| | --- |
| | license: apache-2.0 |
| | tags: |
| | - flight-planning |
| | - transformer |
| | - coordinate-prediction |
| | - sequence-to-sequence |
| | - count-classification |
| | --- |
| | # Flight Plan Coordinate Prediction Model (Seq2SeqCoordsTransformer) |
| | The encoder-decoder transformer model was trained for an AI flight planning project. Predicts normalized coordinates directly and waypoint count via classification. |
| | ## Model Description |
| | Seq2SeqCoordsTransformer architecture using `torch.nn.Transformer`. Predicts normalized lat/lon coordinates autoregressively and waypoint count (0-10) via classification head on encoder output. |
| | * Embed Dim: 256, Heads: 8, Enc Layers: 4, Dec Layers: 4, Max Waypoints: 10 |
| | ## Intended Use |
| | Research prototype. **Not for real-world navigation.** |
| | ## Limitations |
| | Accuracy depends on data/tuning. Fixed max waypoints (10). Not certified. **Architecture differs significantly from previous versions in this repo.** |
| | ## How to Use |
| | This requires loading the custom `Seq2SeqCoordsTransformer` class and weights. Generation requires autoregressive decoding and taking the argmax of the count logits. |
| |
|
| | Read this article - https://medium.com/ai-simplified-in-plain-english/building-a-transformer-model-with-seq2seq-architecture-for-flight-planning-0bdd1fecaefe |
| |
|
| |
|
| | ## Training Data |
| | Trained on `frankmorales2020/flight_plan_waypoints` - https://huggingface.co/datasets/frankmorales2020/flight_plan_waypoints. |
| | ## Contact |
| | Frank Morales, BEng, MEng, SMIEEE (Boeing ATF) - https://www.linkedin.com/in/frank-morales1964/ |
