Vamos
🦀
Generate navigation paths on images using prompts
VAMOS: A Hierarchical Vision-Language-Action Model for Capab
This collection contains VLM planner checkpoints, affordance module checkpoints for Spot and HOUND, training datasets, and a demo
Note Try out our demo!
mateoguaman/vamos
Robotics • 3B • Updated • 43Note This model trained WITH navigation data, natural language preference annotations/augmentations, and VQA co-training data. This is our steerable model
mateoguaman/vamos_navigation_only
Robotics • 3B • Updated • 34Note This model was only trained with navigation data, WITHOUT natural language preference annotations/augmentations nor VQA co-training data. We ran real-world navigation experiments with this model.
-
mateoguaman/spot_affordance_model
Updated -
mateoguaman/hound_affordance_model
Updated -
mateoguaman/vamos_dataset
Viewer • Updated • 1.29M • 8 • 1 -
mateoguaman/vamos_navigation_only_dataset
Viewer • Updated • 499k • 91 • 1