This checkpoint is designed for use with SatNav, the continuous-state vision-and-language navigation platform for satellite maps. The SatNav NaVILA integration uses it to predict compact actions from a language instruction and eight RGB observations.

Model

Starting checkpoint: a8cheng/navila-siglip-llama3-8b-v1.5-pretrain
Training data: SatNav-v0.1 offline trajectories
Training: 1 epoch, full-parameter fine-tuning
Action format: stop, forward, left, and right

Repository name

navila-satnav: NaVILA adapted to SatNav
scratch: starts from the NaVILA pretraining checkpoint, before navigation SFT
1ep: trained for one epoch
8f: uses eight visual frames per sample
sample: the following fields describe trajectory-step sampling
hk7: keeps the first seven action steps
fs7: keeps every seventh step in a consecutive forward run after the head; turning steps are kept
stopx4: repeats each terminal stop sample four times

Reference Results

Evaluated in SatSim with the full split and a 500-step cap.

Split	Episodes	NE	OS	SR	SPL
`val_seen`	4,574	93.05	27.59	18.10	18.02
`val_unseen`	8,756	128.88	23.66	13.00	12.96

Usage

Use this checkpoint with the SatNav NaVILA integration. It is also listed in the SatNav Baseline Model Zoo.

License

The checkpoint contains a Llama 3 backbone and is released under the applicable Llama 3 terms. NaVILA, SatNav, and other components retain their own licenses.

Eku127/navila-satnav-scratch-1ep-8f-sample-hk7-fs7-stopx4

NaVILA for SatNav — Scratch

Model

Repository name

Reference Results

Usage

License

Eku127/
navila-satnav-scratch-1ep-8f-sample-hk7-fs7-stopx4