Real-time algorithm for table tennis with a desktop robotic arm
Bibliographic record
Abstract
Table tennis with collaborative robots has been a challenge in robotics for decades, due to its unique challenges, especially high-speed movements and real-time ball trajectory predictions for responsive and accurate gameplay. Over the years, several table tennis robots have been developed, showing progressively enhanced abilities for returning balls, hitting specific targets, rallying with collaborative human users, and playing amateur-level games. However, these robotic systems remain costly for individuals, often relying on industrial components, or specialized designs. Emerging AI-integrated personal desktop robotic arms could help bridge the performance gap between affordable personal robotic systems and traditional industrial robots, particularly in terms of dexterity, speed, and precision. Despite this potential, desktop robotic arms have not yet been used for table tennis. However, existing table tennis algorithms require specific adaptations to accommodate the constraints of desktop robots. This paper aims to develop a dedicated algorithm for a collaborative table tennis system using a desktop robotic arm to demonstrate the achievable performance of AI-integrated desktop robots. The proposed system utilizes a 5-degree-of-freedom (DOF) serial robot, integrating advanced algorithms and machine learning models to improve performance. This system enables short collaborative rallies, returning 71.3% of balls overall, improving to 81.4% after fine-tuning system parameters — approaching the best one from the literature (88%) using a 7-DOF industrial robotic arm. This underscores the potential of affordable, AI-integrated desktop robotic arms for high-speed human–robot collaboration. Future works will focus on adapting the algorithm for specialized desktop hardware, expanding desktop robots to other applications, and further enhancing their performance.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.012 | 0.003 |
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".