BenchmarkPAW-GEN-10
Environmente07Place loaded boxes in container (bimanual)
- Episodes
- Rho 30 DiT-Flow 30 GR00T N1.7 30 MolmoAct 2 30 Pi 0.5 30
- Total duration
- Rho 18:47 DiT-Flow 18:10 GR00T N1.7 14:27 MolmoAct 2 18:46 Pi 0.5 16:46
- Mean duration
- Rho 37.6 s DiT-Flow 36.3 s GR00T N1.7 28.9 s MolmoAct 2 37.5 s Pi 0.5 33.5 s
- Success
- Rho 60% DiT-Flow 53% GR00T N1.7 13% MolmoAct 2 63% Pi 0.5 7%
- Manipulation density
- Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.9%Gripper engaged64.4%Contact force > 5 N75.4%Gripper engaged or in contact81.3% DiT-Flow Share of time manipulating, five definitionsJoints moving99.7%End-effector moving94.7%Gripper engaged66.5%Contact force > 5 N74.3%Gripper engaged or in contact87.4% GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.2%Gripper engaged65.5%Contact force > 5 N70.7%Gripper engaged or in contact90.8% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.0%Gripper engaged60.2%Contact force > 5 N79.8%Gripper engaged or in contact84.9% Pi 0.5 Share of time manipulating, five definitionsJoints moving99.9%End-effector moving98.4%Gripper engaged66.4%Contact force > 5 N74.8%Gripper engaged or in contact87.8%
- 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
0:000:38