Safety prompt advanced driver-assistance system

• Main Author: Shu, Haozhan
• Other Authors: Su Rong
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: https://hdl.handle.net/10356/173224
• Institution: Nanyang Technological University

This Dissertation is centered around the implementation of an advanced driver-assistance system within the Euro Truck Simulator 2 environment. Its core components encompass an exploration of the research context, the design of the advanced driver-assistance system, the execution of experiments and subse-quent results analysis, and the formulation of conclusive remarks along with future prospects. In the section devoted to the design of the advanced driver-assistance system, an exhaustive exposition is provided concerning the target de-tection module, employing YOLOv6, the lane detection module employing CLR-Net, the depth estimation module utilizing the Monodepth2 algorithm, and the environmental perception module. The control algorithm design section eluci-dates the development of the PID control algorithm, the lateral control algorithm for low-speed scenarios, and the decision scene switching algorithm. Within the section dedicated to system realization and testing, an initial introduction is fur-nished regarding the utilized hardware and software platforms. Subsequently, an elaborate delineation of the experimental setting (Euro Truck Simulator 2) is presented, accompanied by a comprehensive analysis of the outcomes obtained from target detection, lane detection, and depth estimation. The dissertation culminates with system testing, analysis, comparative evaluations of experimen-tal results, and in-depth discussions. Lastly, in the conclusion and prospective outlook section, the dissertation consolidates the research achievements and un-derscores identified shortcomings, offering recommendations for future enhance-ments. It also offers an overview of potential research avenues to explore in the future. Through perusing this scholarly document, readers can gain a comprehensive understanding of the intricacies involved in conceiving and realizing an advanced driver-assistance system operating within the Euro Truck Simulator 2 environment. The document further imparts insights through rigorous analysis and comparisons of experimental results. Furthermore, it elucidates the current research landscape within this domain and outlines promising directions for fu-ture investigations.