Comparing Pre-Trained Object Detection Models for Autonomous Grasp on Affordable Prosthetic Hands
Bibliographic record
Abstract
While prosthetic technology has advanced significantly in recent years, discomfort, poor fit, and functional limitations still contribute to high rejection rates among users who feel more efficient without the prosthesis. In the field of prosthetics, improving the stability of grasp and natural control is crucial for reducing rejection rates. By improving these aspects, the user can reduce the likelihood of complications arising, such as discomfort or pain. The integration of vision technology, a novel prosthetic approach, holds immense promise for revolutionizing how we design and use prosthetic devices. Incorporating advanced vision algorithms into prosthetic devices can augment users' sensory capabilities and enhance their interaction with the surrounding environment. Vision-based prostheses offer the potential for more intuitive and natural control, enabling users to manipulate objects with greater precision and dexterity. This paper presents preliminary insights into rejection rates and the utilization of vision-based grasping in robotics, with implications for prosthetic applications. In this study, we investigate the performance of Mobilenet SSD, YOLOv5m, and YOLOv5l in autonomous grasp tasks across two distances, providing valuable data on their adaptability in real-world contexts. Our analysis delves into the effectiveness of vision-based grasping algorithms in grasp experiments with intact subjects, showing successful grasp attempts ranging from 84% to 92% in two different distances and three different grasp types.
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 | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".