Uni-NaVid for SatNav — Base initialization

This checkpoint is designed for use with SatNav, the continuous-state vision-and-language navigation platform for satellite maps. The SatNav Uni-NaVid integration uses it to predict short action sequences from a language instruction and a stream of RGB observations.

Model

• Starting checkpoint: lmsys/vicuna-7b-v1.5
• Vision encoder: EVA-CLIP
• Training data: SatNav-v0.1 offline trajectories
• Training: 1 epoch, learning rate 1e-5
• Action window: up to 4 actions

Repository name

• uninavid-satnav: Uni-NaVid adapted to SatNav
• scratch: base initialization from the Vicuna 7B v1.5 checkpoint
• 1ep: trained for one epoch
• lr1e-5: uses a learning rate of 1e-5

Reference Results

Results reported in the SatNav paper, baseline comparison, row UniNaVid.

SR, SPL, and OS are percentages. NE is measured in meters. Steps is the average number of executed environment actions, including turns and stop.

Usage

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

License

The checkpoint follows the applicable Llama 2 terms. Uni-NaVid, EVA-CLIP, SatNav, and other components retain their own licenses.