---
license: mit
library_name: pytorch
pipeline_tag: robotics
tags:
  - uav
  - visual-navigation
  - starvla
  - qwen3-vl
---

# MapFly-Agent

Reference policy of the [MapFly](https://github.com/GuYan66/MapFly) benchmark:
Qwen3-VL-4B with starVLA's QwenOFT action head, plus a stop and progress head.
Code is `starVLA/examples/uav/` in that repository.

## Checkpoint

P1-R0 on OSM maps, 80k steps (main rows of Tables I–III):

| Folder | Head | Test Seen SR | Test Unseen SR |
|---|---|---|---|
| `mapfly_agent_oft_p1r0/` | QwenOFT | 86.6 | 62.7 |

```text
mapfly_agent_oft_p1r0/
  config.yaml
  dataset_statistics.json
  checkpoints/steps_80000_pytorch_model.pt
```

Download into `$PLAYGROUND/Checkpoints/` (default `starVLA/playground/Checkpoints`):

```bash
huggingface-cli download EzGuYan/MapFly-Agent mapfly_agent_oft_p1r0 --local-dir playground/Checkpoints/mapfly_agent_oft_p1r0
```

Serve and evaluate from the MapFly checkout:

```bash
CKPT=$PLAYGROUND/Checkpoints/mapfly_agent_oft_p1r0/checkpoints/steps_80000_pytorch_model.pt \
  bash starVLA/examples/uav/eval_files/run_policy_server.sh
ROLE=unseen TAG=oft_p1r0 bash starVLA/examples/uav/eval_files/run_eval_split.sh
```

The other paper rows (QwenGR00T, other tracks) are trained with `HEAD` /
`VARIANT` in `starVLA/examples/uav/README.md`; those checkpoints are not
released here.

`config.yaml` names the base VLM as `Qwen/Qwen3-VL-4B-Instruct`. Put a copy under
`playground/Pretrained_models/` if your serving setup still expects a local tree.

## License

MIT. The Qwen3-VL weights inside the checkpoint follow Qwen's license.