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 33:31 DiT-Flow 30:30 GR00T N1.7 26:33 MolmoAct 2 30:19 Pi 0.5 28:25
- Mean duration
- Rho 67.0 s DiT-Flow 61.0 s GR00T N1.7 53.1 s MolmoAct 2 60.6 s Pi 0.5 56.8 s
- Success
- Rho 80% DiT-Flow 90% GR00T N1.7 67% MolmoAct 2 70% Pi 0.5 80%
- Manipulation density
- Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.4%Gripper engaged71.4%Contact force > 5 N66.0%Gripper engaged or in contact91.2% DiT-Flow Share of time manipulating, five definitionsJoints moving99.7%End-effector moving98.5%Gripper engaged73.1%Contact force > 5 N75.3%Gripper engaged or in contact92.9% GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.7%Gripper engaged71.0%Contact force > 5 N64.6%Gripper engaged or in contact88.2% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.4%Gripper engaged73.7%Contact force > 5 N70.0%Gripper engaged or in contact91.9% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.7%Gripper engaged72.3%Contact force > 5 N68.4%Gripper engaged or in contact90.0%
- 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
0:001:22