{"url":"/dataset/rgb-stacking","name":"RGB-Stacking","full_name":null,"description_markdown":"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.\r\n\r\nImage source: [https://github.com/deepmind/rgb_stacking](https://github.com/deepmind/rgb_stacking)","description_withheld":null,"homepage":"https://github.com/deepmind/rgb_stacking","introduced_date":"2021-10-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/beyond-pick-and-place-tackling-robotic","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","first_author":"Alex X. Lee","url":null},"license":{"name":"Apache 2.0 license","url":"https://github.com/deepmind/rgb_stacking/blob/main/LICENSE"},"modalities":[{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[{"name":"Visual Tracking","url":"/task/visual-tracking","datasets_with_task":"/datasets/task/visual-tracking"},{"name":"Skill Generalization","url":"/task/skill-generalization","datasets_with_task":"/datasets/task/skill-generalization"},{"name":"Skill Mastery","url":"/task/skill-mastery","datasets_with_task":"/datasets/task/skill-mastery"}],"languages":[],"variants":["RGB-Stacking"],"data_loaders":[],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/skill-generalization-on-rgb-stacking","task":"Skill Generalization","dataset_variant":"RGB-Stacking","rows":2,"metrics":["Group 1","Group 2","Group 3","Group 4","Group 5","Average"],"first_row_in_archive_order":{"model":"Gato","paper":"/paper/a-generalist-agent","metrics":{"Average":"50.2","Group 1":"24.5","Group 2":"33","Group 3":"50.5","Group 4":"76.5","Group 5":"66.5"},"code_links":[{"title":"OrigamiDream/gato","url":"https://github.com/OrigamiDream/gato"},{"title":"ManifoldRG/gato-control","url":"https://github.com/ManifoldRG/gato-control"},{"title":"LAS1520/Gato-A-Generalist-Agent","url":"https://github.com/LAS1520/Gato-A-Generalist-Agent"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/skill-mastery-on-rgb-stacking","task":"Skill Mastery","dataset_variant":"RGB-Stacking","rows":2,"metrics":["Average","Group 1","Group 2","Group 3","Group 4","Group 5"],"first_row_in_archive_order":{"model":"Gato","paper":"/paper/a-generalist-agent","metrics":{"Average":"75.6","Group 1":"58","Group 2":"57.6","Group 3":"78.5","Group 4":"89","Group 5":"95.1"},"code_links":[{"title":"OrigamiDream/gato","url":"https://github.com/OrigamiDream/gato"},{"title":"ManifoldRG/gato-control","url":"https://github.com/ManifoldRG/gato-control"},{"title":"LAS1520/Gato-A-Generalist-Agent","url":"https://github.com/LAS1520/Gato-A-Generalist-Agent"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-tracking-on-rgb-stacking","task":"Visual Tracking","dataset_variant":"RGB-Stacking","rows":2,"metrics":["Average Jaccard"],"first_row_in_archive_order":{"model":"TAPIR (MOVi-E)","paper":"/paper/tapir-tracking-any-point-with-per-frame","metrics":{"Average Jaccard":"66.2"},"code_links":[{"title":"deepmind/tapnet","url":"https://github.com/deepmind/tapnet"},{"title":"riponazad/echotracker","url":"https://github.com/riponazad/echotracker"},{"title":"ibaiGorordo/Tapir-Pytorch-Inference","url":"https://github.com/ibaiGorordo/Tapir-Pytorch-Inference"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/tapir-tracking-any-point-with-per-frame","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","date":"2023-06-14","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-generalist-agent","title":"A Generalist Agent","date":"2022-05-12","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/beyond-pick-and-place-tackling-robotic","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","date":"2021-10-12","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":3,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}