Tactile Contact Patterns for Robotic Grasping: A Dataset of Real and Simulated Data
Bibliographic record
Abstract
Advancing tactile sensing in robotics and machine learning necessitates high-quality datasets encompassing realworld and simulated interactions. In this paper, we present a comprehensive dataset containing 46,200 samples collected from a deformable, capacitive-based tactile sensor. The dataset is equally divided into three main groups: 15,400 real samples, 15,400 synthetic samples generated using Abaqus, and 15,400 synthetic samples generated using Isaac Gym through finite element analysis (FEA). Data acquisition was performed under two experimental scenarios. In the first scenario, 49 unique indenters were pressed onto the sensor at various force levels, producing various contact patterns. In the second scenario, the sensor was integrated into a 2F-85 Robotiq parallel gripper to grasp 12 different objects. We provide a detailed account of the dataset construction process, elaborate on its composition, and introduce a graphical user interface that enables the creation of customized datasets tailored to specific application needs. Ultimately, we present a case study employing Transfer Learning to exemplify the dataset's potential by utilizing real and synthetic data to recognize surface types (flat or curved), showcasing how synthetic data can be effectively leveraged alongside real data to enhance performance. To access the code and resources used in this research, all files are available in our GitHub repository at [TactileDataset](https://github.com/Lab-CORO/TactileDataset).
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".