SwiftVLN for SatNav — Reference

Related Repositories

• SwiftVLN: training and evaluation code for these checkpoints.
• SatNav: satellite-image navigation environments, datasets, and evaluation tools.

This checkpoint is designed for SwiftVLN on SatNav, the continuous-state vision-and-language navigation benchmark over satellite imagery. It predicts short navigation-action sequences from an instruction, the current RGB window, and sampled visual memory.

Model

• Starting checkpoint: Qwen/Qwen2.5-VL-3B-Instruct
• Training data: SatNav-v0.1 offline expert trajectories
• Training: 1 epoch, full-parameter fine-tuning, learning rate 2e-5
• Context: 32 RGB frames, up to 8 uniformly sampled history frames
• Prediction horizon: 4 actions
• Memory: per-frame average pooling with stride 2

Repository name

• swiftvln-satnav: SwiftVLN trained and evaluated on SatNav
• 3b: Qwen2.5-VL 3B backbone
• 1ep: trained for one epoch
• f32s4: uses a 32-frame window and predicts four actions
• overlap0: uses non-overlapping training windows
• pf-h8: uses per-frame memory with up to eight history frames
• pool-s2: applies average pooling with stride 2
• noembed: uses no embedding enhancement

Reference Results

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

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 SwiftVLN evaluation guide. Keep the full repository name unchanged because SwiftVLN derives the evaluation configuration from it.

This checkpoint is the reference model in the SwiftVLN SatNav Ablation Model Zoo.