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 32:31 DiT-Flow 31:32 GR00T N1.7 25:54 MolmoAct 2 28:32 Pi 0.5 32:20
- Mean duration
- Rho 65.0 s DiT-Flow 63.1 s GR00T N1.7 51.8 s MolmoAct 2 57.1 s Pi 0.5 64.7 s
- Success
- Rho 80% DiT-Flow 90% GR00T N1.7 60% MolmoAct 2 73% Pi 0.5 77%
- Manipulation density
- Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.0%Gripper engaged70.4%Contact force > 5 N67.3%Gripper engaged or in contact90.8% DiT-Flow Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.1%Gripper engaged72.4%Contact force > 5 N74.9%Gripper engaged or in contact92.4% GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.6%Gripper engaged70.7%Contact force > 5 N68.8%Gripper engaged or in contact89.5% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.4%Gripper engaged73.5%Contact force > 5 N73.9%Gripper engaged or in contact93.4% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.8%Gripper engaged71.7%Contact force > 5 N74.0%Gripper engaged or in contact91.8%
- 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
0:001:38