ManiSkill2
ManiSkill2 is a unified, fully simulated robotic manipulation benchmark built on the SAPIEN physics engine, covering 20 manipulation task families with 2000+ object models and 4M+ verified demonstration frames.
Source notes
ManiSkill2 is a unified, fully simulated robotic manipulation benchmark built on the SAPIEN physics engine, covering 20 manipulation task families with 2000+ object models and 4M+ verified demonstration frames. It spans stationary and mobile-base, single- and dual-arm, and rigid- and soft-body tasks, with RGB, depth/RGBD, and point-cloud observations and a unified evaluation protocol for RL, imitation learning, and sense-plan-act methods. Robots are Franka Panda arms (single or dual) mounted on stationary or mobile bases.
- Scale
- 7.14 GB size
- Formats
- hdf5
- License
- custom
- Published
- 2023-02-09
Decision summary
scripted
Metadata requires review against the official source before publication.
Read the dataset manifest and feature schema.
Release history
Source-backed release timing for this canonical dataset record.
- Release evidence
Dataset series published
Release timing is recorded from official dataset metadata.
Selection readiness
6 evidence dimensions for deciding whether this dataset is ready to inspect, compare, or adopt. This is not a model benchmark.
Catalog evidence · not task performance
How scores work73/100
Provisional
4/6 dimensions scored · 48% confidence
Read the evidence behind all 6 dimensions
Access and governance
Access and license are declared by the source.
Schema and signal coverage
No machine-readable schema has been verified yet.
Policy training readiness
Observation and action/state signals are declared; alignment quality still depends on sample verification.
World-model readiness
Temporal observations plus geometry or semantic context are declared; sample alignment remains to be audited.
Failure and recovery readiness
No verified failure/recovery annotation evidence is available yet.
Download and processing readiness
Scale is declared; transfer and processing estimates are not measured.
Review unresolved evidence and next checks
Signal gaps
- Gaze / attention. Not enough evidence is available to classify this signal.
Next checks
- Read the dataset manifest and feature schema.
- Run a bounded sample audit before assigning Strong readiness.
Engineering checks (OBRS) behind this record
Needs Audit
OBRS metadata and reported test evidence. A breakdown behind Selection readiness, not a separate score or an independent OpenBot certification.
- A passing real-hardware test report is required.
- A passing ingestion/pipeline test report is required.
- A passing privacy and provenance review is required.
Dataset facts
- Source
- UC San Diego (Hao Su Lab / SAPIEN)
- Evidence
- secondary claim
- Formats
- hdf5
- tasks
- 20
- size
- 7.14 GB
Loop signals
6/7 present or partial
No decision-grade evidence captured yet.
unknownView 6 more signal categories
depth · video · ManiSkill2 is a unified, fully simulated robotic manipulation benchmark built on the SAPIEN physics engine, covering 20 manipulation task families with 2000+ object models and 4M+ verified demonstration frames. It spans stationary and mobile-base, single- and dual-arm, and rigid- and soft-body tasks, with RGB, depth/RGBD, and point-cloud observations and a unified evaluation protocol for RL, imitation learning, and sense-plan-act methods. Robots are Franka Panda arms (single or dual) mounted on stationary or mobile bases.
presentManiSkill2 is a unified, fully simulated robotic manipulation benchmark built on the SAPIEN physics engine, covering 20 manipulation task families with 2000+ object models and 4M+ verified demonstration frames. It spans stationary and mobile-base, single- and dual-arm, and rigid- and soft-body tasks, with RGB, depth/RGBD, and point-cloud observations and a unified evaluation protocol for RL, imitation learning, and sense-plan-act methods. Robots are Franka Panda arms (single or dual) mounted on stationary or mobile bases.
partialhas-success-labels · ManiSkill2 is a unified, fully simulated robotic manipulation benchmark built on the SAPIEN physics engine, covering 20 manipulation task families with 2000+ object models and 4M+ verified demonstration frames. It spans stationary and mobile-base, single- and dual-arm, and rigid- and soft-body tasks, with RGB, depth/RGBD, and point-cloud observations and a unified evaluation protocol for RL, imitation learning, and sense-plan-act methods. Robots are Franka Panda arms (single or dual) mounted on stationary or mobile bases.
partialManiSkill2 is a unified, fully simulated robotic manipulation benchmark built on the SAPIEN physics engine, covering 20 manipulation task families with 2000+ object models and 4M+ verified demonstration frames. It spans stationary and mobile-base, single- and dual-arm, and rigid- and soft-body tasks, with RGB, depth/RGBD, and point-cloud observations and a unified evaluation protocol for RL, imitation learning, and sense-plan-act methods. Robots are Franka Panda arms (single or dual) mounted on stationary or mobile bases.
presentdepth · simulation · ManiSkill2 is a unified, fully simulated robotic manipulation benchmark built on the SAPIEN physics engine, covering 20 manipulation task families with 2000+ object models and 4M+ verified demonstration frames. It spans stationary and mobile-base, single- and dual-arm, and rigid- and soft-body tasks, with RGB, depth/RGBD, and point-cloud observations and a unified evaluation protocol for RL, imitation learning, and sense-plan-act methods. Robots are Franka Panda arms (single or dual) mounted on stationary or mobile bases.
presentOpen · custom · hdf5
partialEvidence details and provenance
Official signal claims
Schema and annotations
No machine-readable schema facts are captured.
Sample verification
Pending. Metadata does not prove sample coverage, alignment, or file integrity.
curated official source
Integration notes
- Metadata requires review against the official source before publication.