Thorogood, Alistair (2023) Formula SAE – Simulation & Autonomous Control. [USQ Project]
![[img]](https://sear.unisq.edu.au/style/images/fileicons/text.png) |
Text (Project – redacted)
Thorogood_A_Tobias_Redacted.pdf Download (5MB) |
Abstract
The Society of Automotive Engineers (SAE) have been running a student-based racing competition the Formula SAE (FSAE) since 1981, there are currently over 600 competing teams from universities all over the world. The competition has evolved, with the automotive industry, to include an electric vehicle class since 2013 and an autonomous vehicle class since 2017.
This thesis project is intended to serve as an initial entry into Autonomous FSAE development for the UniSQ team. To achieve this, three project aims were developed and successfully achieved.
Project Aim 1: Set up and Test Simulation Environment A range of existing Formula Student simulators were evaluated and the Formula Student Driverless Simulator was found to be most suitable for this project. The Simulator was installed, tested, and utilised for the development of basic self-driving.
Project Aim 2: Demonstrate Basic Self-Driving Basic self-driving was demonstrated utilising C++ and python with the ROS2 robotics framework. ROS2 nodes were created for traffic cone perception, steering angle determination, throttle position, and vehicle control. A final lap time of 82.21 seconds was achieved, a significant improvement from the initial lap time of 160.37 seconds.
Project Aim 3: Establish UniSQ FSAE Autonomous Development Platform A git repository containing the ROS2 workspace was utilised as the development platform. This contained all nodes for basic self-driving, improved perception and visualisation tools used throughout the development.
Above the aims of this project, an effective and robust LiDAR based perception algorithm was developed based off the Velodyne VLP-16 LiDAR. Using the VLP-16 LiDAR allowed for easier integration into a real-world vehicle. Within the simulator the perception range was improved from 7m to greater than 20m. The improved simulation perception allows for future simulated autonomous development in; motion estimation and mapping, and vehicle control.
|
Statistics for this ePrint Item |
| Item Type: | USQ Project |
|---|---|
| Item Status: | Live Archive |
| Faculty/School / Institute/Centre: | Current – Faculty of Health, Engineering and Sciences - School of Engineering (1 Jan 2022 -) |
| Supervisors: | Lobsey, Craig; Low, Tobias |
| Qualification: | Bachelor of Engineering (Honours) (Mechatronics) |
| Date Deposited: | 02 Oct 2025 01:22 |
| Last Modified: | 02 Oct 2025 01:23 |
| Uncontrolled Keywords: | Autonomous FSAE |
| URI: | https://sear.unisq.edu.au/id/eprint/53008 |
Actions (login required)
 |
Archive Repository Staff Only |
