StreamVLN for SatNav — Navigation-pretrained initialization

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

Model

• Starting checkpoint: mengwei0427/StreamVLN_Video_qwen_1_5_r2r_rxr_envdrop_scalevln_v1_3
• Training data: SatNav-v0.1 offline trajectories
• Training: 1 epoch, full-parameter fine-tuning, learning rate 2e-5
• Context: 32 frames, 8 history samples, 4 future actions

Repository name

• streamvln-satnav: StreamVLN adapted to SatNav
• continue: navigation-pretrained initialization from the StreamVLN checkpoint
• 1ep: trained for one epoch
• f32h8s4: uses 32 frames, eight history samples, and four future actions
• lr2e-5: uses a learning rate of 2e-5

Reference Results

Results reported in the SatNav paper, baseline comparison, row StreamVLN (navigation-pretrained).

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 StreamVLN integration. It is also listed in the SatNav Baseline Model Zoo.

License

The checkpoint is released under CC BY-NC-SA 4.0. StreamVLN, SatNav, model components, and datasets remain subject to their respective terms.