DavidSunok commited on
Commit
2ea37b7
·
verified ·
1 Parent(s): 9aae59b

Add selected 16,000 ClickBell trajectories under real_data/clickbell

Browse files
real_data/clickbell/DATASET_INFO.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "task": "clickbell",
3
+ "episodes": 16000,
4
+ "left": 8000,
5
+ "right": 8000,
6
+ "collection_domain": "simulation",
7
+ "robot": "Piper real-robot URDF",
8
+ "robot_urdf_commit": "ac41fcbcdda598f01b51cf6175ed9a24d0dacadc",
9
+ "format": "original, byte-identical HDF5 episodes in gzip-compressed tar shards",
10
+ "selection_manifest_source_sha256": "215e85dcba42d81a8f52ad646254721f681a1e29de724bb3f2e3cda97165aeaf",
11
+ "excluded_candidate_episodes": 391,
12
+ "physics_hz": 250,
13
+ "save_freq": 15,
14
+ "nominal_observation_hz": 16.666666666666668,
15
+ "rgb_views": 3,
16
+ "source_root": "/mnt/nas-h/huangzengxiang/intact-flash-sim2real/dataset/robotwin-high-entropy/single-arm/clickbell",
17
+ "source_root_requested": "/mnt/INTACT-WAM-NAS/huangzengxiang/intact-flash-sim2real/dataset/robotwin-high-entropy/single-arm/clickbell",
18
+ "archives": [
19
+ {
20
+ "archive": "clickbell-00000-of-00007.tar.gz",
21
+ "source_archive": "master/episode_archives/v3_4090-11_episodes.tar",
22
+ "source_archive_sha256": "5117178ef0a6e5ff20a7f103e90ef5e6b51aff38a5a14f1283eb21e271839a20",
23
+ "bytes": 9592250276,
24
+ "sha256": "ffa0d6a4f09f08c6c6e3a76e7c590df4e97367ee222c8a9e09c6b3887997cac7",
25
+ "episodes": 3170
26
+ },
27
+ {
28
+ "archive": "clickbell-00001-of-00007.tar.gz",
29
+ "source_archive": "master/episode_archives/v3_4090-12_episodes.tar",
30
+ "source_archive_sha256": "b253fc0a571dff6a22ffcb28052a6ea0153ea3706d177c84c7fb6b6083e59440",
31
+ "bytes": 8449241960,
32
+ "sha256": "f08e78954e5927cf2d893c89b120b70025d4c8bc206d0db711d3204ba976497a",
33
+ "episodes": 2789
34
+ },
35
+ {
36
+ "archive": "clickbell-00002-of-00007.tar.gz",
37
+ "source_archive": "master/episode_archives/v3_4090-14_episodes.tar",
38
+ "source_archive_sha256": "270ca867caaba3c8739224a6b4af5fcb631f622febdb680fb93aa2340a6c0ea7",
39
+ "bytes": 9581682702,
40
+ "sha256": "a458bc17ed9dd72dfa26b4b056d1fc3bb3b17161c7711e53c52705fe6aa64b6e",
41
+ "episodes": 3159
42
+ },
43
+ {
44
+ "archive": "clickbell-00003-of-00007.tar.gz",
45
+ "source_archive": "master/episode_archives/v3_4090-4_episodes.tar",
46
+ "source_archive_sha256": "af0eddac215ce0321617615914eb877a127c4b30b2de0cca7bddde0c612fc114",
47
+ "bytes": 9664601733,
48
+ "sha256": "ea65d0f9f2d31767594964c7eb68a2b48988e3d7f7ddea3bf17e5d34a2480dcf",
49
+ "episodes": 3198
50
+ },
51
+ {
52
+ "archive": "clickbell-00004-of-00007.tar.gz",
53
+ "source_archive": "master/episode_archives/v3_4090-6_episodes.tar",
54
+ "source_archive_sha256": "c7eb344c28d9dadac38084494dcfa1c2bddd4a4c6fb5f8cc02e07f0c0f424077",
55
+ "bytes": 4802529547,
56
+ "sha256": "9058272ed79f35e9cc3d4826a182a7036208118f62f86b33ebc34dac9bdeb876",
57
+ "episodes": 1592
58
+ },
59
+ {
60
+ "archive": "clickbell-00005-of-00007.tar.gz",
61
+ "source_archive": "master/episode_archives/v4_4090-1_episodes.tar",
62
+ "source_archive_sha256": "2b8893a092c7699df7807bea59dbd2cbcb843fb092691cf946d6243fc417e625",
