Long-horizon task completion on Calvin ABC->D
98.1Success Rate (1)PriGo-DP
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| PriGo-DPevaluation_type=Zero-shot, horizon=Long-horizon2026.07 | 98.1 | 92.1 | 87.6 | 80.4 | 59.9 | 4.18 | |
| GR-MGInput=S-RGBD, G-RGBD, P2025.03 | 96.8 | 89.3 | 81.5 | 72.7 | 64.4 | 4.04 | |
| VPPCategory=Ours, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 96.5 | 90.9 | 86.6 | 82 | 76.9 | 4.33 | |
| RoboFlamingoTraining Data=ABCD (Lang)2023.11 | 96.4 | 89.6 | 82.4 | 74 | 66 | 4.09 | |
| RoboUniViewTrain → Test=D → D2024.06 | 96.2 | 88.8 | 77.6 | 66.6 | 56.3 | 3.855 | |
| GHIL-GlueInput=S-RGB2025.03 | 95.2 | 88.5 | 73.2 | 62.5 | 49.8 | 3.69 | |
| ADProevaluation_type=Zero-shot, horizon=Long-horizon2026.07 | 94.7 | 83 | 73.6 | 61.4 | 51.1 | 3.64 | |
| DitaInput=S-RGB2025.03 | 94.5 | 82.5 | 72.8 | 61.3 | 50 | 3.61 | |
| DTPevaluation_type=Zero-shot, horizon=Long-horizon2026.07 | 94.5 | 82.5 | 72.8 | 61.3 | 50 | 3.61 | |
| E_diff^CONSInput=S-RGB2025.03 | 94.3 | 77.5 | 62 | 48.3 | 34 | 3.16 | |
| RoboUniViewTrain → Test=ABC → D2024.06 | 94.2 | 84.2 | 73.4 | 62.2 | 50.7 | 3.647 | |
| RoboUniviewCategory=3D Method, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 94.2 | 84.2 | 73.4 | 62.2 | 50.7 | 3.65 | |
| 3D Diffuser ActorType=other, Zero-shot=true2025.01 | 93.8 | 80.3 | 66.2 | 53.3 | 41.2 | 3.35 | |
| 3DDAevaluation_type=Zero-shot, horizon=Long-horizon2026.07 | 93.8 | 80.3 | 66.2 | 53.3 | 41.2 | 3.35 | |
| HULC++Train → Test=D → D2024.06 | 93 | 79 | 64 | 52 | 40 | 3.3 | |
| UP-VLAType=Prediction&VLA, Zero-shot=true2025.01 | 92.8 | 86.5 | 81.5 | 76.9 | 69.9 | 4.08 | |
| 3D DiffuserInput=S-RGBD, G-RGBD, P, Cam2025.03 | 92.2 | 78.7 | 63.9 | 51.2 | 41.2 | 3.27 | |
| 3D Diffuser ActorTrain → Test=ABC → D2024.06 | 92.2 | 78.7 | 63.9 | 51.2 | 41.2 | 3.27 | |
| VidmanCategory=Future Prediction Related Method, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 91.5 | 76.4 | 68.2 | 59.2 | 46.7 | 3.42 | |
| RD-VLAParams=0.52026.02 | 91.4 | 79.5 | 67.9 | 54.9 | 45.3 | 3.39 | |
| OpenVLAParams=72026.02 | 91.3 | 77.8 | 62 | 52.1 | 43.5 | 3.27 | |
| Dita w/o PretrainInput=S-RGB2025.03 | 89.5 | 63.3 | 39.8 | 27.3 | 18.5 | 2.38 | |
| HULCTraining Data=ABCD (Lang)2023.11 | 89.2 | 70.1 | 54.8 | 42 | 33.5 | 2.9 | |
| HULCTraining Data=ABCD (Full)2023.11 | 88.9 | 73.3 | 58.7 | 47.5 | 38.3 | 3.06 | |
| LCDTrain → Test=D → D2024.06 | 88.7 | 69.9 | 54.5 | 42.7 | 32.2 | 2.88 | |
| VPPCategory=Data Efficiency, Annotated Data=10% ABC, Zero-shot evaluation=true2024.12 | 87.8 | 74.6 | 63.2 | 54 | 45.3 | 3.25 | |
| VLASParams=72026.02 | 87.2 | 64.2 | 40.9 | 28.1 | 19.6 | 2.4 | |
| SusieType=Prediction, Zero-shot=true2025.01 | 87 | 69 | 49 | 38 | 26 | 2.69 | |
| SuSIEInput=S-RGB2025.03 | 87 | 69 | 49 | 38 | 26 | 2.69 | |
| SusieCategory=Future Prediction Related Method, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 87 | 69 | 49 | 38 | 26 | 2.69 | |
| SuSIEParams=1.32026.02 | 87 | 69 | 49 | 38 | 26 | 2.69 | |
| DeeRParams=32026.02 | 86.2 | 70.1 | 51.8 | 41.5 | 30.4 | 2.82 | |
| RoboFlamingoTrain → Test=D → D2024.06 | 86 | 71.4 | 58.5 | 46 | 34.9 | 2.968 | |
| GR-1Type=Prediction, Zero-shot=true2025.01 | 85.4 | 71.2 | 59.6 | 49.7 | 40.1 | 3.06 | |
| GR-1Input=S-RGB, G-RGB, P2025.03 | 85.4 | 71.2 | 59.6 | 49.7 | 40.1 | 3.06 | |
| GR-1Train → Test=ABC → D2024.06 | 85.4 | 71.2 | 59.6 | 49.7 | 40.1 | 3.06 | |
