Robot Manipulation on RLBench
Metric: Training Time (V100 x 8 x day) (higher is better)
Metric: Training Time (V100 x 8 x day) (higher is better)
| # | Model↕ | Training Time (V100 x 8 x day)▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | PerAct (Evaluated in RVT) | 16 | No | Perceiver-Actor: A Multi-Task Transformer for Ro... | 2022-09-12 | Code |
| 2 | PerAct | 16 | No | Perceiver-Actor: A Multi-Task Transformer for Ro... | 2022-09-12 | Code |
| 3 | 3D Diffuser Actor | 8 | No | 3D Diffuser Actor: Policy Diffusion with 3D Scen... | 2024-02-16 | Code |
| 4 | Act3D | 5 | No | Act3D: 3D Feature Field Transformers for Multi-T... | 2023-06-30 | Code |
| 5 | PolarNet | 5 | No | PolarNet: 3D Point Clouds for Language-Guided Ro... | 2023-09-27 | Code |
| 6 | RVT | 1 | No | RVT: Robotic View Transformer for 3D Object Mani... | 2023-06-26 | Code |
| 7 | RVT-2 | 0.83 | No | RVT-2: Learning Precise Manipulation from Few De... | 2024-06-12 | Code |
| 8 | 3D-LOTUS | 0.28 | No | Towards Generalizable Vision-Language Robotic Ma... | 2024-10-02 | Code |
| 9 | Mini Diffuser | 0.24 | No | Mini Diffuser: Fast Multi-task Diffusion Policy ... | 2025-05-14 | Code |