Table 1 Simulation results for all methods (Success Rates in %).
From: A framework for robotic manipulation tasks based on multiple zero shot models
Method | Task 01 | Task 02 | Task 03 | Task 04 | Average |
|---|---|---|---|---|---|
Gato-200M | 79.0 | 68.0 | 91.5 | 74.0 | 78.1 |
Flamingo-200M | 56.0 | 58.5 | 63.0 | 62.5 | 60.0 |
GPT-200M | 62.0 | 57.5 | 41.0 | 54.5 | 53.8 |
Panda Act | 92.4 | 85.2 | 98.5 | 94.2 | 92.6 |