63
+ "bytes": 4818817067,
64
+ "sha256": "a32019c5c290c1f344d3a1a0c928fa15eea01c579a035f65e13a845b9bb9a730",
65
+ "episodes": 1594
66
+ },
67
+ {
68
+ "archive": "clickbell-00006-of-00007.tar.gz",
69
+ "source_archive": "master/episode_archives/v4_4090-48-3_episodes.tar",
70
+ "source_archive_sha256": "f92c0aaf6eb6e9856658680d6f4ce958339fd2b939d1ebe44a0127ba210e8898",
71
+ "bytes": 1503552917,
72
+ "sha256": "96badf34662c0b2c10270d22c2cbfd33d607fe78e931196e2389a5227f6130aa",
73
+ "episodes": 498
74
+ }
75
+ ]
76
+ }
real_data/clickbell/README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # ClickBell selected 16,000 trajectories
2
+
3
+ This release contains exactly **16,000 selected simulated ClickBell trajectories**: 8,000 using the left arm and 8,000 using the right arm. It was collected in simulation using the Piper real-robot URDF from `piper_ros@ac41fcbcdda598f01b51cf6175ed9a24d0dacadc`. The repository directory is named `real_data` as requested; these are **not real-world robot recordings**.
4
+
5
+ Each episode is the original, byte-identical `.hdf5` file, containing three RGB views, joint states, control targets, the raw 250 Hz control stream, camera calibration, and scene metadata. The source uses 250 Hz physics with `save_freq=15` (nominal saved observations at 16.6667 Hz). No action realignment, normalization, image conversion, or data resampling was applied during publication.
6
+
7
+ The seven `clickbell-*-of-00007.tar.gz` files contain only the selected HDF5 episodes. They exclude the 391 candidates not selected for the formal dataset and exclude collection caches and failed trajectories. Within each archive, the original `shard_*/data/episode*.hdf5` paths are retained. Extract all seven archives into the same directory.
8
+
9
+ ```python
10
+ from pathlib import Path
11
+ import tarfile
12
+ from huggingface_hub import snapshot_download
13
+
14
+ root = Path(snapshot_download("INTACT-JEPA/INTACT", allow_patterns="real_data/clickbell/*")) / "real_data/clickbell"
15
+ for archive in sorted(root.glob("clickbell-*-of-00007.tar.gz")):
16
+ with tarfile.open(archive, "r:gz") as f:
17
+ f.extractall("clickbell_episodes", filter="data")
18
+ ```
19
+
20
+ `selection_manifest.jsonl` has one record per selected episode with its published `archive`, `member`, byte count, and SHA-256, together with the original selection fields. `source_selection_manifest.jsonl` and `source_summary.json` preserve the original selector output. The original selection manifest SHA-256 is `215e85dcba42d81a8f52ad646254721f681a1e29de724bb3f2e3cda97165aeaf`.
21
+
22
+ `DATASET_INFO.json` records the collection and release identities. `SHA256SUMS` covers every other published file. Every source episode archive was checked against the source release SHA-256 manifest while reading it; every published HDF5 has its own SHA-256 in the selection manifest.
23
+
24
+ The inherited task, camera, action, and success contracts are retained, with the robot URDF replaced by the stated real-robot model. The `real_data` folder name does not imply a measured sim-to-real result.
