Use in Thailand
    (2024-01-01)
    Sithanant, Thana
    ;
    Chaiyasoonthorn, Wornchanok
    ;
    Chaveesuk, Singha
    This study explores the intricacies of autonomous vehicle (AV) acceptance within the unique landscape of Thailand where AV adoption remains a challenge despite some global success. Employing an in-depth interview methodology, our research is based on grounded theory in a qualitative approach, aiming to provide an understanding of this phenomenon. Our investigation is based on semi-structured interviews with 19 regular AV users, chosen after thorough background verification to ensure the research's credibility. These interviews, ranging from 45 to 60 min, facilitated an in-depth exploration of the subject matter. Employing ATLAS.ti software, one intriguing revelation from our study is the counterintuitive behavior of the participants: All Thai AV drivers regularly deactivate the autonomous functions of their AVs. Among others, this phenomenon is influenced by several factors, including Thailand's distinct traffic conditions, the unpredictable of local driving behaviors, and pervasive trust issues regarding the capabilities of autonomous systems. We meticulously detail the complexities surrounding AV adoption, shedding light on the multifaceted nature of the challenge. Our discussion offers a nuanced understanding of the factors contributing to the preference for manual control among Thai AV users, providing valuable information for policymakers, industry stakeholders, and researchers seeking to comprehend the intricacies of AV acceptance. In conclusion, this research serves as a foundational resource for future investigations by facilitating more effective strategies for AV integration in diverse global contexts.