BenchmarkPAW-GEN-10
Environmente08Place spray bottles upright, nozzle forward (bimanual handover)
- Episodes
- Rho 30 DiT-Flow 30 GR00T N1.7 30 MolmoAct 2 30 Pi 0.5 30
- Total duration
- Rho 29:50 DiT-Flow 31:58 GR00T N1.7 29:55 MolmoAct 2 29:40 Pi 0.5 31:48
- Mean duration
- Rho 59.7 s DiT-Flow 63.9 s GR00T N1.7 59.8 s MolmoAct 2 59.3 s Pi 0.5 63.6 s
- Success
- Rho 87% DiT-Flow 90% GR00T N1.7 73% MolmoAct 2 90% Pi 0.5 83%
- Manipulation density
- Rho Share of time manipulating, five definitionsJoints moving99.9%End-effector moving99.5%Gripper engaged71.9%Contact force > 5 N67.1%Gripper engaged or in contact90.2% DiT-Flow Share of time manipulating, five definitionsJoints moving99.8%End-effector moving98.7%Gripper engaged70.4%Contact force > 5 N73.1%Gripper engaged or in contact92.4% GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.7%Gripper engaged72.0%Contact force > 5 N65.5%Gripper engaged or in contact90.7% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.4%Gripper engaged74.0%Contact force > 5 N74.5%Gripper engaged or in contact93.1% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.5%Gripper engaged72.1%Contact force > 5 N73.4%Gripper engaged or in contact92.8%
- SPARC smoothness
- Rho Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. DiT-Flow Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. GR00T N1.7 Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. MolmoAct 2 Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. Pi 0.5 Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015.
Episode
Held-out benchmark environment
0:000:00