real_data/clickbell/SHA256SUMS ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 6441561c16fab513baf195076852c111cd3e3fe3e322fbc471e4709df1ddc0e6 DATASET_INFO.json
2
+ 9572bb724fe26412a74c646d1ccc10aaf9806ddf603ca228af882df47d0cbf1c README.md
3
+ ffa0d6a4f09f08c6c6e3a76e7c590df4e97367ee222c8a9e09c6b3887997cac7 clickbell-00000-of-00007.tar.gz
4
+ f08e78954e5927cf2d893c89b120b70025d4c8bc206d0db711d3204ba976497a clickbell-00001-of-00007.tar.gz
5
+ a458bc17ed9dd72dfa26b4b056d1fc3bb3b17161c7711e53c52705fe6aa64b6e clickbell-00002-of-00007.tar.gz
6
+ ea65d0f9f2d31767594964c7eb68a2b48988e3d7f7ddea3bf17e5d34a2480dcf clickbell-00003-of-00007.tar.gz
7
+ 9058272ed79f35e9cc3d4826a182a7036208118f62f86b33ebc34dac9bdeb876 clickbell-00004-of-00007.tar.gz
8
+ a32019c5c290c1f344d3a1a0c928fa15eea01c579a035f65e13a845b9bb9a730 clickbell-00005-of-00007.tar.gz
9
+ 96badf34662c0b2c10270d22c2cbfd33d607fe78e931196e2389a5227f6130aa clickbell-00006-of-00007.tar.gz
10
+ 5c0f88cc41b7844a52c9a442b394ff99c610d9ef0fe51b05c9d7d1c39edde70f selection_manifest.jsonl
11
+ 215e85dcba42d81a8f52ad646254721f681a1e29de724bb3f2e3cda97165aeaf source_selection_manifest.jsonl
12
+ 59edfeb1e6dfd8939863479592c58cc3d91f85024c93aac491ad581081b44f32 source_summary.json
real_data/clickbell/clickbell-00000-of-00007.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa0d6a4f09f08c6c6e3a76e7c590df4e97367ee222c8a9e09c6b3887997cac7
3
+ size 9592250276
real_data/clickbell/clickbell-00001-of-00007.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f08e78954e5927cf2d893c89b120b70025d4c8bc206d0db711d3204ba976497a
3
+ size 8449241960
real_data/clickbell/clickbell-00002-of-00007.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a458bc17ed9dd72dfa26b4b056d1fc3bb3b17161c7711e53c52705fe6aa64b6e
3
+ size 9581682702
real_data/clickbell/clickbell-00003-of-00007.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea65d0f9f2d31767594964c7eb68a2b48988e3d7f7ddea3bf17e5d34a2480dcf
3
+ size 9664601733
real_data/clickbell/clickbell-00004-of-00007.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9058272ed79f35e9cc3d4826a182a7036208118f62f86b33ebc34dac9bdeb876
3
+ size 4802529547
real_data/clickbell/clickbell-00005-of-00007.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a32019c5c290c1f344d3a1a0c928fa15eea01c579a035f65e13a845b9bb9a730
3
+ size 4818817067
real_data/clickbell/clickbell-00006-of-00007.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96badf34662c0b2c10270d22c2cbfd33d607fe78e931196e2389a5227f6130aa
3
+ size 1503552917
real_data/clickbell/selection_manifest.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
real_data/clickbell/source_selection_manifest.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
real_data/clickbell/source_summary.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "all_observed_cells": 118,
3
+ "audited_projection_records": 16391,
4
+ "candidate_records": 16362,
5
+ "cell_max": 309,
6
+ "cell_median_nonzero": 157,
7
+ "cell_min_nonzero": 8,
8
+ "coverage_cell_source": "hdf5_critical_point_projection",
9
+ "excluded_unstable_boundary_cells": {
10
+ "0,1,1": 3,
11
+ "0,3,1": 1,
12
+ "0,5,1": 1,
13
+ "0,6,1": 2,
14
+ "0,7,1": 3,
15
+ "3,0,0": 6,
16
+ "3,1,0": 7,
17
+ "3,1,2": 1,
18
+ "3,3,2": 2,
19
+ "3,4,0": 5,
20
+ "3,4,2": 2,
21
+ "3,5,2": 4,
22
+ "3,6,0": 5,
23
+ "3,7,2": 3,
24
+ "6,1,1": 1,
25
+ "6,2,1": 1,
26
+ "6,4,1": 1
27
+ },
28
+ "image_8x8_occupied": 64,
29
+ "in_grid_surplus_not_selected": 362,
30
+ "left": 8000,
31
+ "master_candidate_records": 16391,
32
+ "max_image_cell_share": 0.025875,
33
+ "normalized_entropy_8x8_image": 0.9651501638735346,
34
+ "normalized_entropy_8x8x3_all192": 0.834704532575889,
35
+ "normalized_entropy_8x8x3_empirical_feasible": 0.9508863746925403,
36
+ "projection_outside_fixed_roi": 29,
37
+ "realized_cells": 101,
38
+ "right": 8000,
39
+ "schema_version": "robotwin-piper-official-default-250hz-3view-formal16000-v1",
40
+ "selected_records": 16000,
41
+ "selection_manifest": "selection_manifest.jsonl",
42
+ "source_audit_reports": 188,
43
+ "stable_feasible_min_success_count": 8,
44
+ "surplus_not_selected": 391
45
+ }