| GR-1Category=Future Prediction Related Method, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 85.4 | 71.2 | 59.6 | 49.7 | 40.1 | 3.06 | |
| GR-1Params=3.12026.02 | 85.4 | 71.2 | 59.6 | 49.7 | 40.1 | 3.06 | |
| SPILTrain → Test=D → D2024.06 | 84.6 | 65.1 | 50.8 | 38 | 28.6 | 2.64 | |
| UP-VLA-phi-w/o-mmuType=Prediction, Zero-shot=true, reproduced=true2025.01 | 84.4 | 70.5 | 60.4 | 52 | 43 | 3.13 | |
| RT-1Training Data=ABCD (Lang)2023.11 | 84.4 | 61.7 | 43.8 | 32.3 | 22.7 | 2.45 | |
| HULCTrain → Test=D → D2024.06 | 82.7 | 64.9 | 50.4 | 38.5 | 28.3 | 2.64 | |
| Robo-FlamingoType=VLA, Zero-shot=true2025.01 | 82.4 | 61.9 | 46.6 | 33.1 | 23.5 | 2.47 | |
| RoboFlamingoInput=S-RGB, G-RGB2025.03 | 82.4 | 61.9 | 46.6 | 33.1 | 23.5 | 2.47 | |
| RoboFlamingoTraining Data=ABC (Lang)2023.11 | 82.4 | 61.9 | 46.6 | 33.1 | 23.5 | 2.48 | |
| RoboFlamingoTrain → Test=ABC → D2024.06 | 82.4 | 61.9 | 46.6 | 33.1 | 23.5 | 2.47 | |
| Robo-FlamingoCategory=Direct Action Learning Method, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 82.4 | 61.9 | 46.6 | 33.1 | 23.5 | 2.47 | |
| RoboFlamingoParams=32026.02 | 82.4 | 61.9 | 46.6 | 33.1 | 23.5 | 2.48 | |
| MCILTrain → Test=D → D2024.06 | 76.4 | 48.8 | 30.1 | 18.1 | 9.3 | 1.82 | |
| E_diff^CONS w/o PretrainInput=S-RGB2025.03 | 75.5 | 44.8 | 25 | 15 | 7.5 | 1.68 | |
| SPILTrain → Test=ABC → D2024.06 | 74.2 | 46.3 | 27.6 | 14.7 | 8 | 1.71 | |
| LCBParams=72026.02 | 73.6 | 50.2 | 28.5 | 16 | 9.9 | 1.78 | |
| GR-1Category=Data Efficiency, Annotated Data=10% ABC, Zero-shot evaluation=true2024.12 | 67.2 | 37.1 | 19.8 | 10.8 | 6.9 | 1.41 | |
| GCBCTrain → Test=D → D2024.06 | 64.7 | 28.4 | 12.2 | 4.9 | 1.3 | 1.11 | |
| MDTCategory=Future Prediction Related Method, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 63.1 | 42.9 | 24.7 | 15.1 | 9.1 | 1.55 | |
| UP-VLA-RT-2Type=VLA, Zero-shot=true, reproduced=true2025.01 | 61.2 | 38.9 | 23.6 | 13.8 | 6.2 | 1.44 | |
| Uni-PiType=Prediction, Zero-shot=true2025.01 | 56 | 16 | 8 | 8 | 4 | 0.92 | |
| Uni-PiCategory=Future Prediction Related Method, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 56 | 16 | 8 | 8 | 4 | 0.92 | |
| DP3evaluation_type=Zero-shot, horizon=Long-horizon2026.07 | 53.9 | 44.7 | 38 | 34.3 | 29 | 2 | |
| RT-1Type=other, Zero-shot=true2025.01 | 53.3 | 22.2 | 9.4 | 3.8 | 1.3 | 0.9 | |
| RT-1Training Data=ABC (Lang)2023.11 | 53.3 | 22.2 | 9.4 | 3.8 | 1.3 | 0.9 | |
| RT-1Train → Test=ABC → D2024.06 | 53.3 | 22.2 | 9.4 | 3.8 | 1.3 | 0.9 | |
| RT-1Category=Direct Action Learning Method, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 53.3 | 22.2 | 9.4 | 3.8 | 1.3 | 0.9 | |
| RT-1Params=-2026.02 | 53.3 | 22.2 | 9.4 | 3.8 | 1.3 | 0.9 | |
| HULCTrain → Test=ABC → D2024.06 | 48.1 | 16.5 | 5.7 | 1.9 | 1.1 | 0.67 | |
| 3D-VLAType=VLA, Zero-shot=true2025.01 | 44.7 | 16.3 | 8.1 | 1.6 | 0 | 0.71 | |
| HULCTraining Data=ABC (Full)2023.11 | 41.8 | 16.5 | 5.7 | 1.9 | 1.1 | 0.67 | |
| Diffusion PolicyType=other, Zero-shot=true, reproduced=true2025.01 | 40.2 | 12.3 | 2.6 | 0.8 | 0 | 0.56 | |
| Diffusion PolicyCategory=Direct Action Learning Method, Annotated Data=100% ABC, Zero-shot evaluation=true2024.12 | 40.2 | 12.3 | 2.6 | 0.8 | 0 | 0.56 | |
| MCILTraining Data=ABCD (Full)2023.11 | 37.3 | 2.7 | 0.2 | 0 | 0 | 0.4 | |
| MCILTraining Data=ABC (Full)2023.11 | 30.4 | 1.3 | 0.2 | 0 | 0 | 0.31 | |
| MCILTrain → Test=ABC → D2024.06 | 30.4 | 1.3 | 0.2 | 0 | 0 | 0.4 |