OpenBot
Back to Explore
Manipulation datasetOpen

FurnitureBench

FurnitureBench is a reproducible real-world benchmark from CLVR Lab (KAIST) for long-horizon, complex robotic manipulation framed as furniture assembly with a Franka Panda arm. It releases 5100 successful teleoperation demonstrations totaling 219.6 hours across 9 furniture models and three task-initialization randomness levels (low/medium/high). The released demonstration files contain two RGB camera streams (wrist and front, 224x224x3) plus proprioceptive robot state; the physical rig additionally supports rear and RGBD/depth sensing. It also ships FurnitureSim, an Isaac Gym/Factory-based simulator, plus 3D-printable furniture models and a standardized environment setup.

Scale
219.6 hours
Formats
custom
License
MIT
Published
2023-05-22

Decision summary

Best for

teleoperation

Main blocker

Metadata requires review against the official source before publication.

Next check

Read the dataset manifest and feature schema.

Catalog assessment

Selection evidence

70/100

Provisional · confidence 42 · 3/6 evaluated

Access and governance

Access and license are declared by the source.

usefulfit 75 · confidence 85

Schema and signal coverage

No machine-readable schema has been verified yet.

unknownnot scored · confidence 15

Policy training readiness

Observation and action/state signals are declared; alignment quality still depends on sample verification.

usefulfit 70 · confidence 55
View 3 more dimensions

World-model readiness

World-model observation, geometry, or temporal semantics are not verified.

unknownnot scored · confidence 15

Failure and recovery readiness

No verified failure/recovery annotation evidence is available yet.

unknownnot scored · confidence 15

Download and processing readiness

Scale is declared; transfer and processing estimates are not measured.

usefulfit 65 · confidence 65
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
CLVR Lab, KAIST
Evidence
secondary claim
Formats
custom
episodes
5100
hours
219.6
tasks
9
bytes
1265941610496
Read paper

Metadata coverage

Loop signals

5/7 present or partial

Gaze / attention

No decision-grade evidence captured yet.

unknown
Feedback / correction / failure

No decision-grade evidence captured yet.

unknown
View 5 more signal categories
Observation / ego video

video · FurnitureBench is a reproducible real-world benchmark from CLVR Lab (KAIST) for long-horizon, complex robotic manipulation framed as furniture assembly with a Franka Panda arm. It releases 5100 successful teleoperation demonstrations totaling 219.6 hours across 9 furniture models and three task-initialization randomness levels (low/medium/high). The released demonstration files contain two RGB camera streams (wrist and front, 224x224x3) plus proprioceptive robot state; the physical rig additionally supports rear and RGBD/depth sensing. It also ships FurnitureSim, an Isaac Gym/Factory-based simulator, plus 3D-printable furniture models and a standardized environment setup.

present
Action / hand pose / robot state

ee_pose · FurnitureBench is a reproducible real-world benchmark from CLVR Lab (KAIST) for long-horizon, complex robotic manipulation framed as furniture assembly with a Franka Panda arm. It releases 5100 successful teleoperation demonstrations totaling 219.6 hours across 9 furniture models and three task-initialization randomness levels (low/medium/high). The released demonstration files contain two RGB camera streams (wrist and front, 224x224x3) plus proprioceptive robot state; the physical rig additionally supports rear and RGBD/depth sensing. It also ships FurnitureSim, an Isaac Gym/Factory-based simulator, plus 3D-printable furniture models and a standardized environment setup.

present
Language intent / task phase

has-success-labels · FurnitureBench is a reproducible real-world benchmark from CLVR Lab (KAIST) for long-horizon, complex robotic manipulation framed as furniture assembly with a Franka Panda arm. It releases 5100 successful teleoperation demonstrations totaling 219.6 hours across 9 furniture models and three task-initialization randomness levels (low/medium/high). The released demonstration files contain two RGB camera streams (wrist and front, 224x224x3) plus proprioceptive robot state; the physical rig additionally supports rear and RGBD/depth sensing. It also ships FurnitureSim, an Isaac Gym/Factory-based simulator, plus 3D-printable furniture models and a standardized environment setup.

partial
Sim-real pairing

simulation · FurnitureBench is a reproducible real-world benchmark from CLVR Lab (KAIST) for long-horizon, complex robotic manipulation framed as furniture assembly with a Franka Panda arm. It releases 5100 successful teleoperation demonstrations totaling 219.6 hours across 9 furniture models and three task-initialization randomness levels (low/medium/high). The released demonstration files contain two RGB camera streams (wrist and front, 224x224x3) plus proprioceptive robot state; the physical rig additionally supports rear and RGBD/depth sensing. It also ships FurnitureSim, an Isaac Gym/Factory-based simulator, plus 3D-printable furniture models and a standardized environment setup.

present
License / format / access

Open · MIT · custom

partial
Evidence details and provenance

Official signal claims

Ee_poseProprioceptionVideo

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

Related records