Section A: Project Information
This project leverages a simple race car simulation to introduce the fundamentals of supervised learning in an engaging, hands-on manner. By programming a virtual race car to navigate a track, students explore key concepts in machine learning, such as data collection, model training, and performance evaluation. The project integrates a gamified approach to learning, making abstract technical principles accessible to beginners while maintaining rigor for advanced learners.
Key innovations include the use of a visually appealing race car simulation to demystify complex AI concepts and a modular design that allows students to focus on specific aspects of supervised learning without being overwhelmed.
With potential applications in classrooms, workshops, and self-paced online courses, this project has the power to enhance AI literacy among students and educators. By fostering curiosity and encouraging practical engagement, it equips participants with skills that are increasingly relevant in the modern workforce.
Section B: Participant Information
| Title | First Name | Last Name | Organisation/Institution | Faculty/Department/Unit | Phone Number | Current Study Programme | Current Year of Study | Contact Person / Team Leader | |
|---|---|---|---|---|---|---|---|---|---|
| Mr. | Jiafei | Wang | The Education University of Hong Kong | Faculty of Liberal Arts and Social Sciences | s1151618@s.eduhk.hk | 51062157 | Diploma | Year 1 |
|
Section C: Project Details
The growing importance of AI and machine learning in today’s world demands educational tools that are both accessible and effective. However, many educational resources on machine learning are either overly theoretical or too complex for beginners, creating a gap in understanding for students without advanced technical backgrounds.
This project was inspired by the need for an intuitive and engaging way to teach supervised learning, a foundational concept in machine learning. The idea of a race car simulation was chosen for its universal appeal and ability to visually demonstrate abstract concepts, such as how a model improves performance over time.
The underlying hypothesis is that interactive, gamified learning experiences improve student engagement and comprehension compared to traditional, lecture-based teaching methods. By providing a hands-on activity, students can directly observe the impact of their decisions on the performance of a supervised learning model, making the learning process tangible and memorable. The combination of visual feedback (e.g., the race car navigating the track) and iterative model improvement closely mirrors real-world machine learning workflows, making it a practical and effective teaching tool.
None
The project is implemented using Python, employing the tkinter library for the graphical user interface (GUI) and interactive components. Its functional architecture consists of the following key components:
Input Interface: Allows users to assign weights to sensor-action mappings for each car, simulating supervised learning by using weights to determine car behavior.
Game Environment: A simulation environment with a visually interactive racetrack, where cars navigate based on user-defined weights and real-time sensor data.
Physics and Logic Engine: Governs car movement, collision detection, lap tracking, and sensor input processing.
Visualization and Feedback: Displays the cars on the track, their states (e.g., laps completed, steps taken), and their interactions with the environment in real-time.
Key Technical Features
Weight Configuration: Users input specific sensor-action weights via a tkinter-based table interface. These weights define how cars respond to sensor input (e.g., forward, left, or right).
Sensor Data Simulation: Cars use virtual sensors to detect distances to track boundaries in four directions (front, back, left, and right). Sensor readings dynamically update as cars move.
Customizable Racetrack: Racetrack geometry (e.g., width, borders) is programmatically defined, enabling scalability for future enhancements like more complex tracks or obstacles.
Decision Logic: Cars calculate scores for actions by multiplying sensor data with user-defined weights, selecting the action with the highest score to determine their next move.
Relationship Between Functions and Technologies
Function Point Technical Application Progress
Sensor Logic Raycasting Algorithm (Math) Completed
Decision-making Process Matrix Multiplication Completed
Visualization Tkinter Canvas + Geometry Completed
This project reimagines machine learning education by combining technical rigor with gamification. The use of a race car simulation to teach supervised learning is both novel and engaging, offering a creative departure from traditional, theory-heavy approaches. Unlike existing educational tools, this project emphasizes active learning through direct interaction with models and real-time visual feedback.
The gamified nature of the project fosters curiosity and experimentation. For instance, users can compete to achieve the fastest lap time through better data labeling or model optimization. This interactive approach helps demystify the machine learning process, making it more approachable for beginners.
By balancing innovation and accessibility, the project effectively bridges the gap between theoretical knowledge and practical application, making it a valuable tool for educators, students, and self-learners alike.
Scalability is built into the project’s modular design. The simulation can be expanded to include more complex track layouts, additional machine learning algorithms (e.g., reinforcement learning), and multiplayer functionality, allowing multiple users to collaborate or compete.
To address potential bottlenecks, the system employs lightweight frameworks and optimized code, ensuring smooth performance even on basic hardware. Regular feedback from users will guide updates and improvements, ensuring the platform evolves to meet their needs.
Long-term user engagement will be fostered through ongoing challenges, such as weekly competitions or new track releases. The system’s adaptability ensures it remains relevant as user needs and educational standards evolve.
This project addresses the critical need for AI literacy in an increasingly technology-driven world. By making supervised learning accessible and engaging, it empowers students from diverse backgrounds to explore opportunities in AI, reducing barriers to entry for beginners.
Personal Information Collection Statement (PICS):
1. The personal data collected in this form will be used for activity-organizing, record keeping and reporting only. The collected personal data will be purged within 6 years after the event.
2. Please note that it is obligatory to provide the personal data required.
3. Your personal data collected will be kept by the LTTC and will not be transferred to outside parties.
4. You have the right to request access to and correction of information held by us about you. If you wish to access or correct your personal data, please contact our staff at lttc@eduhk.hk.
5. The University’s Privacy Policy Statement can be access at https://www.eduhk.hk/en/privacy-policy.
- I have read and agree to the competition rules and privacy policy.