Opencv new dataset vs Explicit dataset vs old dataset comparison
Comparing which circuits do the brains complete
Model | Dataset | Montmeló | Simple circuit no red line | Simple circuit no line no wall | Simple circuit white road | Simple circuit white road no line |
---|---|---|---|---|---|---|
Explicit | - | ✅ | ❌ | ❌ | ✅ | ❌ |
OpenCV | - | ✅ | ❌ | ❌ | ✅ | ❌ |
PilotNet | Old | ✅ | ❌ | ✅ | ✅ | ❌ |
PilotNet | Explicit | ✅ | ❌(last turns) | ❌(some turns ok) | ✅ | ❌ |
PilotNet | OpenCV(fastest) | ✅(lowering rate much) | ❌ | ❌ | ✅ | ❌ |
Deepest LSTM | Old | ✅ | ❌ | ✅ | ❌ | ❌ |
Deepest LSTM | Explicit | ✅ | ❌ | ❌ | ✅ | ❌ |
Deepest LSTM | OpenCV(fastest) | ✅(lowering rate) | ❌ | ✅(over the grass) | ✅ | ❌ |
Frankenstein | Old | ✅(lowering rate) | ✅ | ✅(over the grass | ✅ | ❌ |
Frankenstein | Explicit | ✅ | ❌ | ❌ | ✅ | ❌ |
Frankenstein | OpenCV(fastest) | - | - | - | - | - |
PilotNet 3D | Old | ✅(lowering rate) | ❌ | ❌ | ✅ | ❌ |
PilotNet 3D | Explicit | ❌ | ❌ | ❌ | ❌ | ❌ |
PilotNet 3D | OpenCV(fastest) | - | - | - | - | - |
Comparing stats values
Model | Dataset | MAE train | MAE val | MSE train | MSE val |
---|---|---|---|---|---|
PilotNet | Old | 5.16e⁻3 | 0.028 | 2.6e⁻4 | 5.63e⁻3 |
PilotNet | Explicit | 2.39e⁻3 | 3.03e⁻3 | 5.39e⁻3 | 4.39e⁻3 |
PilotNet | OpenCV(fastest) | 4.40e⁻3 | 5.46e⁻3 | 1.67e⁻3 | 6.45e⁻3 |
Deepest LSTM | Old | - | 0.047 | - | 8.27e⁻3 |
Deepest LSTM | Explicit | 0.023 | 0.02 | 3.73e⁻3 | 3.39e⁻3 |
Deepest LSTM | OpenCV(fastest) | 0.018 | 0.016 | 4.16e⁻3 | 3.82e⁻3 |
Frankenstein | Old | 0.032 | 0.044 | 3.49e⁻3 | 6.32e⁻3 |
Frankenstein | Explicit | 0.016 | 0.015 | 2.05e⁻3 | 2.14e⁻3 |
Frankenstein | OpenCV(fastest) | 0.019 | 0.018 | 3.9e⁻3 | 3.5e⁻3 |
Comparing V and W of each brain
Dataset | V min | V max | W min | W max |
---|---|---|---|---|
Old | -0.6 | 13 | -3 | 3 |
Explicit | -0.6 | 13 | -3 | 3 |
OpenCV(fastest) | 6.5 | 24 | -7.1 | 7.1 |