Robot Manipulation Generalization On Gembench
평가 지표
Average Success Rate
Average Success Rate (L1)
Average Success Rate (L2)
Average Success Rate (L3)
Average Success Rate (L4)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Average Success Rate | Average Success Rate (L1) | Average Success Rate (L2) | Average Success Rate (L3) | Average Success Rate (L4) |
|---|---|---|---|---|---|
| polarnet-3d-point-clouds-for-language-guided | 38.4 | 77.7±0.9 | 37.1±1.4 | 38.5±1.7 | 0.1±0.2 |
| towards-generalizable-vision-language-robotic | 48.0 | 68.7±0.6 | 64.5±0.9 | 41.5±1.8 | 17.4±0.4 |
| 3d-diffuser-actor-policy-diffusion-with-3d | 44.0 | 91.9±0.8 | 43.4±2.8 | 37.0±2.2 | 0.0±0.0 |
| rvt-2-learning-precise-manipulation-from-few | 44.0 | 89.1±0.8 | 51.0±2.3 | 36.0±2.2 | 0.0±0.0 |
| instruction-driven-history-aware-policies-for | 30.4 | 60.3±1.5 | 26.1±1.4 | 35.1±1.7 | 0.0±0.0 |
| towards-generalizable-vision-language-robotic | 45.7 | 94.3±1.4 | 49.9±2.2 | 38.1±1.1 | 0.3±0.3 |