RoboCasa
RoboCasa is a MuJoCo/robosuite-based simulation framework of photorealistic kitchen environments for training generalist robots (used in NVIDIA's GR00T effort). The original RSS 2024 release provides 120 kitchen scenes (10 floor plans, 12 styles), 2,509 3D assets across 153 categories, and 100 tasks (25 atomic + 75 LLM-generated composite), with 50 human demonstrations per atomic task expanded to 100K+ trajectories via MimicGen on a PandaOmron (Franka arm on Omron mobile base). The framework also supports cross-embodiments including humanoid robots and quadruped robots with arms. The 2026 RoboCasa365 extension scales this to 365 tasks across 2,500 kitchen scenes, 3,200+ objects, and 600+ hours of human plus 1,600+ hours of synthetic demonstrations.
- Scale
- 2227 hours
- Formats
- hdf5 · lerobot
- License
- CC-BY-4.0
- Published
- 2024-06-04
Decision summary
scripted
Metadata requires review against the official source before publication.
Read the dataset manifest and feature schema.
Catalog assessment
Selection evidence
73/100
Provisional · confidence 48 · 4/6 evaluated
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.
View 3 more dimensions
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.
- Feedback / correction / failure. 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.
Record specifics
Dataset facts
- Source
- UT Austin (Yuke Zhu) and NVIDIA Research
- Evidence
- secondary claim
- Formats
- hdf5 · lerobot
- hours
- 2227
- tasks
- 100
Metadata coverage
Loop signals
5/7 present or partial
No decision-grade evidence captured yet.
unknownNo decision-grade evidence captured yet.
unknownView 5 more signal categories
video
presentee_pose
partiallanguage · has-success-labels · RoboCasa is a MuJoCo/robosuite-based simulation framework of photorealistic kitchen environments for training generalist robots (used in NVIDIA's GR00T effort). The original RSS 2024 release provides 120 kitchen scenes (10 floor plans, 12 styles), 2,509 3D assets across 153 categories, and 100 tasks (25 atomic + 75 LLM-generated composite), with 50 human demonstrations per atomic task expanded to 100K+ trajectories via MimicGen on a PandaOmron (Franka arm on Omron mobile base). The framework also supports cross-embodiments including humanoid robots and quadruped robots with arms. The 2026 RoboCasa365 extension scales this to 365 tasks across 2,500 kitchen scenes, 3,200+ objects, and 600+ hours of human plus 1,600+ hours of synthetic demonstrations.
presentsimulation · RoboCasa is a MuJoCo/robosuite-based simulation framework of photorealistic kitchen environments for training generalist robots (used in NVIDIA's GR00T effort). The original RSS 2024 release provides 120 kitchen scenes (10 floor plans, 12 styles), 2,509 3D assets across 153 categories, and 100 tasks (25 atomic + 75 LLM-generated composite), with 50 human demonstrations per atomic task expanded to 100K+ trajectories via MimicGen on a PandaOmron (Franka arm on Omron mobile base). The framework also supports cross-embodiments including humanoid robots and quadruped robots with arms. The 2026 RoboCasa365 extension scales this to 365 tasks across 2,500 kitchen scenes, 3,200+ objects, and 600+ hours of human plus 1,600+ hours of synthetic demonstrations.
presentOpen · CC-BY-4.0 · hdf5 · lerobot
presentEvidence 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.
Catalog links