Robot Manipulation Generalization On The
Metrics
Average decrease average across all perturbations
Results
Performance results of various models on this benchmark
Model Name | Average decrease average across all perturbations | Paper Title | Repository |
|---|---|---|---|
| SAM2Act | -4.3 | - | - |
| R3M | -49.9 | R3M: A Universal Visual Representation for Robot Manipulation | |
| 3D Diffuser Actor | -15.6 | 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations | |
| PerAct | -17.13467282 | THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation | - |
| ACT | -61.8 | Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware | - |
| PerAct | -17.3 | Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation | |
| MVP | -16.3 | Masked Visual Pre-training for Motor Control | |
| GENIMA | -41.6 | Generative Image as Action Models | |
| RVT2 | -19.5 | RVT-2: Learning Precise Manipulation from Few Demonstrations | |
| RVT | -14.5 | RVT: Robotic View Transformer for 3D Object Manipulation |
0 of 10 row(s) selected.