RGB-Stacking is a benchmark for vision-based robotic manipulation. The robot is trained to learn how to grasp objects and balance them on top of one another.
Image source: https://github.com/deepmind/rgb_stacking
Variants: RGB-Stacking
This dataset is used in 3 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Visual Tracking | TAPIR (MOVi-E) | TAPIR: Tracking Any Point with … | 2023-06-14 |
| Visual Tracking | TAPIR (Panning MOVi-E) | TAPIR: Tracking Any Point with … | 2023-06-14 |
| Skill Generalization | Gato | A Generalist Agent | 2022-05-12 |
| Skill Mastery | Gato | A Generalist Agent | 2022-05-12 |
| Skill Generalization | BC - IMP | Beyond Pick-and-Place: Tackling Robotic Stacking … | 2021-10-12 |
| Skill Mastery | BC-IMP | Beyond Pick-and-Place: Tackling Robotic Stacking … | 2021-10-12 |
Recent papers with results on this dataset: