Autonomous Ping Pong Ball Collector
Bibliographic record
Abstract
This paper aims to document and showcase the process of a final-year Computer Engineering Capstone project at Toronto Metropolitan University. The goal was to create a fully autonomous vehicle capable of detecting and collecting scattered ping pong balls across a flat plane through the use of computer vision, machine learning and computer engineering. This involved several key components such as collecting an image dataset through a high res camera, training a machine learning model on said dataset using the Mobilenet SSD V2 neural network architecture for the purposes of object detection, assembling and integrating hardware components such as motors and servos with their respective wirings and power management, working with NVIDIA Jetson Nano and it's interfaces, and using python/C++ to program scripts to help coordinate all of the different functions. This project was a collaborative effort that involved the integration of these different software and hardware components, and this paper attempts to concisely highlight the technical details of each component and explain how it integrates with the rest of the system in order to achieve the goal of autonomously collecting ping pong balls. Upon completion of the capstone term, the project was deemed a success and was demonstrated to the respective FLC, and was shown at the capstone showcase at Toronto Metropolitan University.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".